diff options
Diffstat (limited to 'clang')
78 files changed, 4676 insertions, 1630 deletions
diff --git a/clang/AreaTeamMembers.txt b/clang/AreaTeamMembers.txt index 964d11e..2928943 100644 --- a/clang/AreaTeamMembers.txt +++ b/clang/AreaTeamMembers.txt @@ -13,5 +13,5 @@ rnk@google.com (email), rnk (Discourse), rnk (GitHub), rnk (Discord) Other Members ------------- Eli Friedman -efriedma@quicinc.com> (email), efriedma-quic (Discourse), efriedma-quic (GitHub) +efriedma@qti.qualcomm.com> (email), efriedma-quic (Discourse), efriedma-quic (GitHub) diff --git a/clang/Maintainers.rst b/clang/Maintainers.rst index 8fb2201..1d16ea9 100644 --- a/clang/Maintainers.rst +++ b/clang/Maintainers.rst @@ -46,7 +46,7 @@ Clang LLVM IR generation | rjmccall\@apple.com (email), rjmccall (Phabricator), rjmccall (GitHub) | Eli Friedman -| efriedma\@quicinc.com (email), efriedma (Phabricator), efriedma-quic (GitHub) +| efriedma\@qti.qualcomm.com (email), efriedma (Phabricator), efriedma-quic (GitHub) | Anton Korobeynikov | anton\@korobeynikov.info (email), asl (Phabricator), asl (GitHub) diff --git a/clang/bindings/python/clang/cindex.py b/clang/bindings/python/clang/cindex.py index 2786add..c48bc9c 100644 --- a/clang/bindings/python/clang/cindex.py +++ b/clang/bindings/python/clang/cindex.py @@ -2363,6 +2363,13 @@ class Cursor(Structure): return conf.lib.clang_getFieldDeclBitWidth(self) # type: ignore [no-any-return] @cursor_null_guard + def is_function_inlined(self) -> bool: + """ + Check if the function is inlined. + """ + return bool(conf.lib.clang_Cursor_isFunctionInlined(self)) + + @cursor_null_guard def has_attrs(self) -> bool: """ Determine whether the given cursor has any attributes. @@ -4310,6 +4317,7 @@ FUNCTION_LIST: list[LibFunc] = [ ("clang_Cursor_isAnonymous", [Cursor], bool), ("clang_Cursor_isAnonymousRecordDecl", [Cursor], bool), ("clang_Cursor_isBitField", [Cursor], bool), + ("clang_Cursor_isFunctionInlined", [Cursor], c_uint), ("clang_Location_isInSystemHeader", [SourceLocation], bool), ("clang_PrintingPolicy_dispose", [PrintingPolicy]), ("clang_PrintingPolicy_getProperty", [PrintingPolicy, c_int], c_uint), diff --git a/clang/bindings/python/tests/cindex/test_cursor.py b/clang/bindings/python/tests/cindex/test_cursor.py index eb0d1d5..7cb616a7 100644 --- a/clang/bindings/python/tests/cindex/test_cursor.py +++ b/clang/bindings/python/tests/cindex/test_cursor.py @@ -784,6 +784,21 @@ int count(int a, int b){ cursor = get_cursor(tu, "reg") self.assertEqual(cursor.storage_class, StorageClass.REGISTER) + def test_function_inlined(self): + tu = get_tu( + """ +inline void f_inline(void); +void f_noninline(void); +int d_noninline; +""" + ) + cursor = get_cursor(tu, "f_inline") + self.assertEqual(cursor.is_function_inlined(), True) + cursor = get_cursor(tu, "f_noninline") + self.assertEqual(cursor.is_function_inlined(), False) + cursor = get_cursor(tu, "d_noninline") + self.assertEqual(cursor.is_function_inlined(), False) + def test_availability(self): tu = get_tu("class A { A(A const&) = delete; };", lang="cpp") diff --git a/clang/docs/AMDGPUSupport.rst b/clang/docs/AMDGPUSupport.rst index 3eada5f..18e3de8 100644 --- a/clang/docs/AMDGPUSupport.rst +++ b/clang/docs/AMDGPUSupport.rst @@ -49,10 +49,6 @@ Predefined Macros - Defined as 1 if the CU mode is enabled and 0 if the WGP mode is enabled. * - ``__AMDGCN_UNSAFE_FP_ATOMICS__`` - Defined if unsafe floating-point atomics are allowed. - * - ``__AMDGCN_WAVEFRONT_SIZE__`` - - Defines the wavefront size. Allowed values are 32 and 64 (deprecated). - * - ``__AMDGCN_WAVEFRONT_SIZE`` - - Alias to ``__AMDGCN_WAVEFRONT_SIZE__`` (deprecated). * - ``__HAS_FMAF__`` - Defined if FMAF instruction is available (deprecated). * - ``__HAS_LDEXPF__`` diff --git a/clang/docs/ClangFormatStyleOptions.rst b/clang/docs/ClangFormatStyleOptions.rst index 570cab2..0b4a484 100644 --- a/clang/docs/ClangFormatStyleOptions.rst +++ b/clang/docs/ClangFormatStyleOptions.rst @@ -197,57 +197,29 @@ the configuration (without a prefix: ``Auto``). .. _AlignAfterOpenBracket: -**AlignAfterOpenBracket** (``BracketAlignmentStyle``) :versionbadge:`clang-format 3.8` :ref:`¶ <AlignAfterOpenBracket>` +**AlignAfterOpenBracket** (``Boolean``) :versionbadge:`clang-format 3.8` :ref:`¶ <AlignAfterOpenBracket>` If ``true``, horizontally aligns arguments after an open bracket. - This applies to round brackets (parentheses), angle brackets and square - brackets. - - Possible values: - - * ``BAS_Align`` (in configuration: ``Align``) - Align parameters on the open bracket, e.g.: - - .. code-block:: c++ - - someLongFunction(argument1, - argument2); - - * ``BAS_DontAlign`` (in configuration: ``DontAlign``) - Don't align, instead use ``ContinuationIndentWidth``, e.g.: - - .. code-block:: c++ - - someLongFunction(argument1, - argument2); - - * ``BAS_AlwaysBreak`` (in configuration: ``AlwaysBreak``) - Always break after an open bracket, if the parameters don't fit - on a single line, e.g.: - - .. code-block:: c++ - someLongFunction( - argument1, argument2); - - * ``BAS_BlockIndent`` (in configuration: ``BlockIndent``) - Always break after an open bracket, if the parameters don't fit - on a single line. Closing brackets will be placed on a new line. - E.g.: - - .. code-block:: c++ + .. code-block:: c++ - someLongFunction( - argument1, argument2 - ) + true: vs. false + someLongFunction(argument1, someLongFunction(argument1, + argument2); argument2); - .. note:: - - This currently only applies to braced initializer lists (when - ``Cpp11BracedListStyle`` is not ``Block``) and parentheses. + .. note:: + As of clang-format 22 this option is a bool with the previous + option of ``Align`` replaced with ``true``, ``DontAlign`` replaced + with ``false``, and the options of ``AlwaysBreak`` and ``BlockIndent`` + replaced with ``true`` and with setting of new style options using + ``BreakAfterOpenBracketBracedList``, ``BreakAfterOpenBracketFunction``, + ``BreakAfterOpenBracketIf``, ``BreakBeforeCloseBracketBracedList``, + ``BreakBeforeCloseBracketFunction``, and ``BreakBeforeCloseBracketIf``. + This applies to round brackets (parentheses), angle brackets and square + brackets. .. _AlignArrayOfStructures: @@ -2746,6 +2718,67 @@ the configuration (without a prefix: ``Auto``). @Mock DataLoad loader; +.. _BreakAfterOpenBracketBracedList: + +**BreakAfterOpenBracketBracedList** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakAfterOpenBracketBracedList>` + Force break after the left bracket of a braced initializer list (when + ``Cpp11BracedListStyle`` is ``true``) when the list exceeds the column + limit. + + .. code-block:: c++ + + true: false: + vector<int> x { vs. vector<int> x {1, + 1, 2, 3} 2, 3} + +.. _BreakAfterOpenBracketFunction: + +**BreakAfterOpenBracketFunction** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakAfterOpenBracketFunction>` + Force break after the left parenthesis of a function (declaration, + definition, call) when the parameters exceed the column limit. + + .. code-block:: c++ + + true: false: + foo ( vs. foo (a, + a , b) b) + +.. _BreakAfterOpenBracketIf: + +**BreakAfterOpenBracketIf** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakAfterOpenBracketIf>` + Force break after the left parenthesis of an if control statement + when the expression exceeds the column limit. + + .. code-block:: c++ + + true: false: + if constexpr ( vs. if constexpr (a || + a || b) b) + +.. _BreakAfterOpenBracketLoop: + +**BreakAfterOpenBracketLoop** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakAfterOpenBracketLoop>` + Force break after the left parenthesis of a loop control statement + when the expression exceeds the column limit. + + .. code-block:: c++ + + true: false: + while ( vs. while (a && + a && b) { b) { + +.. _BreakAfterOpenBracketSwitch: + +**BreakAfterOpenBracketSwitch** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakAfterOpenBracketSwitch>` + Force break after the left parenthesis of a switch control statement + when the expression exceeds the column limit. + + .. code-block:: c++ + + true: false: + switch ( vs. switch (a + + a + b) { b) { + .. _BreakAfterReturnType: **BreakAfterReturnType** (``ReturnTypeBreakingStyle``) :versionbadge:`clang-format 19` :ref:`¶ <BreakAfterReturnType>` @@ -3383,6 +3416,79 @@ the configuration (without a prefix: ``Auto``). +.. _BreakBeforeCloseBracketBracedList: + +**BreakBeforeCloseBracketBracedList** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakBeforeCloseBracketBracedList>` + Force break before the right bracket of a braced initializer list (when + ``Cpp11BracedListStyle`` is ``true``) when the list exceeds the column + limit. The break before the right bracket is only made if there is a + break after the opening bracket. + + .. code-block:: c++ + + true: false: + vector<int> x { vs. vector<int> x { + 1, 2, 3 1, 2, 3} + } + +.. _BreakBeforeCloseBracketFunction: + +**BreakBeforeCloseBracketFunction** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakBeforeCloseBracketFunction>` + Force break before the right parenthesis of a function (declaration, + definition, call) when the parameters exceed the column limit. + + .. code-block:: c++ + + true: false: + foo ( vs. foo ( + a , b a , b) + ) + +.. _BreakBeforeCloseBracketIf: + +**BreakBeforeCloseBracketIf** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakBeforeCloseBracketIf>` + Force break before the right parenthesis of an if control statement + when the expression exceeds the column limit. The break before the + closing parenthesis is only made if there is a break after the opening + parenthesis. + + .. code-block:: c++ + + true: false: + if constexpr ( vs. if constexpr ( + a || b a || b ) + ) + +.. _BreakBeforeCloseBracketLoop: + +**BreakBeforeCloseBracketLoop** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakBeforeCloseBracketLoop>` + Force break before the right parenthesis of a loop control statement + when the expression exceeds the column limit. The break before the + closing parenthesis is only made if there is a break after the opening + parenthesis. + + .. code-block:: c++ + + true: false: + while ( vs. while ( + a && b a && b) { + ) { + +.. _BreakBeforeCloseBracketSwitch: + +**BreakBeforeCloseBracketSwitch** (``Boolean``) :versionbadge:`clang-format 22` :ref:`¶ <BreakBeforeCloseBracketSwitch>` + Force break before the right parenthesis of a switch control statement + when the expression exceeds the column limit. The break before the + closing parenthesis is only made if there is a break after the opening + parenthesis. + + .. code-block:: c++ + + true: false: + switch ( vs. switch ( + a + b a + b) { + ) { + .. _BreakBeforeConceptDeclarations: **BreakBeforeConceptDeclarations** (``BreakBeforeConceptDeclarationsStyle``) :versionbadge:`clang-format 12` :ref:`¶ <BreakBeforeConceptDeclarations>` diff --git a/clang/docs/HIPSupport.rst b/clang/docs/HIPSupport.rst index ec2af2a..ab9ea11 100644 --- a/clang/docs/HIPSupport.rst +++ b/clang/docs/HIPSupport.rst @@ -180,8 +180,7 @@ Predefined Macros - Alias to ``__HIP_API_PER_THREAD_DEFAULT_STREAM__``. Deprecated. Note that some architecture specific AMDGPU macros will have default values when -used from the HIP host compilation. Other :doc:`AMDGPU macros <AMDGPUSupport>` -like ``__AMDGCN_WAVEFRONT_SIZE__`` (deprecated) will default to 64 for example. +used from the HIP host compilation. Compilation Modes ================= diff --git a/clang/docs/Modules.rst b/clang/docs/Modules.rst index acbe45e..e45ee9f 100644 --- a/clang/docs/Modules.rst +++ b/clang/docs/Modules.rst @@ -421,13 +421,7 @@ As an example, the module map file for the C standard library might look a bit l .. parsed-literal:: - module std [system] [extern_c] { - module assert { - textual header "assert.h" - header "bits/assert-decls.h" - export * - } - + module std [system] { module complex { header "complex.h" export * @@ -440,7 +434,6 @@ As an example, the module map file for the C standard library might look a bit l module errno { header "errno.h" - header "sys/errno.h" export * } @@ -673,14 +666,14 @@ of checking *use-declaration*\s, and must still be a lexically-valid header file. In the future, we intend to pre-tokenize such headers and include the token sequence within the prebuilt module representation. -A header with the ``exclude`` specifier is excluded from the module. It will not be included when the module is built, nor will it be considered to be part of the module, even if an ``umbrella`` header or directory would otherwise make it part of the module. +A header with the ``exclude`` specifier is excluded from the module. It will not be included when the module is built, nor will it be considered to be part of the module, even if an ``umbrella`` directory would otherwise make it part of the module. -**Example:** The C header ``assert.h`` is an excellent candidate for a textual header, because it is meant to be included multiple times (possibly with different ``NDEBUG`` settings). However, declarations within it should typically be split into a separate modular header. +**Example:** A "X macro" header is an excellent candidate for a textual header, because it is can't be compiled standalone, and by itself does not contain any declarations. .. parsed-literal:: - module std [system] { - textual header "assert.h" + module MyLib [system] { + textual header "xmacros.h" } A given header shall not be referenced by more than one *header-declaration*. diff --git a/clang/docs/OpenMPSupport.rst b/clang/docs/OpenMPSupport.rst index 61b5bab..10a8d09 100644 --- a/clang/docs/OpenMPSupport.rst +++ b/clang/docs/OpenMPSupport.rst @@ -1,662 +1,662 @@ -.. raw:: html
-
- <style type="text/css">
- .none { background-color: #FFCCCC }
- .part { background-color: #FFFF99 }
- .good { background-color: #CCFF99 }
- </style>
-
-.. role:: none
-.. role:: part
-.. role:: good
-
-.. contents::
- :local:
-
-==============
-OpenMP Support
-==============
-
-Clang fully supports OpenMP 4.5, almost all of 5.0 and most of 5.1/2.
-Clang supports offloading to X86_64, AArch64, PPC64[LE], NVIDIA GPUs (all models) and AMD GPUs (all models).
-
-In addition, the LLVM OpenMP runtime `libomp` supports the OpenMP Tools
-Interface (OMPT) on x86, x86_64, AArch64, and PPC64 on Linux, Windows, and macOS.
-OMPT is also supported for NVIDIA and AMD GPUs.
-
-For the list of supported features from OpenMP 5.0 and 5.1
-see `OpenMP implementation details`_ and `OpenMP 51 implementation details`_.
-
-General improvements
-====================
-- New collapse clause scheme to avoid expensive remainder operations.
- Compute loop index variables after collapsing a loop nest via the
- collapse clause by replacing the expensive remainder operation with
- multiplications and additions.
-
-- When using the collapse clause on a loop nest the default behavior
- is to automatically extend the representation of the loop counter to
- 64 bits for the cases where the sizes of the collapsed loops are not
- known at compile time. To prevent this conservative choice and use
- at most 32 bits, compile your program with the
- `-fopenmp-optimistic-collapse`.
-
-
-GPU devices support
-===================
-
-Data-sharing modes
-------------------
-
-Clang supports two data-sharing models for Cuda devices: `Generic` and `Cuda`
-modes. The default mode is `Generic`. `Cuda` mode can give an additional
-performance and can be activated using the `-fopenmp-cuda-mode` flag. In
-`Generic` mode all local variables that can be shared in the parallel regions
-are stored in the global memory. In `Cuda` mode local variables are not shared
-between the threads and it is user responsibility to share the required data
-between the threads in the parallel regions. Often, the optimizer is able to
-reduce the cost of `Generic` mode to the level of `Cuda` mode, but the flag,
-as well as other assumption flags, can be used for tuning.
-
-Features not supported or with limited support for Cuda devices
----------------------------------------------------------------
-
-- Cancellation constructs are not supported.
-
-- Doacross loop nest is not supported.
-
-- User-defined reductions are supported only for trivial types.
-
-- Nested parallelism: inner parallel regions are executed sequentially.
-
-- Debug information for OpenMP target regions is supported, but sometimes it may
- be required to manually specify the address class of the inspected variables.
- In some cases the local variables are actually allocated in the global memory,
- but the debug info may be not aware of it.
-
-
-.. _OpenMP implementation details:
-
-OpenMP 5.0 Implementation Details
-=================================
-
-The following table provides a quick overview over various OpenMP 5.0 features
-and their implementation status. Please post on the
-`Discourse forums (Runtimes - OpenMP category)`_ for more
-information or if you want to help with the
-implementation.
-
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-|Category | Feature | Status | Reviews |
-+==============================+==============================================================+==========================+=======================================================================+
-| loop | support != in the canonical loop form | :good:`done` | D54441 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | #pragma omp loop (directive) | :part:`partial` | D145823 (combined forms) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | #pragma omp loop bind | :part:`worked on` | D144634 (needs review) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | collapse imperfectly nested loop | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | collapse non-rectangular nested loop | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | C++ range-base for loop | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | clause: if for SIMD directives | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | inclusive scan (matching C++17 PSTL) | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory management | memory allocators | :good:`done` | r341687,r357929 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory management | allocate directive and allocate clause | :good:`done` | r355614,r335952 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| OMPD | OMPD interfaces | :good:`done` | https://reviews.llvm.org/D99914 (Supports only HOST(CPU) and Linux |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| OMPT | OMPT interfaces (callback support) | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| thread affinity | thread affinity | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | taskloop reduction | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | task affinity | :part:`not upstream` | https://github.com/jklinkenberg/openmp/tree/task-affinity |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | clause: depend on the taskwait construct | :good:`done` | D113540 (regular codegen only) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | depend objects and detachable tasks | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | mutexinoutset dependence-type for tasks | :good:`done` | D53380,D57576 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | combined taskloop constructs | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | master taskloop | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | parallel master taskloop | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | master taskloop simd | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | parallel master taskloop simd | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| SIMD | atomic and simd constructs inside SIMD code | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| SIMD | SIMD nontemporal | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | infer target functions from initializers | :part:`worked on` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | infer target variables from initializers | :good:`done` | D146418 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | OMP_TARGET_OFFLOAD environment variable | :good:`done` | D50522 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | support full 'defaultmap' functionality | :good:`done` | D69204 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | device specific functions | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: device_type | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: extended device | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: uses_allocators clause | :good:`done` | https://github.com/llvm/llvm-project/pull/157025 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: in_reduction | :part:`worked on` | r308768 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | omp_get_device_num() | :good:`done` | D54342,D128347 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | structure mapping of references | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | nested target declare | :good:`done` | D51378 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | implicitly map 'this' (this[:1]) | :good:`done` | D55982 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | allow access to the reference count (omp_target_is_present) | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | requires directive | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: unified_shared_memory | :good:`done` | D52625,D52359 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: unified_address | :part:`partial` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: reverse_offload | :part:`partial` | D52780,D155003 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: atomic_default_mem_order | :good:`done` | D53513 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: dynamic_allocators | :part:`unclaimed parts` | D53079 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | user-defined mappers | :good:`done` | D56326,D58638,D58523,D58074,D60972,D59474 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | map array-section with implicit mapper | :good:`done` | https://github.com/llvm/llvm-project/pull/101101 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | mapping lambda expression | :good:`done` | D51107 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | clause: use_device_addr for target data | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | support close modifier on map clause | :good:`done` | D55719,D55892 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | teams construct on the host device | :good:`done` | r371553 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | support non-contiguous array sections for target update | :good:`done` | https://github.com/llvm/llvm-project/pull/144635 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | pointer attachment | :part:`being repaired` | @abhinavgaba (https://github.com/llvm/llvm-project/pull/153683) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| atomic | hints for the atomic construct | :good:`done` | D51233 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| base language | C11 support | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| base language | C++11/14/17 support | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| base language | lambda support | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | array shaping | :good:`done` | D74144 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | library shutdown (omp_pause_resource[_all]) | :good:`done` | D55078 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | metadirectives | :part:`mostly done` | D91944, https://github.com/llvm/llvm-project/pull/128640 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | conditional modifier for lastprivate clause | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | iterator and multidependences | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | depobj directive and depobj dependency kind | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | user-defined function variants | :good:`done`. | D67294, D64095, D71847, D71830, D109635 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | pointer/reference to pointer based array reductions | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | prevent new type definitions in clauses | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory model | memory model update (seq_cst, acq_rel, release, acquire,...) | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-
-
-.. _OpenMP 51 implementation details:
-
-OpenMP 5.1 Implementation Details
-=================================
-
-The following table provides a quick overview over various OpenMP 5.1 features
-and their implementation status.
-Please post on the
-`Discourse forums (Runtimes - OpenMP category)`_ for more
-information or if you want to help with the
-implementation.
-
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-|Category | Feature | Status | Reviews |
-+==============================+==============================================================+==========================+=======================================================================+
-| atomic | 'compare' clause on atomic construct | :good:`done` | D120290, D120007, D118632, D120200, D116261, D118547, D116637 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| atomic | 'fail' clause on atomic construct | :part:`worked on` | D123235 (in progress) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| base language | C++ attribute specifier syntax | :good:`done` | D105648 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | 'present' map type modifier | :good:`done` | D83061, D83062, D84422 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | 'present' motion modifier | :good:`done` | D84711, D84712 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | 'present' in defaultmap clause | :good:`done` | D92427 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | map clause reordering based on 'present' modifier | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | device-specific environment variables | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | omp_target_is_accessible routine | :good:`done` | https://github.com/llvm/llvm-project/pull/138294 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | omp_get_mapped_ptr routine | :good:`done` | D141545 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | new async target memory copy routines | :good:`done` | D136103 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | thread_limit clause on target construct | :part:`partial` | D141540 (offload), D152054 (host, in progress) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | has_device_addr clause on target construct | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | iterators in map clause or motion clauses | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | indirect clause on declare target directive | :part:`In Progress` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | allow virtual functions calls for mapped object on device | :part:`partial` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | interop construct | :part:`partial` | parsing/sema done: D98558, D98834, D98815 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| device | assorted routines for querying interoperable properties | :part:`partial` | D106674 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | Loop tiling transformation | :good:`done` | D76342 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | Loop unrolling transformation | :good:`done` | D99459 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| loop | 'reproducible'/'unconstrained' modifiers in 'order' clause | :part:`partial` | D127855 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory management | alignment for allocate directive and clause | :good:`done` | D115683 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory management | 'allocator' modifier for allocate clause | :good:`done` | https://github.com/llvm/llvm-project/pull/114883 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory management | 'align' modifier for allocate clause | :good:`done` | https://github.com/llvm/llvm-project/pull/121814 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory management | new memory management routines | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory management | changes to omp_alloctrait_key enum | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| memory model | seq_cst clause on flush construct | :good:`done` | https://github.com/llvm/llvm-project/pull/114072 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | 'omp_all_memory' keyword and use in 'depend' clause | :good:`done` | D125828, D126321 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | error directive | :good:`done` | D139166 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | scope construct | :good:`done` | D157933, https://github.com/llvm/llvm-project/pull/109197 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | routines for controlling and querying team regions | :part:`partial` | D95003 (libomp only) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | changes to ompt_scope_endpoint_t enum | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | omp_display_env routine | :good:`done` | D74956 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | extended OMP_PLACES syntax | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | OMP_NUM_TEAMS and OMP_TEAMS_THREAD_LIMIT env vars | :good:`done` | D138769 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | 'target_device' selector in context specifier | :none:`worked on` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | begin/end declare variant | :good:`done` | D71179 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | dispatch construct and function variant argument adjustment | :part:`worked on` | D99537, D99679 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | assumes directives | :part:`worked on` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | assume directive | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | nothing directive | :good:`done` | D123286 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | masked construct and related combined constructs | :good:`done` | D99995, D100514, PR-121741(parallel_masked_taskloop) |
-| | | | PR-121746(parallel_masked_task_loop_simd),PR-121914(masked_taskloop) |
-| | | | PR-121916(masked_taskloop_simd) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc | default(firstprivate) & default(private) | :good:`done` | D75591 (firstprivate), D125912 (private) |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| other | deprecating master construct | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| OMPT | new barrier types added to ompt_sync_region_t enum | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| OMPT | async data transfers added to ompt_target_data_op_t enum | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| OMPT | new barrier state values added to ompt_state_t enum | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| OMPT | new 'emi' callbacks for external monitoring interfaces | :good:`done` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| OMPT | device tracing interface | :none:`in progress` | jplehr |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | 'strict' modifier for taskloop construct | :none:`unclaimed` | |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | inoutset in depend clause | :good:`done` | D97085, D118383 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| task | nowait clause on taskwait | :part:`partial` | parsing/sema done: D131830, D141531 |
-+------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-
-
-.. _OpenMP 5.2 implementation details:
-
-OpenMP 5.2 Implementation Details
-=================================
-
-The following table provides a quick overview of various OpenMP 5.2 features
-and their implementation status. Please post on the
-`Discourse forums (Runtimes - OpenMP category)`_ for more
-information or if you want to help with the
-implementation.
-
-
-
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-|Feature | C/C++ Status | Fortran Status | Reviews |
-+=============================================================+===========================+===========================+==========================================================================+
-| omp_in_explicit_task() | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| semantics of explicit_task_var and implicit_task_var | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| ompx sentinel for C/C++ directive extensions | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| ompx prefix for clause extensions | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| if clause on teams construct | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| step modifier added | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| declare mapper: Add iterator modifier on map clause | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| declare mapper: Add iterator modifier on map clause | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| memspace and traits modifiers to uses allocator i | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Add otherwise clause to metadirectives | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| doacross clause with support for omp_cur_iteration | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| position of interop_type in init clause on iterop | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| implicit map type for target enter/exit data | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| work OMPT type for work-sharing loop constructs | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| allocate and firstprivate on scope directive | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Change loop consistency for order clause | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Add memspace and traits modifiers to uses_allocators | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Keep original base pointer on map w/o matched candidate | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Pure procedure support for certain directives | :none:`N/A` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| ALLOCATE statement support for allocators | :none:`N/A` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| dispatch construct extension to support end directive | :none:`N/A` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-
-
-
-.. _OpenMP 5.2 Deprecations:
-
-OpenMP 5.2 Deprecations
-=======================
-
-
-
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| | C/C++ Status | Fortran Status | Reviews |
-+=============================================================+===========================+===========================+==========================================================================+
-| Linear clause syntax | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| The minus operator | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Map clause modifiers without commas | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| The use of allocate directives with ALLOCATE statement | :good:`N/A` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| uses_allocators list syntax | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| The default clause on metadirectives | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| The delimited form of the declare target directive | :none:`unclaimed` | :good:`N/A` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| The use of the to clause on the declare target directive | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| The syntax of the destroy clause on the depobj construct | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| keyword source and sink as task-dependence modifiers | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| interop types in any position on init clause of interop | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| ompd prefix usage for some ICVs | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-
-.. _OpenMP 6.0 implementation details:
-
-OpenMP 6.0 Implementation Details
-=================================
-
-The following table provides a quick overview of various OpenMP 6.0 features
-and their implementation status. Please post on the
-`Discourse forums (Runtimes - OpenMP category)`_ for more
-information or if you want to help with the
-implementation.
-
-
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-|Feature | C/C++ Status | Fortran Status | Reviews |
-+=============================================================+===========================+===========================+==========================================================================+
-| free-agent threads | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| threadset clause | :part:`in progress` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Recording of task graphs | :part:`in progress` | :part:`in progress` | clang: jtb20, flang: kparzysz |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Parallel inductions | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| init_complete for scan directive | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop interchange transformation | :good:`done` | :none:`unclaimed` | Clang (interchange): https://github.com/llvm/llvm-project/pull/93022 |
-| | | | Clang (permutation): https://github.com/llvm/llvm-project/pull/92030 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop reverse transformation | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/92916 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop stripe transformation | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/119891 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop fusion transformation | :part:`in progress` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/139293 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop index set splitting transformation | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop transformation apply clause | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop fuse transformation | :good:`done` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| workdistribute construct | | :none:`in progress` | @skc7, @mjklemm |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| task_iteration | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| memscope clause for atomic and flush | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| transparent clause (hull tasks) | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| rule-based compound directives | :part:`In Progress` | :part:`In Progress` | kparzysz |
-| | | | Testing for Fortran missing |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| C23, C++23 | :none:`unclaimed` | | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Fortran 2023 | | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| decl attribute for declarative directives | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| C attribute syntax | :none:`unclaimed` | | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| pure directives in DO CONCURRENT | | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Optional argument for all clauses | :none:`partial` | :none:`In Progress` | Parse/Sema (nowait): https://github.com/llvm/llvm-project/pull/159628 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Function references for locator list items | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| All clauses accept directive name modifier | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Extensions to depobj construct | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Extensions to atomic construct | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Private reductions | :good:`mostly` | :none:`unclaimed` | Parse/Sema:https://github.com/llvm/llvm-project/pull/129938 |
-| | | | Codegen: https://github.com/llvm/llvm-project/pull/134709 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Self maps | :part:`partial` | :none:`unclaimed` | parsing/sema done: https://github.com/llvm/llvm-project/pull/129888 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Release map type for declare mapper | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Extensions to interop construct | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| no_openmp_constructs | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/125933 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| safe_sync and progress with identifier and API | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| OpenMP directives in concurrent loop regions | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/125621 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| atomics constructs on concurrent loop regions | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/125621 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Loop construct with DO CONCURRENT | | :part:`In Progress` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| device_type clause for target construct | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| nowait for ancestor target directives | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| New API for devices' num_teams/thread_limit | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Host and device environment variables | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| num_threads ICV and clause accepts list | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Numeric names for environment variables | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Increment between places for OMP_PLACES | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| OMP_AVAILABLE_DEVICES envirable | :none:`unclaimed` | :none:`unclaimed` | (should wait for "Traits for default device envirable" being done) |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Traits for default device envirable | :part:`in progress` | :none:`unclaimed` | ro-i |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Optionally omit array length expression | :good:`done` | :none:`unclaimed` | (Parse) https://github.com/llvm/llvm-project/pull/148048, |
-| | | | (Sema) https://github.com/llvm/llvm-project/pull/152786 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Canonical loop sequences | :part:`in progress` | :part:`in progress` | Clang: https://github.com/llvm/llvm-project/pull/139293 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Clarifications to Fortran map semantics | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| default clause at target construct | :part:`In Progress` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| ref count update use_device_{ptr, addr} | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Clarifications to implicit reductions | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| ref modifier for map clauses | :part:`In Progress` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| map-type modifiers in arbitrary position | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/90499 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Lift nesting restriction on concurrent loop | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/125621 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| priority clause for target constructs | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| changes to target_data construct | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Non-const do_not_sync for nowait/nogroup | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| need_device_addr modifier for adjust_args clause | :part:`partial` | :none:`unclaimed` | Parsing/Sema: https://github.com/llvm/llvm-project/pull/143442 |
-| | | | https://github.com/llvm/llvm-project/pull/149586 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Prescriptive num_threads | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/160659 |
-| | | | https://github.com/llvm/llvm-project/pull/146403 |
-| | | | https://github.com/llvm/llvm-project/pull/146404 |
-| | | | https://github.com/llvm/llvm-project/pull/146405 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Message and severity clauses | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/146093 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Local clause on declare target | :part:`In Progress` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| groupprivate directive | :part:`In Progress` | :part:`partial` | Flang: kparzysz, mjklemm |
-| | | | |
-| | | | Flang parser: https://github.com/llvm/llvm-project/pull/153807 |
-| | | | Flang sema: https://github.com/llvm/llvm-project/pull/154779 |
-| | | | Clang parse/sema: https://github.com/llvm/llvm-project/pull/158134 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| variable-category on default clause | :good:`done` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Changes to omp_target_is_accessible | :part:`In Progress` | :part:`In Progress` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| defaultmap implicit-behavior 'storage' | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/158336 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| defaultmap implicit-behavior 'private' | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/158712 |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-
-.. _OpenMP 6.1 implementation details:
-
-OpenMP 6.1 Implementation Details (Experimental)
-================================================
-
-The following table provides a quick overview over various OpenMP 6.1 features
-and their implementation status. Since OpenMP 6.1 has not yet been released, the
-following features are experimental and are subject to change at any time.
-Please post on the `Discourse forums (Runtimes - OpenMP category)`_ for more
-information or if you want to help with the
-implementation.
-
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-|Feature | C/C++ Status | Fortran Status | Reviews |
-+=============================================================+===========================+===========================+==========================================================================+
-| dyn_groupprivate clause | :part:`In Progress` | :part:`In Progress` | C/C++: kevinsala (https://github.com/llvm/llvm-project/pull/152651 |
-| | | | https://github.com/llvm/llvm-project/pull/152830 |
-| | | | https://github.com/llvm/llvm-project/pull/152831) |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop flatten transformation | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| loop grid/tile modifiers for sizes clause | :none:`unclaimed` | :none:`unclaimed` | |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| attach map-type modifier | :part:`In Progress` | :none:`unclaimed` | C/C++: @abhinavgaba; |
-| | | | RT: @abhinavgaba (https://github.com/llvm/llvm-project/pull/149036, |
-| | | | https://github.com/llvm/llvm-project/pull/158370) |
-+-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-
-
-OpenMP Extensions
-=================
-
-The following table provides a quick overview over various OpenMP
-extensions and their implementation status. These extensions are not
-currently defined by any standard, so links to associated LLVM
-documentation are provided. As these extensions mature, they will be
-considered for standardization. Please post on the
-`Discourse forums (Runtimes - OpenMP category)`_ to provide feedback.
-
-+------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+
-|Category | Feature | Status | Reviews |
-+==============================+===================================================================================+==========================+========================================================+
-| atomic extension | `'atomic' strictly nested within 'teams' | :good:`prototyped` | D126323 |
-| | <https://openmp.llvm.org/docs/openacc/OpenMPExtensions.html#atomicWithinTeams>`_ | | |
-+------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+
-| device extension | `'ompx_hold' map type modifier | :good:`prototyped` | D106509, D106510 |
-| | <https://openmp.llvm.org/docs/openacc/OpenMPExtensions.html#ompx-hold>`_ | | |
-+------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+
-| device extension | `'ompx_bare' clause on 'target teams' construct | :good:`prototyped` | #66844, #70612 |
-| | <https://www.osti.gov/servlets/purl/2205717>`_ | | |
-+------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+
-| device extension | Multi-dim 'num_teams' and 'thread_limit' clause on 'target teams ompx_bare' | :good:`partial` | #99732, #101407, #102715 |
-| | construct | | |
-+------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+
-
-.. _Discourse forums (Runtimes - OpenMP category): https://discourse.llvm.org/c/runtimes/openmp/35
+.. raw:: html + + <style type="text/css"> + .none { background-color: #FFCCCC } + .part { background-color: #FFFF99 } + .good { background-color: #CCFF99 } + </style> + +.. role:: none +.. role:: part +.. role:: good + +.. contents:: + :local: + +============== +OpenMP Support +============== + +Clang fully supports OpenMP 4.5, almost all of 5.0 and most of 5.1/2. +Clang supports offloading to X86_64, AArch64, PPC64[LE], NVIDIA GPUs (all models) and AMD GPUs (all models). + +In addition, the LLVM OpenMP runtime `libomp` supports the OpenMP Tools +Interface (OMPT) on x86, x86_64, AArch64, and PPC64 on Linux, Windows, and macOS. +OMPT is also supported for NVIDIA and AMD GPUs. + +For the list of supported features from OpenMP 5.0 and 5.1 +see `OpenMP implementation details`_ and `OpenMP 51 implementation details`_. + +General improvements +==================== +- New collapse clause scheme to avoid expensive remainder operations. + Compute loop index variables after collapsing a loop nest via the + collapse clause by replacing the expensive remainder operation with + multiplications and additions. + +- When using the collapse clause on a loop nest the default behavior + is to automatically extend the representation of the loop counter to + 64 bits for the cases where the sizes of the collapsed loops are not + known at compile time. To prevent this conservative choice and use + at most 32 bits, compile your program with the + `-fopenmp-optimistic-collapse`. + + +GPU devices support +=================== + +Data-sharing modes +------------------ + +Clang supports two data-sharing models for Cuda devices: `Generic` and `Cuda` +modes. The default mode is `Generic`. `Cuda` mode can give an additional +performance and can be activated using the `-fopenmp-cuda-mode` flag. In +`Generic` mode all local variables that can be shared in the parallel regions +are stored in the global memory. In `Cuda` mode local variables are not shared +between the threads and it is user responsibility to share the required data +between the threads in the parallel regions. Often, the optimizer is able to +reduce the cost of `Generic` mode to the level of `Cuda` mode, but the flag, +as well as other assumption flags, can be used for tuning. + +Features not supported or with limited support for Cuda devices +--------------------------------------------------------------- + +- Cancellation constructs are not supported. + +- Doacross loop nest is not supported. + +- User-defined reductions are supported only for trivial types. + +- Nested parallelism: inner parallel regions are executed sequentially. + +- Debug information for OpenMP target regions is supported, but sometimes it may + be required to manually specify the address class of the inspected variables. + In some cases the local variables are actually allocated in the global memory, + but the debug info may be not aware of it. + + +.. _OpenMP implementation details: + +OpenMP 5.0 Implementation Details +================================= + +The following table provides a quick overview over various OpenMP 5.0 features +and their implementation status. Please post on the +`Discourse forums (Runtimes - OpenMP category)`_ for more +information or if you want to help with the +implementation. + ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +|Category | Feature | Status | Reviews | ++==============================+==============================================================+==========================+=======================================================================+ +| loop | support != in the canonical loop form | :good:`done` | D54441 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | #pragma omp loop (directive) | :part:`partial` | D145823 (combined forms) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | #pragma omp loop bind | :part:`worked on` | D144634 (needs review) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | collapse imperfectly nested loop | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | collapse non-rectangular nested loop | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | C++ range-base for loop | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | clause: if for SIMD directives | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | inclusive scan (matching C++17 PSTL) | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory management | memory allocators | :good:`done` | r341687,r357929 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory management | allocate directive and allocate clause | :good:`done` | r355614,r335952 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| OMPD | OMPD interfaces | :good:`done` | https://reviews.llvm.org/D99914 (Supports only HOST(CPU) and Linux | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| OMPT | OMPT interfaces (callback support) | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| thread affinity | thread affinity | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | taskloop reduction | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | task affinity | :part:`not upstream` | https://github.com/jklinkenberg/openmp/tree/task-affinity | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | clause: depend on the taskwait construct | :good:`done` | D113540 (regular codegen only) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | depend objects and detachable tasks | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | mutexinoutset dependence-type for tasks | :good:`done` | D53380,D57576 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | combined taskloop constructs | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | master taskloop | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | parallel master taskloop | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | master taskloop simd | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | parallel master taskloop simd | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| SIMD | atomic and simd constructs inside SIMD code | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| SIMD | SIMD nontemporal | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | infer target functions from initializers | :part:`worked on` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | infer target variables from initializers | :good:`done` | D146418 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | OMP_TARGET_OFFLOAD environment variable | :good:`done` | D50522 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | support full 'defaultmap' functionality | :good:`done` | D69204 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | device specific functions | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: device_type | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: extended device | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: uses_allocators clause | :good:`done` | https://github.com/llvm/llvm-project/pull/157025 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: in_reduction | :part:`worked on` | r308768 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | omp_get_device_num() | :good:`done` | D54342,D128347 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | structure mapping of references | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | nested target declare | :good:`done` | D51378 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | implicitly map 'this' (this[:1]) | :good:`done` | D55982 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | allow access to the reference count (omp_target_is_present) | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | requires directive | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: unified_shared_memory | :good:`done` | D52625,D52359 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: unified_address | :part:`partial` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: reverse_offload | :part:`partial` | D52780,D155003 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: atomic_default_mem_order | :good:`done` | D53513 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: dynamic_allocators | :part:`unclaimed parts` | D53079 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | user-defined mappers | :good:`done` | D56326,D58638,D58523,D58074,D60972,D59474 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | map array-section with implicit mapper | :good:`done` | https://github.com/llvm/llvm-project/pull/101101 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | mapping lambda expression | :good:`done` | D51107 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | clause: use_device_addr for target data | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | support close modifier on map clause | :good:`done` | D55719,D55892 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | teams construct on the host device | :good:`done` | r371553 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | support non-contiguous array sections for target update | :good:`done` | https://github.com/llvm/llvm-project/pull/144635 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | pointer attachment | :part:`being repaired` | @abhinavgaba (https://github.com/llvm/llvm-project/pull/153683) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| atomic | hints for the atomic construct | :good:`done` | D51233 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| base language | C11 support | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| base language | C++11/14/17 support | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| base language | lambda support | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | array shaping | :good:`done` | D74144 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | library shutdown (omp_pause_resource[_all]) | :good:`done` | D55078 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | metadirectives | :part:`mostly done` | D91944, https://github.com/llvm/llvm-project/pull/128640 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | conditional modifier for lastprivate clause | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | iterator and multidependences | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | depobj directive and depobj dependency kind | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | user-defined function variants | :good:`done`. | D67294, D64095, D71847, D71830, D109635 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | pointer/reference to pointer based array reductions | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | prevent new type definitions in clauses | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory model | memory model update (seq_cst, acq_rel, release, acquire,...) | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ + + +.. _OpenMP 51 implementation details: + +OpenMP 5.1 Implementation Details +================================= + +The following table provides a quick overview over various OpenMP 5.1 features +and their implementation status. +Please post on the +`Discourse forums (Runtimes - OpenMP category)`_ for more +information or if you want to help with the +implementation. + ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +|Category | Feature | Status | Reviews | ++==============================+==============================================================+==========================+=======================================================================+ +| atomic | 'compare' clause on atomic construct | :good:`done` | D120290, D120007, D118632, D120200, D116261, D118547, D116637 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| atomic | 'fail' clause on atomic construct | :part:`worked on` | D123235 (in progress) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| base language | C++ attribute specifier syntax | :good:`done` | D105648 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | 'present' map type modifier | :good:`done` | D83061, D83062, D84422 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | 'present' motion modifier | :good:`done` | D84711, D84712 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | 'present' in defaultmap clause | :good:`done` | D92427 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | map clause reordering based on 'present' modifier | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | device-specific environment variables | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | omp_target_is_accessible routine | :good:`done` | https://github.com/llvm/llvm-project/pull/138294 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | omp_get_mapped_ptr routine | :good:`done` | D141545 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | new async target memory copy routines | :good:`done` | D136103 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | thread_limit clause on target construct | :part:`partial` | D141540 (offload), D152054 (host, in progress) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | has_device_addr clause on target construct | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | iterators in map clause or motion clauses | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | indirect clause on declare target directive | :part:`In Progress` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | allow virtual functions calls for mapped object on device | :part:`partial` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | interop construct | :part:`partial` | parsing/sema done: D98558, D98834, D98815 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| device | assorted routines for querying interoperable properties | :part:`partial` | D106674 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | Loop tiling transformation | :good:`done` | D76342 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | Loop unrolling transformation | :good:`done` | D99459 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| loop | 'reproducible'/'unconstrained' modifiers in 'order' clause | :part:`partial` | D127855 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory management | alignment for allocate directive and clause | :good:`done` | D115683 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory management | 'allocator' modifier for allocate clause | :good:`done` | https://github.com/llvm/llvm-project/pull/114883 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory management | 'align' modifier for allocate clause | :good:`done` | https://github.com/llvm/llvm-project/pull/121814 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory management | new memory management routines | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory management | changes to omp_alloctrait_key enum | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| memory model | seq_cst clause on flush construct | :good:`done` | https://github.com/llvm/llvm-project/pull/114072 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | 'omp_all_memory' keyword and use in 'depend' clause | :good:`done` | D125828, D126321 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | error directive | :good:`done` | D139166 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | scope construct | :good:`done` | D157933, https://github.com/llvm/llvm-project/pull/109197 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | routines for controlling and querying team regions | :part:`partial` | D95003 (libomp only) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | changes to ompt_scope_endpoint_t enum | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | omp_display_env routine | :good:`done` | D74956 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | extended OMP_PLACES syntax | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | OMP_NUM_TEAMS and OMP_TEAMS_THREAD_LIMIT env vars | :good:`done` | D138769 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | 'target_device' selector in context specifier | :none:`worked on` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | begin/end declare variant | :good:`done` | D71179 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | dispatch construct and function variant argument adjustment | :part:`worked on` | D99537, D99679 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | assumes directives | :part:`worked on` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | assume directive | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | nothing directive | :good:`done` | D123286 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | masked construct and related combined constructs | :good:`done` | D99995, D100514, PR-121741(parallel_masked_taskloop) | +| | | | PR-121746(parallel_masked_task_loop_simd),PR-121914(masked_taskloop) | +| | | | PR-121916(masked_taskloop_simd) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| misc | default(firstprivate) & default(private) | :good:`done` | D75591 (firstprivate), D125912 (private) | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| other | deprecating master construct | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| OMPT | new barrier types added to ompt_sync_region_t enum | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| OMPT | async data transfers added to ompt_target_data_op_t enum | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| OMPT | new barrier state values added to ompt_state_t enum | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| OMPT | new 'emi' callbacks for external monitoring interfaces | :good:`done` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| OMPT | device tracing interface | :none:`in progress` | jplehr | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | 'strict' modifier for taskloop construct | :none:`unclaimed` | | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | inoutset in depend clause | :good:`done` | D97085, D118383 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ +| task | nowait clause on taskwait | :part:`partial` | parsing/sema done: D131830, D141531 | ++------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+ + + +.. _OpenMP 5.2 implementation details: + +OpenMP 5.2 Implementation Details +================================= + +The following table provides a quick overview of various OpenMP 5.2 features +and their implementation status. Please post on the +`Discourse forums (Runtimes - OpenMP category)`_ for more +information or if you want to help with the +implementation. + + + ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +|Feature | C/C++ Status | Fortran Status | Reviews | ++=============================================================+===========================+===========================+==========================================================================+ +| omp_in_explicit_task() | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| semantics of explicit_task_var and implicit_task_var | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| ompx sentinel for C/C++ directive extensions | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| ompx prefix for clause extensions | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| if clause on teams construct | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| step modifier added | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| declare mapper: Add iterator modifier on map clause | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| declare mapper: Add iterator modifier on map clause | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| memspace and traits modifiers to uses allocator i | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Add otherwise clause to metadirectives | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| doacross clause with support for omp_cur_iteration | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| position of interop_type in init clause on iterop | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| implicit map type for target enter/exit data | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| work OMPT type for work-sharing loop constructs | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| allocate and firstprivate on scope directive | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Change loop consistency for order clause | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Add memspace and traits modifiers to uses_allocators | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Keep original base pointer on map w/o matched candidate | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Pure procedure support for certain directives | :none:`N/A` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| ALLOCATE statement support for allocators | :none:`N/A` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| dispatch construct extension to support end directive | :none:`N/A` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ + + + +.. _OpenMP 5.2 Deprecations: + +OpenMP 5.2 Deprecations +======================= + + + ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| | C/C++ Status | Fortran Status | Reviews | ++=============================================================+===========================+===========================+==========================================================================+ +| Linear clause syntax | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| The minus operator | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Map clause modifiers without commas | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| The use of allocate directives with ALLOCATE statement | :good:`N/A` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| uses_allocators list syntax | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| The default clause on metadirectives | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| The delimited form of the declare target directive | :none:`unclaimed` | :good:`N/A` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| The use of the to clause on the declare target directive | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| The syntax of the destroy clause on the depobj construct | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| keyword source and sink as task-dependence modifiers | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| interop types in any position on init clause of interop | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| ompd prefix usage for some ICVs | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ + +.. _OpenMP 6.0 implementation details: + +OpenMP 6.0 Implementation Details +================================= + +The following table provides a quick overview of various OpenMP 6.0 features +and their implementation status. Please post on the +`Discourse forums (Runtimes - OpenMP category)`_ for more +information or if you want to help with the +implementation. + + ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +|Feature | C/C++ Status | Fortran Status | Reviews | ++=============================================================+===========================+===========================+==========================================================================+ +| free-agent threads | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| threadset clause | :part:`partial` | :none:`unclaimed` | Parse/Sema/Codegen : https://github.com/llvm/llvm-project/pull/13580 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Recording of task graphs | :part:`in progress` | :part:`in progress` | clang: jtb20, flang: kparzysz | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Parallel inductions | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| init_complete for scan directive | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop interchange transformation | :good:`done` | :none:`unclaimed` | Clang (interchange): https://github.com/llvm/llvm-project/pull/93022 | +| | | | Clang (permutation): https://github.com/llvm/llvm-project/pull/92030 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop reverse transformation | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/92916 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop stripe transformation | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/119891 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop fusion transformation | :part:`in progress` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/139293 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop index set splitting transformation | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop transformation apply clause | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop fuse transformation | :good:`done` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| workdistribute construct | | :none:`in progress` | @skc7, @mjklemm | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| task_iteration | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| memscope clause for atomic and flush | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| transparent clause (hull tasks) | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| rule-based compound directives | :part:`In Progress` | :part:`In Progress` | kparzysz | +| | | | Testing for Fortran missing | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| C23, C++23 | :none:`unclaimed` | | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Fortran 2023 | | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| decl attribute for declarative directives | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| C attribute syntax | :none:`unclaimed` | | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| pure directives in DO CONCURRENT | | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Optional argument for all clauses | :none:`partial` | :none:`In Progress` | Parse/Sema (nowait): https://github.com/llvm/llvm-project/pull/159628 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Function references for locator list items | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| All clauses accept directive name modifier | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Extensions to depobj construct | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Extensions to atomic construct | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Private reductions | :good:`mostly` | :none:`unclaimed` | Parse/Sema:https://github.com/llvm/llvm-project/pull/129938 | +| | | | Codegen: https://github.com/llvm/llvm-project/pull/134709 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Self maps | :part:`partial` | :none:`unclaimed` | parsing/sema done: https://github.com/llvm/llvm-project/pull/129888 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Release map type for declare mapper | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Extensions to interop construct | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| no_openmp_constructs | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/125933 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| safe_sync and progress with identifier and API | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| OpenMP directives in concurrent loop regions | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/125621 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| atomics constructs on concurrent loop regions | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/125621 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Loop construct with DO CONCURRENT | | :part:`In Progress` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| device_type clause for target construct | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| nowait for ancestor target directives | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| New API for devices' num_teams/thread_limit | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Host and device environment variables | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| num_threads ICV and clause accepts list | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Numeric names for environment variables | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Increment between places for OMP_PLACES | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| OMP_AVAILABLE_DEVICES envirable | :none:`unclaimed` | :none:`unclaimed` | (should wait for "Traits for default device envirable" being done) | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Traits for default device envirable | :part:`in progress` | :none:`unclaimed` | ro-i | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Optionally omit array length expression | :good:`done` | :none:`unclaimed` | (Parse) https://github.com/llvm/llvm-project/pull/148048, | +| | | | (Sema) https://github.com/llvm/llvm-project/pull/152786 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Canonical loop sequences | :part:`in progress` | :part:`in progress` | Clang: https://github.com/llvm/llvm-project/pull/139293 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Clarifications to Fortran map semantics | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| default clause at target construct | :part:`In Progress` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| ref count update use_device_{ptr, addr} | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Clarifications to implicit reductions | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| ref modifier for map clauses | :part:`In Progress` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| map-type modifiers in arbitrary position | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/90499 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Lift nesting restriction on concurrent loop | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/125621 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| priority clause for target constructs | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| changes to target_data construct | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Non-const do_not_sync for nowait/nogroup | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| need_device_addr modifier for adjust_args clause | :part:`partial` | :none:`unclaimed` | Parsing/Sema: https://github.com/llvm/llvm-project/pull/143442 | +| | | | https://github.com/llvm/llvm-project/pull/149586 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Prescriptive num_threads | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/160659 | +| | | | https://github.com/llvm/llvm-project/pull/146403 | +| | | | https://github.com/llvm/llvm-project/pull/146404 | +| | | | https://github.com/llvm/llvm-project/pull/146405 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Message and severity clauses | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/146093 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Local clause on declare target | :part:`In Progress` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| groupprivate directive | :part:`In Progress` | :part:`partial` | Flang: kparzysz, mjklemm | +| | | | | +| | | | Flang parser: https://github.com/llvm/llvm-project/pull/153807 | +| | | | Flang sema: https://github.com/llvm/llvm-project/pull/154779 | +| | | | Clang parse/sema: https://github.com/llvm/llvm-project/pull/158134 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| variable-category on default clause | :good:`done` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| Changes to omp_target_is_accessible | :part:`In Progress` | :part:`In Progress` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| defaultmap implicit-behavior 'storage' | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/158336 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| defaultmap implicit-behavior 'private' | :good:`done` | :none:`unclaimed` | https://github.com/llvm/llvm-project/pull/158712 | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ + +.. _OpenMP 6.1 implementation details: + +OpenMP 6.1 Implementation Details (Experimental) +================================================ + +The following table provides a quick overview over various OpenMP 6.1 features +and their implementation status. Since OpenMP 6.1 has not yet been released, the +following features are experimental and are subject to change at any time. +Please post on the `Discourse forums (Runtimes - OpenMP category)`_ for more +information or if you want to help with the +implementation. + ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +|Feature | C/C++ Status | Fortran Status | Reviews | ++=============================================================+===========================+===========================+==========================================================================+ +| dyn_groupprivate clause | :part:`In Progress` | :part:`In Progress` | C/C++: kevinsala (https://github.com/llvm/llvm-project/pull/152651 | +| | | | https://github.com/llvm/llvm-project/pull/152830 | +| | | | https://github.com/llvm/llvm-project/pull/152831) | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop flatten transformation | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| loop grid/tile modifiers for sizes clause | :none:`unclaimed` | :none:`unclaimed` | | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ +| attach map-type modifier | :part:`In Progress` | :none:`unclaimed` | C/C++: @abhinavgaba; | +| | | | RT: @abhinavgaba (https://github.com/llvm/llvm-project/pull/149036, | +| | | | https://github.com/llvm/llvm-project/pull/158370) | ++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+ + + +OpenMP Extensions +================= + +The following table provides a quick overview over various OpenMP +extensions and their implementation status. These extensions are not +currently defined by any standard, so links to associated LLVM +documentation are provided. As these extensions mature, they will be +considered for standardization. Please post on the +`Discourse forums (Runtimes - OpenMP category)`_ to provide feedback. + ++------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+ +|Category | Feature | Status | Reviews | ++==============================+===================================================================================+==========================+========================================================+ +| atomic extension | `'atomic' strictly nested within 'teams' | :good:`prototyped` | D126323 | +| | <https://openmp.llvm.org/docs/openacc/OpenMPExtensions.html#atomicWithinTeams>`_ | | | ++------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+ +| device extension | `'ompx_hold' map type modifier | :good:`prototyped` | D106509, D106510 | +| | <https://openmp.llvm.org/docs/openacc/OpenMPExtensions.html#ompx-hold>`_ | | | ++------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+ +| device extension | `'ompx_bare' clause on 'target teams' construct | :good:`prototyped` | #66844, #70612 | +| | <https://www.osti.gov/servlets/purl/2205717>`_ | | | ++------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+ +| device extension | Multi-dim 'num_teams' and 'thread_limit' clause on 'target teams ompx_bare' | :good:`partial` | #99732, #101407, #102715 | +| | construct | | | ++------------------------------+-----------------------------------------------------------------------------------+--------------------------+--------------------------------------------------------+ + +.. _Discourse forums (Runtimes - OpenMP category): https://discourse.llvm.org/c/runtimes/openmp/35 diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst index add1582..73aaaad 100644 --- a/clang/docs/ReleaseNotes.rst +++ b/clang/docs/ReleaseNotes.rst @@ -613,6 +613,14 @@ clang-format literals. - Add ``Leave`` suboption to ``IndentPPDirectives``. - Add ``AllowBreakBeforeQtProperty`` option. +- Add ``BreakAfterOpenBracketBracedList'', ``BreakAfterOpenBracketFunction'', + ``BreakAfterOpenBracketIf``, ``BreakAfterOpenBracketLoop``, + ``BreakAfterOpenBracketSwitch``, ``BreakBeforeCloseBracketBracedList'', + ``BreakBeforeCloseBracketFunction``, ``BreakBeforeCloseBracketIf``, + ``BreakBeforeCloseBracketLoop``, ``BreakBeforeCloseBracketSwitch`` options. +- Deprecate ``AlwaysBreak`` and ``BlockIndent`` suboptions from the + ``AlignAfterOpenBracket`` option, and make ``AlignAfterOpenBracket`` a + ``bool`` type. libclang -------- @@ -651,6 +659,7 @@ Sanitizers Python Binding Changes ---------------------- +- Exposed ``clang_Cursor_isFunctionInlined``. - Exposed ``clang_getCursorLanguage`` via ``Cursor.language``. - Add all missing ``CursorKind``s, ``TypeKind``s and ``ExceptionSpecificationKind``s from ``Index.h`` @@ -661,6 +670,7 @@ OpenMP Support modifier in the ``adjust_args`` clause. - Allow array length to be omitted in array section subscript expression. - Fixed non-contiguous strided update in the ``omp target update`` directive with the ``from`` clause. +- Added support for threadset clause in task and taskloop directives. - Properly handle array section/assumed-size array privatization in C/C++. - Added support to handle new syntax of the ``uses_allocators`` clause. - Added support for ``variable-category`` modifier in ``default clause``. diff --git a/clang/include/clang/AST/OpenMPClause.h b/clang/include/clang/AST/OpenMPClause.h index bc791e4..4f50748 100644 --- a/clang/include/clang/AST/OpenMPClause.h +++ b/clang/include/clang/AST/OpenMPClause.h @@ -1424,6 +1424,86 @@ public: } }; +/// This represents 'threadset' clause in the '#pragma omp task ...' directive. +/// +/// \code +/// #pragma omp task threadset(omp_pool) +/// \endcode +/// In this example directive '#pragma omp task' has simple 'threadset' +/// clause with kind 'omp_pool'. +class OMPThreadsetClause final : public OMPClause { + friend class OMPClauseReader; + + /// Location of '('. + SourceLocation LParenLoc; + + /// A kind of the 'threadset' clause. + OpenMPThreadsetKind Kind = OMPC_THREADSET_unknown; + + /// Start location of the kind in source code. + SourceLocation KindLoc; + + /// Set kind of the clauses. + /// + /// \param K Argument of clause. + void setThreadsetKind(OpenMPThreadsetKind K) { Kind = K; } + + /// Set argument location. + /// + /// \param KLoc Argument location. + void setThreadsetKindLoc(SourceLocation KLoc) { KindLoc = KLoc; } + +public: + /// Build 'threadset' clause with argument \a A ('omp_team' or 'omp_pool'). + /// + /// \param A Argument of the clause ('omp_team' or 'omp_pool'). + /// \param ALoc Starting location of the argument. + /// \param StartLoc Starting location of the clause. + /// \param LParenLoc Location of '('. + /// \param EndLoc Ending location of the clause. + OMPThreadsetClause(OpenMPThreadsetKind A, SourceLocation ALoc, + SourceLocation StartLoc, SourceLocation LParenLoc, + SourceLocation EndLoc) + : OMPClause(llvm::omp::OMPC_threadset, StartLoc, EndLoc), + LParenLoc(LParenLoc), Kind(A), KindLoc(ALoc) {} + + /// Build an empty clause. + OMPThreadsetClause() + : OMPClause(llvm::omp::OMPC_threadset, SourceLocation(), + SourceLocation()) {} + + /// Sets the location of '('. + void setLParenLoc(SourceLocation Loc) { LParenLoc = Loc; } + + /// Returns the location of '('. + SourceLocation getLParenLoc() const { return LParenLoc; } + + /// Returns kind of the clause. + OpenMPThreadsetKind getThreadsetKind() const { return Kind; } + + /// Returns location of clause kind. + SourceLocation getThreadsetKindLoc() const { return KindLoc; } + + child_range children() { + return child_range(child_iterator(), child_iterator()); + } + + const_child_range children() const { + return const_child_range(const_child_iterator(), const_child_iterator()); + } + + child_range used_children() { + return child_range(child_iterator(), child_iterator()); + } + const_child_range used_children() const { + return const_child_range(const_child_iterator(), const_child_iterator()); + } + + static bool classof(const OMPClause *T) { + return T->getClauseKind() == llvm::omp::OMPC_threadset; + } +}; + /// This represents 'proc_bind' clause in the '#pragma omp ...' /// directive. /// diff --git a/clang/include/clang/AST/RecursiveASTVisitor.h b/clang/include/clang/AST/RecursiveASTVisitor.h index 32b2b6b..8cb0a65 100644 --- a/clang/include/clang/AST/RecursiveASTVisitor.h +++ b/clang/include/clang/AST/RecursiveASTVisitor.h @@ -3524,6 +3524,12 @@ bool RecursiveASTVisitor<Derived>::VisitOMPDefaultClause(OMPDefaultClause *) { } template <typename Derived> +bool RecursiveASTVisitor<Derived>::VisitOMPThreadsetClause( + OMPThreadsetClause *) { + return true; +} + +template <typename Derived> bool RecursiveASTVisitor<Derived>::VisitOMPProcBindClause(OMPProcBindClause *) { return true; } diff --git a/clang/include/clang/Basic/Builtins.def b/clang/include/clang/Basic/Builtins.def index b856ad1..3a5b72e 100644 --- a/clang/include/clang/Basic/Builtins.def +++ b/clang/include/clang/Basic/Builtins.def @@ -43,6 +43,7 @@ // SJ -> sigjmp_buf // K -> ucontext_t // p -> pid_t +// e -> _Float16 for HIP/C++ and __fp16 for OpenCL // . -> "...". This may only occur at the end of the function list. // // Types may be prefixed with the following modifiers: diff --git a/clang/include/clang/Basic/BuiltinsAMDGPU.def b/clang/include/clang/Basic/BuiltinsAMDGPU.def index f265d82..36cb527 100644 --- a/clang/include/clang/Basic/BuiltinsAMDGPU.def +++ b/clang/include/clang/Basic/BuiltinsAMDGPU.def @@ -967,6 +967,47 @@ TARGET_BUILTIN(__builtin_amdgcn_image_sample_3d_v4f32_f32, "V4fifffQtV4ibii", "n TARGET_BUILTIN(__builtin_amdgcn_image_sample_3d_v4f16_f32, "V4hifffQtV4ibii", "nc", "image-insts") TARGET_BUILTIN(__builtin_amdgcn_image_sample_cube_v4f32_f32, "V4fifffQtV4ibii", "nc", "image-insts") TARGET_BUILTIN(__builtin_amdgcn_image_sample_cube_v4f16_f32, "V4hifffQtV4ibii", "nc", "image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_1d_v4f32_f32, "V4fifQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_1d_v4f16_f32, "V4eifQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_1darray_v4f32_f32, "V4fiffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_1darray_v4f16_f32, "V4eiffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_2d_f32_f32, "fiffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_2d_v4f32_f32, "V4fiffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_2d_v4f16_f32, "V4eiffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_2darray_f32_f32, "fifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_2darray_v4f32_f32, "V4fifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_2darray_v4f16_f32, "V4eifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_3d_v4f32_f32, "V4fifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_3d_v4f16_f32, "V4eifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_cube_v4f32_f32, "V4fifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_lz_cube_v4f16_f32, "V4eifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_1d_v4f32_f32, "V4fiffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_1d_v4f16_f32, "V4eiffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_1darray_v4f32_f32, "V4fifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_1darray_v4f16_f32, "V4eifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_2d_f32_f32, "fifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_2d_v4f32_f32, "V4fifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_2d_v4f16_f32, "V4eifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_2darray_f32_f32, "fiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_2darray_v4f32_f32, "V4fiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_2darray_v4f16_f32, "V4eiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_3d_v4f32_f32, "V4fiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_3d_v4f16_f32, "V4eiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_cube_v4f32_f32, "V4fiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_l_cube_v4f16_f32, "V4eiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_1d_v4f32_f32, "V4fifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_1d_v4f16_f32, "V4eifffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_1darray_v4f32_f32, "V4fiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_1darray_v4f16_f32, "V4eiffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_2d_f32_f32, "fiffffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_2d_v4f32_f32, "V4fiffffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_2d_v4f16_f32, "V4eiffffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_2darray_f32_f32, "fifffffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_2darray_v4f32_f32, "V4fifffffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_2darray_v4f16_f32, "V4eifffffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_3d_v4f32_f32, "V4fifffffffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_sample_d_3d_v4f16_f32, "V4eifffffffffQtV4ibii", "nc", "extended-image-insts") +TARGET_BUILTIN(__builtin_amdgcn_image_gather4_lz_2d_v4f32_f32, "V4fiffQtV4ibii", "nc", "extended-image-insts") #undef BUILTIN #undef TARGET_BUILTIN diff --git a/clang/include/clang/Basic/BuiltinsX86.td b/clang/include/clang/Basic/BuiltinsX86.td index 500aa85..9e877b9 100644 --- a/clang/include/clang/Basic/BuiltinsX86.td +++ b/clang/include/clang/Basic/BuiltinsX86.td @@ -328,7 +328,6 @@ let Features = "ssse3", Attributes = [NoThrow, Const, Constexpr, RequiredVectorW } let Features = "sse4.1", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in { - def insertps128 : X86Builtin<"_Vector<4, float>(_Vector<4, float>, _Vector<4, float>, _Constant char)">; def roundps : X86Builtin<"_Vector<4, float>(_Vector<4, float>, _Constant int)">; def roundss : X86Builtin<"_Vector<4, float>(_Vector<4, float>, _Vector<4, float>, _Constant int)">; def roundsd : X86Builtin<"_Vector<2, double>(_Vector<2, double>, _Vector<2, double>, _Constant int)">; @@ -342,6 +341,8 @@ let Features = "sse4.1", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] let Features = "sse4.1", Attributes = [NoThrow, Const, Constexpr, RequiredVectorWidth<128>] in { + def insertps128 : X86Builtin<"_Vector<4, float>(_Vector<4, float>, " + "_Vector<4, float>, _Constant char)">; def ptestz128 : X86Builtin<"int(_Vector<2, long long int>, _Vector<2, long long int>)">; def ptestc128 diff --git a/clang/include/clang/Basic/OpenMPKinds.def b/clang/include/clang/Basic/OpenMPKinds.def index 202d06f..328a0747 100644 --- a/clang/include/clang/Basic/OpenMPKinds.def +++ b/clang/include/clang/Basic/OpenMPKinds.def @@ -98,6 +98,9 @@ #ifndef OPENMP_ALLOCATE_MODIFIER #define OPENMP_ALLOCATE_MODIFIER(Name) #endif +#ifndef OPENMP_THREADSET_KIND +#define OPENMP_THREADSET_KIND(Name) +#endif // Static attributes for 'schedule' clause. OPENMP_SCHEDULE_KIND(static) @@ -255,6 +258,9 @@ OPENMP_DOACROSS_MODIFIER(sink) OPENMP_DOACROSS_MODIFIER(sink_omp_cur_iteration) OPENMP_DOACROSS_MODIFIER(source_omp_cur_iteration) +OPENMP_THREADSET_KIND(omp_pool) +OPENMP_THREADSET_KIND(omp_team) + #undef OPENMP_NUMTASKS_MODIFIER #undef OPENMP_NUMTHREADS_MODIFIER #undef OPENMP_GRAINSIZE_MODIFIER @@ -284,4 +290,4 @@ OPENMP_DOACROSS_MODIFIER(source_omp_cur_iteration) #undef OPENMP_DEFAULTMAP_MODIFIER #undef OPENMP_DOACROSS_MODIFIER #undef OPENMP_ALLOCATE_MODIFIER - +#undef OPENMP_THREADSET_KIND diff --git a/clang/include/clang/Basic/OpenMPKinds.h b/clang/include/clang/Basic/OpenMPKinds.h index ed89a31..c9ddbcd 100644 --- a/clang/include/clang/Basic/OpenMPKinds.h +++ b/clang/include/clang/Basic/OpenMPKinds.h @@ -250,6 +250,13 @@ enum OpenMPAllocateClauseModifier { OMPC_ALLOCATE_unknown }; +/// OpenMP modifiers for 'threadset' clause. +enum OpenMPThreadsetKind { +#define OPENMP_THREADSET_KIND(Name) OMPC_THREADSET_##Name, +#include "clang/Basic/OpenMPKinds.def" + OMPC_THREADSET_unknown +}; + /// Number of allowed allocate-modifiers. static constexpr unsigned NumberOfOMPAllocateClauseModifiers = OMPC_ALLOCATE_unknown; diff --git a/clang/include/clang/Format/Format.h b/clang/include/clang/Format/Format.h index 2852c4a..f246def 100644 --- a/clang/include/clang/Format/Format.h +++ b/clang/include/clang/Format/Format.h @@ -62,49 +62,28 @@ struct FormatStyle { /// \version 3.3 int AccessModifierOffset; - /// Different styles for aligning after open brackets. - enum BracketAlignmentStyle : int8_t { - /// Align parameters on the open bracket, e.g.: - /// \code - /// someLongFunction(argument1, - /// argument2); - /// \endcode - BAS_Align, - /// Don't align, instead use ``ContinuationIndentWidth``, e.g.: - /// \code - /// someLongFunction(argument1, - /// argument2); - /// \endcode - BAS_DontAlign, - /// Always break after an open bracket, if the parameters don't fit - /// on a single line, e.g.: - /// \code - /// someLongFunction( - /// argument1, argument2); - /// \endcode - BAS_AlwaysBreak, - /// Always break after an open bracket, if the parameters don't fit - /// on a single line. Closing brackets will be placed on a new line. - /// E.g.: - /// \code - /// someLongFunction( - /// argument1, argument2 - /// ) - /// \endcode - /// - /// \note - /// This currently only applies to braced initializer lists (when - /// ``Cpp11BracedListStyle`` is not ``Block``) and parentheses. - /// \endnote - BAS_BlockIndent, - }; - /// If ``true``, horizontally aligns arguments after an open bracket. /// + /// \code + /// true: vs. false + /// someLongFunction(argument1, someLongFunction(argument1, + /// argument2); argument2); + /// \endcode + /// + /// \note + /// As of clang-format 22 this option is a bool with the previous + /// option of ``Align`` replaced with ``true``, ``DontAlign`` replaced + /// with ``false``, and the options of ``AlwaysBreak`` and ``BlockIndent`` + /// replaced with ``true`` and with setting of new style options using + /// ``BreakAfterOpenBracketBracedList``, ``BreakAfterOpenBracketFunction``, + /// ``BreakAfterOpenBracketIf``, ``BreakBeforeCloseBracketBracedList``, + /// ``BreakBeforeCloseBracketFunction``, and ``BreakBeforeCloseBracketIf``. + /// \endnote + /// /// This applies to round brackets (parentheses), angle brackets and square /// brackets. /// \version 3.8 - BracketAlignmentStyle AlignAfterOpenBracket; + bool AlignAfterOpenBracket; /// Different style for aligning array initializers. enum ArrayInitializerAlignmentStyle : int8_t { @@ -1708,6 +1687,57 @@ struct FormatStyle { /// \version 16 AttributeBreakingStyle BreakAfterAttributes; + /// Force break after the left bracket of a braced initializer list (when + /// ``Cpp11BracedListStyle`` is ``true``) when the list exceeds the column + /// limit. + /// \code + /// true: false: + /// vector<int> x { vs. vector<int> x {1, + /// 1, 2, 3} 2, 3} + /// \endcode + /// \version 22 + bool BreakAfterOpenBracketBracedList; + + /// Force break after the left parenthesis of a function (declaration, + /// definition, call) when the parameters exceed the column limit. + /// \code + /// true: false: + /// foo ( vs. foo (a, + /// a , b) b) + /// \endcode + /// \version 22 + bool BreakAfterOpenBracketFunction; + + /// Force break after the left parenthesis of an if control statement + /// when the expression exceeds the column limit. + /// \code + /// true: false: + /// if constexpr ( vs. if constexpr (a || + /// a || b) b) + /// \endcode + /// \version 22 + bool BreakAfterOpenBracketIf; + + /// Force break after the left parenthesis of a loop control statement + /// when the expression exceeds the column limit. + /// \code + /// true: false: + /// while ( vs. while (a && + /// a && b) { b) { + /// \endcode + /// \version 22 + bool BreakAfterOpenBracketLoop; + + /// Force break after the left parenthesis of a switch control statement + /// when the expression exceeds the column limit. + /// \code + /// true: false: + /// switch ( vs. switch (a + + /// a + b) { b) { + /// \endcode + /// \version 22 + bool BreakAfterOpenBracketSwitch; + /// The function declaration return type breaking style to use. /// \version 19 ReturnTypeBreakingStyle BreakAfterReturnType; @@ -2221,6 +2251,69 @@ struct FormatStyle { /// \version 3.7 BraceBreakingStyle BreakBeforeBraces; + /// Force break before the right bracket of a braced initializer list (when + /// ``Cpp11BracedListStyle`` is ``true``) when the list exceeds the column + /// limit. The break before the right bracket is only made if there is a + /// break after the opening bracket. + /// \code + /// true: false: + /// vector<int> x { vs. vector<int> x { + /// 1, 2, 3 1, 2, 3} + /// } + /// \endcode + /// \version 22 + bool BreakBeforeCloseBracketBracedList; + + /// Force break before the right parenthesis of a function (declaration, + /// definition, call) when the parameters exceed the column limit. + /// \code + /// true: false: + /// foo ( vs. foo ( + /// a , b a , b) + /// ) + /// \endcode + /// \version 22 + bool BreakBeforeCloseBracketFunction; + + /// Force break before the right parenthesis of an if control statement + /// when the expression exceeds the column limit. The break before the + /// closing parenthesis is only made if there is a break after the opening + /// parenthesis. + /// \code + /// true: false: + /// if constexpr ( vs. if constexpr ( + /// a || b a || b ) + /// ) + /// \endcode + /// \version 22 + bool BreakBeforeCloseBracketIf; + + /// Force break before the right parenthesis of a loop control statement + /// when the expression exceeds the column limit. The break before the + /// closing parenthesis is only made if there is a break after the opening + /// parenthesis. + /// \code + /// true: false: + /// while ( vs. while ( + /// a && b a && b) { + /// ) { + /// \endcode + /// \version 22 + bool BreakBeforeCloseBracketLoop; + + /// Force break before the right parenthesis of a switch control statement + /// when the expression exceeds the column limit. The break before the + /// closing parenthesis is only made if there is a break after the opening + /// parenthesis. + /// \code + /// true: false: + /// switch ( vs. switch ( + /// a + b a + b) { + /// ) { + /// \endcode + /// \version 22 + bool BreakBeforeCloseBracketSwitch; + /// Different ways to break before concept declarations. enum BreakBeforeConceptDeclarationsStyle : int8_t { /// Keep the template declaration line together with ``concept``. @@ -5530,10 +5623,23 @@ struct FormatStyle { BreakAdjacentStringLiterals == R.BreakAdjacentStringLiterals && BreakAfterAttributes == R.BreakAfterAttributes && BreakAfterJavaFieldAnnotations == R.BreakAfterJavaFieldAnnotations && + BreakAfterOpenBracketBracedList == + R.BreakAfterOpenBracketBracedList && + BreakAfterOpenBracketFunction == R.BreakAfterOpenBracketFunction && + BreakAfterOpenBracketIf == R.BreakAfterOpenBracketIf && + BreakAfterOpenBracketLoop == R.BreakAfterOpenBracketLoop && + BreakAfterOpenBracketSwitch == R.BreakAfterOpenBracketSwitch && BreakAfterReturnType == R.BreakAfterReturnType && BreakArrays == R.BreakArrays && BreakBeforeBinaryOperators == R.BreakBeforeBinaryOperators && BreakBeforeBraces == R.BreakBeforeBraces && + BreakBeforeCloseBracketBracedList == + R.BreakBeforeCloseBracketBracedList && + BreakBeforeCloseBracketFunction == + R.BreakBeforeCloseBracketFunction && + BreakBeforeCloseBracketIf == R.BreakBeforeCloseBracketIf && + BreakBeforeCloseBracketLoop == R.BreakBeforeCloseBracketLoop && + BreakBeforeCloseBracketSwitch == R.BreakBeforeCloseBracketSwitch && BreakBeforeConceptDeclarations == R.BreakBeforeConceptDeclarations && BreakBeforeInlineASMColon == R.BreakBeforeInlineASMColon && BreakBeforeTemplateCloser == R.BreakBeforeTemplateCloser && diff --git a/clang/include/clang/Sema/SemaOpenMP.h b/clang/include/clang/Sema/SemaOpenMP.h index f9baeed..ba12b40 100644 --- a/clang/include/clang/Sema/SemaOpenMP.h +++ b/clang/include/clang/Sema/SemaOpenMP.h @@ -975,6 +975,12 @@ public: OpenMPDefaultClauseVariableCategory VCKind, SourceLocation VCKindLoc, SourceLocation StartLoc, SourceLocation LParenLoc, SourceLocation EndLoc); + /// Called on well-formed 'threadset' clause. + OMPClause *ActOnOpenMPThreadsetClause(OpenMPThreadsetKind Kind, + SourceLocation KindLoc, + SourceLocation StartLoc, + SourceLocation LParenLoc, + SourceLocation EndLoc); /// Called on well-formed 'proc_bind' clause. OMPClause *ActOnOpenMPProcBindClause(llvm::omp::ProcBindKind Kind, SourceLocation KindLoc, diff --git a/clang/lib/AST/ASTContext.cpp b/clang/lib/AST/ASTContext.cpp index 687cd46..2669f62 100644 --- a/clang/lib/AST/ASTContext.cpp +++ b/clang/lib/AST/ASTContext.cpp @@ -12403,6 +12403,11 @@ static QualType DecodeTypeFromStr(const char *&Str, const ASTContext &Context, // Read the base type. switch (*Str++) { default: llvm_unreachable("Unknown builtin type letter!"); + case 'e': + assert(HowLong == 0 && !Signed && !Unsigned && + "Bad modifiers used with 'e'!"); + Type = Context.getLangOpts().OpenCL ? Context.HalfTy : Context.Float16Ty; + break; case 'x': assert(HowLong == 0 && !Signed && !Unsigned && "Bad modifiers used with 'x'!"); diff --git a/clang/lib/AST/ByteCode/InterpBuiltin.cpp b/clang/lib/AST/ByteCode/InterpBuiltin.cpp index b3ab82d..8b57b96 100644 --- a/clang/lib/AST/ByteCode/InterpBuiltin.cpp +++ b/clang/lib/AST/ByteCode/InterpBuiltin.cpp @@ -3411,7 +3411,7 @@ static bool interp__builtin_x86_byteshift( static bool interp__builtin_ia32_shuffle_generic( InterpState &S, CodePtr OpPC, const CallExpr *Call, - llvm::function_ref<std::pair<unsigned, unsigned>(unsigned, unsigned)> + llvm::function_ref<std::pair<unsigned, int>(unsigned, unsigned)> GetSourceIndex) { assert(Call->getNumArgs() == 3); @@ -3428,8 +3428,19 @@ static bool interp__builtin_ia32_shuffle_generic( for (unsigned DstIdx = 0; DstIdx != NumElems; ++DstIdx) { auto [SrcVecIdx, SrcIdx] = GetSourceIndex(DstIdx, ShuffleMask); - const Pointer &Src = (SrcVecIdx == 0) ? A : B; - TYPE_SWITCH(ElemT, { Dst.elem<T>(DstIdx) = Src.elem<T>(SrcIdx); }); + + if (SrcIdx < 0) { + // Zero out this element + if (ElemT == PT_Float) { + Dst.elem<Floating>(DstIdx) = Floating( + S.getASTContext().getFloatTypeSemantics(VecT->getElementType())); + } else { + INT_TYPE_SWITCH_NO_BOOL(ElemT, { Dst.elem<T>(DstIdx) = T::from(0); }); + } + } else { + const Pointer &Src = (SrcVecIdx == 0) ? A : B; + TYPE_SWITCH(ElemT, { Dst.elem<T>(DstIdx) = Src.elem<T>(SrcIdx); }); + } } Dst.initializeAllElements(); @@ -4382,7 +4393,8 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call, unsigned SrcIdx = ElemInLane >= NumSelectableElems ? 1 : 0; unsigned BitIndex = (DstIdx * BitsPerElem) % MaskBits; unsigned Index = (ShuffleMask >> BitIndex) & IndexMask; - return std::pair<unsigned, unsigned>{SrcIdx, LaneOffset + Index}; + return std::pair<unsigned, int>{SrcIdx, + static_cast<int>(LaneOffset + Index)}; }); case X86::BI__builtin_ia32_shufpd: case X86::BI__builtin_ia32_shufpd256: @@ -4400,7 +4412,27 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call, unsigned SrcIdx = ElemInLane >= NumSelectableElems ? 1 : 0; unsigned BitIndex = (DstIdx * BitsPerElem) % MaskBits; unsigned Index = (ShuffleMask >> BitIndex) & IndexMask; - return std::pair<unsigned, unsigned>{SrcIdx, LaneOffset + Index}; + return std::pair<unsigned, int>{SrcIdx, + static_cast<int>(LaneOffset + Index)}; + }); + case X86::BI__builtin_ia32_insertps128: + return interp__builtin_ia32_shuffle_generic( + S, OpPC, Call, [](unsigned DstIdx, unsigned Mask) { + // Bits [3:0]: zero mask - if bit is set, zero this element + if ((Mask & (1 << DstIdx)) != 0) { + return std::pair<unsigned, int>{0, -1}; + } + // Bits [7:6]: select element from source vector Y (0-3) + // Bits [5:4]: select destination position (0-3) + unsigned SrcElem = (Mask >> 6) & 0x3; + unsigned DstElem = (Mask >> 4) & 0x3; + if (DstIdx == DstElem) { + // Insert element from source vector (B) at this position + return std::pair<unsigned, int>{1, static_cast<int>(SrcElem)}; + } else { + // Copy from destination vector (A) + return std::pair<unsigned, int>{0, static_cast<int>(DstIdx)}; + } }); case X86::BI__builtin_ia32_pshufb128: case X86::BI__builtin_ia32_pshufb256: diff --git a/clang/lib/AST/ExprConstant.cpp b/clang/lib/AST/ExprConstant.cpp index d0404b9..97eeba8 100644 --- a/clang/lib/AST/ExprConstant.cpp +++ b/clang/lib/AST/ExprConstant.cpp @@ -11621,7 +11621,7 @@ static bool evalPackBuiltin(const CallExpr *E, EvalInfo &Info, APValue &Result, static bool evalShuffleGeneric( EvalInfo &Info, const CallExpr *Call, APValue &Out, - llvm::function_ref<std::pair<unsigned, unsigned>(unsigned, unsigned)> + llvm::function_ref<std::pair<unsigned, int>(unsigned, unsigned)> GetSourceIndex) { const auto *VT = Call->getType()->getAs<VectorType>(); @@ -11644,8 +11644,16 @@ static bool evalShuffleGeneric( for (unsigned DstIdx = 0; DstIdx != NumElts; ++DstIdx) { auto [SrcVecIdx, SrcIdx] = GetSourceIndex(DstIdx, ShuffleMask); - const APValue &Src = (SrcVecIdx == 0) ? A : B; - ResultElements.push_back(Src.getVectorElt(SrcIdx)); + + if (SrcIdx < 0) { + // Zero out this element + QualType ElemTy = VT->getElementType(); + ResultElements.push_back( + APValue(APFloat::getZero(Info.Ctx.getFloatTypeSemantics(ElemTy)))); + } else { + const APValue &Src = (SrcVecIdx == 0) ? A : B; + ResultElements.push_back(Src.getVectorElt(SrcIdx)); + } } Out = APValue(ResultElements.data(), ResultElements.size()); @@ -12438,7 +12446,7 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) { if (!evalShuffleGeneric( Info, E, R, [](unsigned DstIdx, - unsigned ShuffleMask) -> std::pair<unsigned, unsigned> { + unsigned ShuffleMask) -> std::pair<unsigned, int> { constexpr unsigned LaneBits = 128u; unsigned NumElemPerLane = LaneBits / 32; unsigned NumSelectableElems = NumElemPerLane / 2; @@ -12451,7 +12459,7 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) { unsigned BitIndex = (DstIdx * BitsPerElem) % MaskBits; unsigned SrcIdx = (ElemInLane < NumSelectableElems) ? 0 : 1; unsigned Index = (ShuffleMask >> BitIndex) & IndexMask; - return {SrcIdx, LaneOffset + Index}; + return {SrcIdx, static_cast<int>(LaneOffset + Index)}; })) return false; return Success(R, E); @@ -12463,7 +12471,7 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) { if (!evalShuffleGeneric( Info, E, R, [](unsigned DstIdx, - unsigned ShuffleMask) -> std::pair<unsigned, unsigned> { + unsigned ShuffleMask) -> std::pair<unsigned, int> { constexpr unsigned LaneBits = 128u; unsigned NumElemPerLane = LaneBits / 64; unsigned NumSelectableElems = NumElemPerLane / 2; @@ -12476,7 +12484,31 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) { unsigned BitIndex = (DstIdx * BitsPerElem) % MaskBits; unsigned SrcIdx = (ElemInLane < NumSelectableElems) ? 0 : 1; unsigned Index = (ShuffleMask >> BitIndex) & IndexMask; - return {SrcIdx, LaneOffset + Index}; + return {SrcIdx, static_cast<int>(LaneOffset + Index)}; + })) + return false; + return Success(R, E); + } + case X86::BI__builtin_ia32_insertps128: { + APValue R; + if (!evalShuffleGeneric( + Info, E, R, + [](unsigned DstIdx, unsigned Mask) -> std::pair<unsigned, int> { + // Bits [3:0]: zero mask - if bit is set, zero this element + if ((Mask & (1 << DstIdx)) != 0) { + return {0, -1}; + } + // Bits [7:6]: select element from source vector Y (0-3) + // Bits [5:4]: select destination position (0-3) + unsigned SrcElem = (Mask >> 6) & 0x3; + unsigned DstElem = (Mask >> 4) & 0x3; + if (DstIdx == DstElem) { + // Insert element from source vector (B) at this position + return {1, static_cast<int>(SrcElem)}; + } else { + // Copy from destination vector (A) + return {0, static_cast<int>(DstIdx)}; + } })) return false; return Success(R, E); diff --git a/clang/lib/AST/OpenMPClause.cpp b/clang/lib/AST/OpenMPClause.cpp index 791df7e..59d9459 100644 --- a/clang/lib/AST/OpenMPClause.cpp +++ b/clang/lib/AST/OpenMPClause.cpp @@ -124,6 +124,7 @@ const OMPClauseWithPreInit *OMPClauseWithPreInit::get(const OMPClause *C) { case OMPC_nowait: case OMPC_untied: case OMPC_mergeable: + case OMPC_threadset: case OMPC_threadprivate: case OMPC_groupprivate: case OMPC_flush: @@ -2035,6 +2036,13 @@ void OMPClausePrinter::VisitOMPDefaultClause(OMPDefaultClause *Node) { OS << ")"; } +void OMPClausePrinter::VisitOMPThreadsetClause(OMPThreadsetClause *Node) { + OS << "threadset(" + << getOpenMPSimpleClauseTypeName(OMPC_threadset, + unsigned(Node->getThreadsetKind())) + << ")"; +} + void OMPClausePrinter::VisitOMPProcBindClause(OMPProcBindClause *Node) { OS << "proc_bind(" << getOpenMPSimpleClauseTypeName(OMPC_proc_bind, diff --git a/clang/lib/AST/StmtProfile.cpp b/clang/lib/AST/StmtProfile.cpp index 05b64cc..c909e1b 100644 --- a/clang/lib/AST/StmtProfile.cpp +++ b/clang/lib/AST/StmtProfile.cpp @@ -546,6 +546,8 @@ void OMPClauseProfiler::VisitOMPNocontextClause(const OMPNocontextClause *C) { void OMPClauseProfiler::VisitOMPDefaultClause(const OMPDefaultClause *C) { } +void OMPClauseProfiler::VisitOMPThreadsetClause(const OMPThreadsetClause *C) {} + void OMPClauseProfiler::VisitOMPProcBindClause(const OMPProcBindClause *C) { } void OMPClauseProfiler::VisitOMPUnifiedAddressClause( diff --git a/clang/lib/Basic/OpenMPKinds.cpp b/clang/lib/Basic/OpenMPKinds.cpp index 64b2bff..3d41f2d 100644 --- a/clang/lib/Basic/OpenMPKinds.cpp +++ b/clang/lib/Basic/OpenMPKinds.cpp @@ -210,6 +210,15 @@ unsigned clang::getOpenMPSimpleClauseType(OpenMPClauseKind Kind, StringRef Str, #define OPENMP_ALLOCATE_MODIFIER(Name) .Case(#Name, OMPC_ALLOCATE_##Name) #include "clang/Basic/OpenMPKinds.def" .Default(OMPC_ALLOCATE_unknown); + case OMPC_threadset: { + unsigned Type = llvm::StringSwitch<unsigned>(Str) +#define OPENMP_THREADSET_KIND(Name) .Case(#Name, OMPC_THREADSET_##Name) +#include "clang/Basic/OpenMPKinds.def" + .Default(OMPC_THREADSET_unknown); + if (LangOpts.OpenMP < 60) + return OMPC_THREADSET_unknown; + return Type; + } case OMPC_num_threads: { unsigned Type = llvm::StringSwitch<unsigned>(Str) #define OPENMP_NUMTHREADS_MODIFIER(Name) .Case(#Name, OMPC_NUMTHREADS_##Name) @@ -565,6 +574,16 @@ const char *clang::getOpenMPSimpleClauseTypeName(OpenMPClauseKind Kind, #include "clang/Basic/OpenMPKinds.def" } llvm_unreachable("Invalid OpenMP 'num_threads' clause modifier"); + case OMPC_threadset: + switch (Type) { + case OMPC_THREADSET_unknown: + return "unknown"; +#define OPENMP_THREADSET_KIND(Name) \ + case OMPC_THREADSET_##Name: \ + return #Name; +#include "clang/Basic/OpenMPKinds.def" + } + llvm_unreachable("Invalid OpenMP 'threadset' clause modifier"); case OMPC_unknown: case OMPC_threadprivate: case OMPC_groupprivate: diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp index d4de704..d4d696b 100644 --- a/clang/lib/Basic/Targets/AMDGPU.cpp +++ b/clang/lib/Basic/Targets/AMDGPU.cpp @@ -356,12 +356,6 @@ void AMDGPUTargetInfo::getTargetDefines(const LangOptions &Opts, if (hasFastFMA()) Builder.defineMacro("FP_FAST_FMA"); - Builder.defineMacro("__AMDGCN_WAVEFRONT_SIZE__", Twine(WavefrontSize), - "compile-time-constant access to the wavefront size will " - "be removed in a future release"); - Builder.defineMacro("__AMDGCN_WAVEFRONT_SIZE", Twine(WavefrontSize), - "compile-time-constant access to the wavefront size will " - "be removed in a future release"); Builder.defineMacro("__AMDGCN_CUMODE__", Twine(CUMode)); } diff --git a/clang/lib/CodeGen/CGDebugInfo.cpp b/clang/lib/CodeGen/CGDebugInfo.cpp index 07a2cfb..ca579c9 100644 --- a/clang/lib/CodeGen/CGDebugInfo.cpp +++ b/clang/lib/CodeGen/CGDebugInfo.cpp @@ -345,7 +345,7 @@ void CGDebugInfo::setLocation(SourceLocation Loc) { if (Loc.isInvalid()) return; - CurLoc = CGM.getContext().getSourceManager().getExpansionLoc(Loc); + CurLoc = CGM.getContext().getSourceManager().getFileLoc(Loc); // If we've changed files in the middle of a lexical scope go ahead // and create a new lexical scope with file node if it's different @@ -572,7 +572,7 @@ llvm::DIFile *CGDebugInfo::getOrCreateFile(SourceLocation Loc) { FileName = TheCU->getFile()->getFilename(); CSInfo = TheCU->getFile()->getChecksum(); } else { - PresumedLoc PLoc = SM.getPresumedLoc(Loc); + PresumedLoc PLoc = SM.getPresumedLoc(SM.getFileLoc(Loc)); FileName = PLoc.getFilename(); if (FileName.empty()) { @@ -599,7 +599,8 @@ llvm::DIFile *CGDebugInfo::getOrCreateFile(SourceLocation Loc) { if (CSKind) CSInfo.emplace(*CSKind, Checksum); } - return createFile(FileName, CSInfo, getSource(SM, SM.getFileID(Loc))); + return createFile(FileName, CSInfo, + getSource(SM, SM.getFileID(SM.getFileLoc(Loc)))); } llvm::DIFile *CGDebugInfo::createFile( @@ -654,7 +655,7 @@ unsigned CGDebugInfo::getLineNumber(SourceLocation Loc) { if (Loc.isInvalid()) return 0; SourceManager &SM = CGM.getContext().getSourceManager(); - return SM.getPresumedLoc(Loc).getLine(); + return SM.getPresumedLoc(SM.getFileLoc(Loc)).getLine(); } unsigned CGDebugInfo::getColumnNumber(SourceLocation Loc, bool Force) { @@ -666,7 +667,8 @@ unsigned CGDebugInfo::getColumnNumber(SourceLocation Loc, bool Force) { if (Loc.isInvalid() && CurLoc.isInvalid()) return 0; SourceManager &SM = CGM.getContext().getSourceManager(); - PresumedLoc PLoc = SM.getPresumedLoc(Loc.isValid() ? Loc : CurLoc); + PresumedLoc PLoc = + SM.getPresumedLoc(Loc.isValid() ? SM.getFileLoc(Loc) : CurLoc); return PLoc.isValid() ? PLoc.getColumn() : 0; } @@ -1174,7 +1176,10 @@ llvm::DIType *CGDebugInfo::CreateType(const BuiltinType *BT) { } llvm::DIType *CGDebugInfo::CreateType(const BitIntType *Ty) { - StringRef Name = Ty->isUnsigned() ? "unsigned _BitInt" : "_BitInt"; + SmallString<32> Name; + llvm::raw_svector_ostream OS(Name); + OS << (Ty->isUnsigned() ? "unsigned _BitInt(" : "_BitInt(") + << Ty->getNumBits() << ")"; llvm::dwarf::TypeKind Encoding = Ty->isUnsigned() ? llvm::dwarf::DW_ATE_unsigned : llvm::dwarf::DW_ATE_signed; @@ -4999,7 +5004,7 @@ void CGDebugInfo::EmitLocation(CGBuilderTy &Builder, SourceLocation Loc) { // Update our current location setLocation(Loc); - if (CurLoc.isInvalid() || CurLoc.isMacroID() || LexicalBlockStack.empty()) + if (CurLoc.isInvalid() || LexicalBlockStack.empty()) return; llvm::MDNode *Scope = LexicalBlockStack.back(); @@ -6275,7 +6280,8 @@ void CGDebugInfo::EmitGlobalAlias(const llvm::GlobalValue *GV, void CGDebugInfo::AddStringLiteralDebugInfo(llvm::GlobalVariable *GV, const StringLiteral *S) { SourceLocation Loc = S->getStrTokenLoc(0); - PresumedLoc PLoc = CGM.getContext().getSourceManager().getPresumedLoc(Loc); + SourceManager &SM = CGM.getContext().getSourceManager(); + PresumedLoc PLoc = SM.getPresumedLoc(SM.getFileLoc(Loc)); if (!PLoc.isValid()) return; diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.cpp b/clang/lib/CodeGen/CGOpenMPRuntime.cpp index 66fea92..121de42 100644 --- a/clang/lib/CodeGen/CGOpenMPRuntime.cpp +++ b/clang/lib/CodeGen/CGOpenMPRuntime.cpp @@ -3731,6 +3731,7 @@ CGOpenMPRuntime::emitTaskInit(CodeGenFunction &CGF, SourceLocation Loc, DestructorsFlag = 0x8, PriorityFlag = 0x20, DetachableFlag = 0x40, + FreeAgentFlag = 0x80, }; unsigned Flags = Data.Tied ? TiedFlag : 0; bool NeedsCleanup = false; @@ -3740,6 +3741,11 @@ CGOpenMPRuntime::emitTaskInit(CodeGenFunction &CGF, SourceLocation Loc, if (NeedsCleanup) Flags = Flags | DestructorsFlag; } + if (const auto *Clause = D.getSingleClause<OMPThreadsetClause>()) { + OpenMPThreadsetKind Kind = Clause->getThreadsetKind(); + if (Kind == OMPC_THREADSET_omp_pool) + Flags = Flags | FreeAgentFlag; + } if (Data.Priority.getInt()) Flags = Flags | PriorityFlag; if (D.hasClausesOfKind<OMPDetachClause>()) diff --git a/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp b/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp index f49a5af..9eab709 100644 --- a/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp +++ b/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp @@ -647,8 +647,8 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID, case AMDGPU::BI__builtin_amdgcn_ballot_w64: { llvm::Type *ResultType = ConvertType(E->getType()); llvm::Value *Src = EmitScalarExpr(E->getArg(0)); - Function *F = CGM.getIntrinsic(Intrinsic::amdgcn_ballot, { ResultType }); - return Builder.CreateCall(F, { Src }); + Function *F = CGM.getIntrinsic(Intrinsic::amdgcn_ballot, {ResultType}); + return Builder.CreateCall(F, {Src}); } case AMDGPU::BI__builtin_amdgcn_inverse_ballot_w32: case AMDGPU::BI__builtin_amdgcn_inverse_ballot_w64: { @@ -1139,6 +1139,83 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID, case AMDGPU::BI__builtin_amdgcn_image_sample_cube_v4f16_f32: return emitAMDGCNImageOverloadedReturnType( *this, E, Intrinsic::amdgcn_image_sample_cube, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_1d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_1d_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_lz_1d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_1d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_1d_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_l_1d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_1d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_1d_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_d_1d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_2d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_2d_v4f16_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_2d_f32_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_lz_2d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_2d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_2d_v4f16_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_2d_f32_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_l_2d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_2d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_2d_v4f16_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_2d_f32_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_d_2d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_3d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_3d_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_lz_3d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_3d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_3d_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_l_3d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_3d_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_3d_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_d_3d, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_cube_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_cube_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_lz_cube, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_cube_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_cube_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_l_cube, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_1darray_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_1darray_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_lz_1darray, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_1darray_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_1darray_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_l_1darray, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_1darray_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_1darray_v4f16_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_d_1darray, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_2darray_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_2darray_v4f16_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_lz_2darray_f32_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_lz_2darray, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_2darray_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_2darray_v4f16_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_l_2darray_f32_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_l_2darray, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_2darray_v4f32_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_2darray_v4f16_f32: + case clang::AMDGPU::BI__builtin_amdgcn_image_sample_d_2darray_f32_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_sample_d_2darray, false); + case clang::AMDGPU::BI__builtin_amdgcn_image_gather4_lz_2d_v4f32_f32: + return emitAMDGCNImageOverloadedReturnType( + *this, E, Intrinsic::amdgcn_image_gather4_lz_2d, false); case AMDGPU::BI__builtin_amdgcn_mfma_scale_f32_16x16x128_f8f6f4: case AMDGPU::BI__builtin_amdgcn_mfma_scale_f32_32x32x64_f8f6f4: { llvm::FixedVectorType *VT = FixedVectorType::get(Builder.getInt32Ty(), 8); diff --git a/clang/lib/CodeGen/TargetBuiltins/ARM.cpp b/clang/lib/CodeGen/TargetBuiltins/ARM.cpp index 60f9b86..15fa78d 100644 --- a/clang/lib/CodeGen/TargetBuiltins/ARM.cpp +++ b/clang/lib/CodeGen/TargetBuiltins/ARM.cpp @@ -1193,14 +1193,22 @@ static const ARMVectorIntrinsicInfo AArch64SISDIntrinsicMap[] = { NEONMAP1(vaddlvq_s32, aarch64_neon_saddlv, AddRetType | Add1ArgType), NEONMAP1(vaddlvq_u32, aarch64_neon_uaddlv, AddRetType | Add1ArgType), NEONMAP1(vaddv_f32, aarch64_neon_faddv, AddRetType | Add1ArgType), - NEONMAP1(vaddv_s32, aarch64_neon_saddv, AddRetType | Add1ArgType), - NEONMAP1(vaddv_u32, aarch64_neon_uaddv, AddRetType | Add1ArgType), + NEONMAP1(vaddv_s16, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddv_s32, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddv_s8, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddv_u16, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddv_u32, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddv_u8, vector_reduce_add, Add1ArgType), NEONMAP1(vaddvq_f32, aarch64_neon_faddv, AddRetType | Add1ArgType), NEONMAP1(vaddvq_f64, aarch64_neon_faddv, AddRetType | Add1ArgType), - NEONMAP1(vaddvq_s32, aarch64_neon_saddv, AddRetType | Add1ArgType), - NEONMAP1(vaddvq_s64, aarch64_neon_saddv, AddRetType | Add1ArgType), - NEONMAP1(vaddvq_u32, aarch64_neon_uaddv, AddRetType | Add1ArgType), - NEONMAP1(vaddvq_u64, aarch64_neon_uaddv, AddRetType | Add1ArgType), + NEONMAP1(vaddvq_s16, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddvq_s32, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddvq_s64, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddvq_s8, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddvq_u16, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddvq_u32, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddvq_u64, vector_reduce_add, Add1ArgType), + NEONMAP1(vaddvq_u8, vector_reduce_add, Add1ArgType), NEONMAP1(vcaged_f64, aarch64_neon_facge, AddRetType | Add1ArgType), NEONMAP1(vcages_f32, aarch64_neon_facge, AddRetType | Add1ArgType), NEONMAP1(vcagtd_f64, aarch64_neon_facgt, AddRetType | Add1ArgType), @@ -1243,27 +1251,43 @@ static const ARMVectorIntrinsicInfo AArch64SISDIntrinsicMap[] = { NEONMAP1(vmaxnmvq_f32, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType), NEONMAP1(vmaxnmvq_f64, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType), NEONMAP1(vmaxv_f32, aarch64_neon_fmaxv, AddRetType | Add1ArgType), - NEONMAP1(vmaxv_s32, aarch64_neon_smaxv, AddRetType | Add1ArgType), - NEONMAP1(vmaxv_u32, aarch64_neon_umaxv, AddRetType | Add1ArgType), + NEONMAP1(vmaxv_s16, vector_reduce_smax, Add1ArgType), + NEONMAP1(vmaxv_s32, vector_reduce_smax, Add1ArgType), + NEONMAP1(vmaxv_s8, vector_reduce_smax, Add1ArgType), + NEONMAP1(vmaxv_u16, vector_reduce_umax, Add1ArgType), + NEONMAP1(vmaxv_u32, vector_reduce_umax, Add1ArgType), + NEONMAP1(vmaxv_u8, vector_reduce_umax, Add1ArgType), NEONMAP1(vmaxvq_f32, aarch64_neon_fmaxv, AddRetType | Add1ArgType), NEONMAP1(vmaxvq_f64, aarch64_neon_fmaxv, AddRetType | Add1ArgType), - NEONMAP1(vmaxvq_s32, aarch64_neon_smaxv, AddRetType | Add1ArgType), - NEONMAP1(vmaxvq_u32, aarch64_neon_umaxv, AddRetType | Add1ArgType), + NEONMAP1(vmaxvq_s16, vector_reduce_smax, Add1ArgType), + NEONMAP1(vmaxvq_s32, vector_reduce_smax, Add1ArgType), + NEONMAP1(vmaxvq_s8, vector_reduce_smax, Add1ArgType), + NEONMAP1(vmaxvq_u16, vector_reduce_umax, Add1ArgType), + NEONMAP1(vmaxvq_u32, vector_reduce_umax, Add1ArgType), + NEONMAP1(vmaxvq_u8, vector_reduce_umax, Add1ArgType), NEONMAP1(vminnmv_f32, aarch64_neon_fminnmv, AddRetType | Add1ArgType), NEONMAP1(vminnmvq_f32, aarch64_neon_fminnmv, AddRetType | Add1ArgType), NEONMAP1(vminnmvq_f64, aarch64_neon_fminnmv, AddRetType | Add1ArgType), NEONMAP1(vminv_f32, aarch64_neon_fminv, AddRetType | Add1ArgType), - NEONMAP1(vminv_s32, aarch64_neon_sminv, AddRetType | Add1ArgType), - NEONMAP1(vminv_u32, aarch64_neon_uminv, AddRetType | Add1ArgType), + NEONMAP1(vminv_s16, vector_reduce_smin, Add1ArgType), + NEONMAP1(vminv_s32, vector_reduce_smin, Add1ArgType), + NEONMAP1(vminv_s8, vector_reduce_smin, Add1ArgType), + NEONMAP1(vminv_u16, vector_reduce_umin, Add1ArgType), + NEONMAP1(vminv_u32, vector_reduce_umin, Add1ArgType), + NEONMAP1(vminv_u8, vector_reduce_umin, Add1ArgType), NEONMAP1(vminvq_f32, aarch64_neon_fminv, AddRetType | Add1ArgType), NEONMAP1(vminvq_f64, aarch64_neon_fminv, AddRetType | Add1ArgType), - NEONMAP1(vminvq_s32, aarch64_neon_sminv, AddRetType | Add1ArgType), - NEONMAP1(vminvq_u32, aarch64_neon_uminv, AddRetType | Add1ArgType), + NEONMAP1(vminvq_s16, vector_reduce_smin, Add1ArgType), + NEONMAP1(vminvq_s32, vector_reduce_smin, Add1ArgType), + NEONMAP1(vminvq_s8, vector_reduce_smin, Add1ArgType), + NEONMAP1(vminvq_u16, vector_reduce_umin, Add1ArgType), + NEONMAP1(vminvq_u32, vector_reduce_umin, Add1ArgType), + NEONMAP1(vminvq_u8, vector_reduce_umin, Add1ArgType), NEONMAP1(vmull_p64, aarch64_neon_pmull64, 0), NEONMAP1(vmulxd_f64, aarch64_neon_fmulx, Add1ArgType), NEONMAP1(vmulxs_f32, aarch64_neon_fmulx, Add1ArgType), - NEONMAP1(vpaddd_s64, aarch64_neon_uaddv, AddRetType | Add1ArgType), - NEONMAP1(vpaddd_u64, aarch64_neon_uaddv, AddRetType | Add1ArgType), + NEONMAP1(vpaddd_s64, vector_reduce_add, Add1ArgType), + NEONMAP1(vpaddd_u64, vector_reduce_add, Add1ArgType), NEONMAP1(vpmaxnmqd_f64, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType), NEONMAP1(vpmaxnms_f32, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType), NEONMAP1(vpmaxqd_f64, aarch64_neon_fmaxv, AddRetType | Add1ArgType), @@ -7067,127 +7091,6 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID, Int = Intrinsic::bitreverse; return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrbit"); } - case NEON::BI__builtin_neon_vaddv_u8: - // FIXME: These are handled by the AArch64 scalar code. - usgn = true; - [[fallthrough]]; - case NEON::BI__builtin_neon_vaddv_s8: { - Int = usgn ? Intrinsic::aarch64_neon_uaddv : Intrinsic::aarch64_neon_saddv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vaddv_u16: - usgn = true; - [[fallthrough]]; - case NEON::BI__builtin_neon_vaddv_s16: { - Int = usgn ? Intrinsic::aarch64_neon_uaddv : Intrinsic::aarch64_neon_saddv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 4); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } - case NEON::BI__builtin_neon_vaddvq_u8: - usgn = true; - [[fallthrough]]; - case NEON::BI__builtin_neon_vaddvq_s8: { - Int = usgn ? Intrinsic::aarch64_neon_uaddv : Intrinsic::aarch64_neon_saddv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 16); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vaddvq_u16: - usgn = true; - [[fallthrough]]; - case NEON::BI__builtin_neon_vaddvq_s16: { - Int = usgn ? Intrinsic::aarch64_neon_uaddv : Intrinsic::aarch64_neon_saddv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } - case NEON::BI__builtin_neon_vmaxv_u8: { - Int = Intrinsic::aarch64_neon_umaxv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vmaxv_u16: { - Int = Intrinsic::aarch64_neon_umaxv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 4); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } - case NEON::BI__builtin_neon_vmaxvq_u8: { - Int = Intrinsic::aarch64_neon_umaxv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 16); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vmaxvq_u16: { - Int = Intrinsic::aarch64_neon_umaxv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } - case NEON::BI__builtin_neon_vmaxv_s8: { - Int = Intrinsic::aarch64_neon_smaxv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vmaxv_s16: { - Int = Intrinsic::aarch64_neon_smaxv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 4); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } - case NEON::BI__builtin_neon_vmaxvq_s8: { - Int = Intrinsic::aarch64_neon_smaxv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 16); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vmaxvq_s16: { - Int = Intrinsic::aarch64_neon_smaxv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } case NEON::BI__builtin_neon_vmaxv_f16: { Int = Intrinsic::aarch64_neon_fmaxv; Ty = HalfTy; @@ -7206,78 +7109,6 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID, Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv"); return Builder.CreateTrunc(Ops[0], HalfTy); } - case NEON::BI__builtin_neon_vminv_u8: { - Int = Intrinsic::aarch64_neon_uminv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vminv_u16: { - Int = Intrinsic::aarch64_neon_uminv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 4); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } - case NEON::BI__builtin_neon_vminvq_u8: { - Int = Intrinsic::aarch64_neon_uminv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 16); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vminvq_u16: { - Int = Intrinsic::aarch64_neon_uminv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } - case NEON::BI__builtin_neon_vminv_s8: { - Int = Intrinsic::aarch64_neon_sminv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vminv_s16: { - Int = Intrinsic::aarch64_neon_sminv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 4); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } - case NEON::BI__builtin_neon_vminvq_s8: { - Int = Intrinsic::aarch64_neon_sminv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int8Ty, 16); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv"); - return Builder.CreateTrunc(Ops[0], Int8Ty); - } - case NEON::BI__builtin_neon_vminvq_s16: { - Int = Intrinsic::aarch64_neon_sminv; - Ty = Int32Ty; - VTy = llvm::FixedVectorType::get(Int16Ty, 8); - llvm::Type *Tys[2] = { Ty, VTy }; - Ops.push_back(EmitScalarExpr(E->getArg(0))); - Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv"); - return Builder.CreateTrunc(Ops[0], Int16Ty); - } case NEON::BI__builtin_neon_vminv_f16: { Int = Intrinsic::aarch64_neon_fminv; Ty = HalfTy; diff --git a/clang/lib/Driver/ToolChains/ZOS.cpp b/clang/lib/Driver/ToolChains/ZOS.cpp index 57bcb3c..9a3c453 100644 --- a/clang/lib/Driver/ToolChains/ZOS.cpp +++ b/clang/lib/Driver/ToolChains/ZOS.cpp @@ -75,7 +75,7 @@ void zos::Assembler::ConstructJob(Compilation &C, const JobAction &JA, const char *Exec = Args.MakeArgString(getToolChain().GetProgramPath("as")); C.addCommand(std::make_unique<Command>(JA, *this, ResponseFileSupport::None(), - Exec, CmdArgs, Inputs)); + Exec, CmdArgs, Inputs, Output)); } static std::string getLEHLQ(const ArgList &Args) { @@ -213,7 +213,7 @@ void zos::Linker::ConstructJob(Compilation &C, const JobAction &JA, const char *Exec = Args.MakeArgString(ToolChain.GetLinkerPath()); C.addCommand(std::make_unique<Command>(JA, *this, ResponseFileSupport::None(), - Exec, CmdArgs, Inputs)); + Exec, CmdArgs, Inputs, Output)); } ToolChain::RuntimeLibType ZOS::GetDefaultRuntimeLibType() const { diff --git a/clang/lib/Format/ContinuationIndenter.cpp b/clang/lib/Format/ContinuationIndenter.cpp index e5abf83..9ab024a 100644 --- a/clang/lib/Format/ContinuationIndenter.cpp +++ b/clang/lib/Format/ContinuationIndenter.cpp @@ -356,9 +356,11 @@ bool ContinuationIndenter::canBreak(const LineState &State) { return CurrentState.BreakBeforeClosingBrace; } - // Allow breaking before the right parens with block indentation if there was - // a break after the left parens, which is tracked by BreakBeforeClosingParen. - if (Style.AlignAfterOpenBracket == FormatStyle::BAS_BlockIndent && + // Check need to break before the right parens if there was a break after + // the left parens, which is tracked by BreakBeforeClosingParen. + if ((Style.BreakBeforeCloseBracketFunction || + Style.BreakBeforeCloseBracketIf || Style.BreakBeforeCloseBracketLoop || + Style.BreakBeforeCloseBracketSwitch) && Current.is(tok::r_paren)) { return CurrentState.BreakBeforeClosingParen; } @@ -837,32 +839,38 @@ void ContinuationIndenter::addTokenOnCurrentLine(LineState &State, bool DryRun, return Tok.is(tok::l_brace) && Tok.isNot(BK_Block) && Style.Cpp11BracedListStyle != FormatStyle::BLS_Block; }; - if (Tok.isNoneOf(tok::l_paren, TT_TemplateOpener, tok::l_square) && - !IsStartOfBracedList()) { + if (IsStartOfBracedList()) + return Style.BreakAfterOpenBracketBracedList; + if (Tok.isNoneOf(tok::l_paren, TT_TemplateOpener, tok::l_square)) return false; - } if (!Tok.Previous) return true; if (Tok.Previous->isIf()) - return Style.AlignAfterOpenBracket == FormatStyle::BAS_AlwaysBreak; - return Tok.Previous->isNoneOf(TT_CastRParen, tok::kw_for, tok::kw_while, - tok::kw_switch) && - !(Style.isJavaScript() && Tok.Previous->is(Keywords.kw_await)); + return Style.BreakAfterOpenBracketIf; + if (Tok.Previous->isLoop(Style)) + return Style.BreakAfterOpenBracketLoop; + if (Tok.Previous->is(tok::kw_switch)) + return Style.BreakAfterOpenBracketSwitch; + if (Style.BreakAfterOpenBracketFunction) { + return !Tok.Previous->is(TT_CastRParen) && + !(Style.isJavaScript() && Tok.is(Keywords.kw_await)); + } + return false; }; auto IsFunctionCallParen = [](const FormatToken &Tok) { return Tok.is(tok::l_paren) && Tok.ParameterCount > 0 && Tok.Previous && Tok.Previous->is(tok::identifier); }; - auto IsInTemplateString = [this](const FormatToken &Tok) { + auto IsInTemplateString = [this](const FormatToken &Tok, bool NestBlocks) { if (!Style.isJavaScript()) return false; for (const auto *Prev = &Tok; Prev; Prev = Prev->Previous) { if (Prev->is(TT_TemplateString) && Prev->opensScope()) return true; - if (Prev->opensScope() || - (Prev->is(TT_TemplateString) && Prev->closesScope())) { - break; - } + if (Prev->opensScope() && !NestBlocks) + return false; + if (Prev->is(TT_TemplateString) && Prev->closesScope()) + return false; } return false; }; @@ -884,21 +892,25 @@ void ContinuationIndenter::addTokenOnCurrentLine(LineState &State, bool DryRun, Tok.isOneOf(tok::ellipsis, Keywords.kw_await))) { return true; } - if (const auto *Previous = Tok.Previous; - !Previous || (Previous->isNoneOf(TT_FunctionDeclarationLParen, - TT_LambdaDefinitionLParen) && - !IsFunctionCallParen(*Previous))) { + const auto *Previous = TokAfterLParen.Previous; + assert(Previous); // IsOpeningBracket(Previous) + if (Previous->Previous && + (Previous->Previous->isIf() || Previous->Previous->isLoop(Style) || + Previous->Previous->is(tok::kw_switch))) { + return false; + } + if (Previous->isNoneOf(TT_FunctionDeclarationLParen, + TT_LambdaDefinitionLParen) && + !IsFunctionCallParen(*Previous)) { return true; } - if (IsOpeningBracket(Tok) || IsInTemplateString(Tok)) + if (IsOpeningBracket(Tok) || IsInTemplateString(Tok, true)) return true; const auto *Next = Tok.Next; return !Next || Next->isMemberAccess() || Next->is(TT_FunctionDeclarationLParen) || IsFunctionCallParen(*Next); }; - if ((Style.AlignAfterOpenBracket == FormatStyle::BAS_AlwaysBreak || - Style.AlignAfterOpenBracket == FormatStyle::BAS_BlockIndent) && - IsOpeningBracket(Previous) && State.Column > getNewLineColumn(State) && + if (IsOpeningBracket(Previous) && State.Column > getNewLineColumn(State) && // Don't do this for simple (no expressions) one-argument function calls // as that feels like needlessly wasting whitespace, e.g.: // @@ -920,7 +932,7 @@ void ContinuationIndenter::addTokenOnCurrentLine(LineState &State, bool DryRun, // Note: This doesn't apply to macro expansion lines, which are MACRO( , , ) // with args as children of the '(' and ',' tokens. It does not make sense to // align the commas with the opening paren. - if (Style.AlignAfterOpenBracket != FormatStyle::BAS_DontAlign && + if (Style.AlignAfterOpenBracket && !CurrentState.IsCSharpGenericTypeConstraint && Previous.opensScope() && Previous.isNoneOf(TT_ObjCMethodExpr, TT_RequiresClause, TT_TableGenDAGArgOpener, @@ -933,7 +945,7 @@ void ContinuationIndenter::addTokenOnCurrentLine(LineState &State, bool DryRun, Previous.Previous->isNoneOf(tok::identifier, tok::l_paren, BK_BracedInit))) || Previous.is(TT_VerilogMultiLineListLParen)) && - !IsInTemplateString(Current)) { + !IsInTemplateString(Current, false)) { CurrentState.Indent = State.Column + Spaces; CurrentState.IsAligned = true; } @@ -1271,8 +1283,20 @@ unsigned ContinuationIndenter::addTokenOnNewLine(LineState &State, } if (PreviousNonComment && PreviousNonComment->is(tok::l_paren)) { - CurrentState.BreakBeforeClosingParen = - Style.AlignAfterOpenBracket == FormatStyle::BAS_BlockIndent; + if (auto Previous = PreviousNonComment->Previous) { + if (Previous->isIf()) { + CurrentState.BreakBeforeClosingParen = Style.BreakBeforeCloseBracketIf; + } else if (Previous->isLoop(Style)) { + CurrentState.BreakBeforeClosingParen = + Style.BreakBeforeCloseBracketLoop; + } else if (Previous->is(tok::kw_switch)) { + CurrentState.BreakBeforeClosingParen = + Style.BreakBeforeCloseBracketSwitch; + } else { + CurrentState.BreakBeforeClosingParen = + Style.BreakBeforeCloseBracketFunction; + } + } } if (PreviousNonComment && PreviousNonComment->is(TT_TemplateOpener)) @@ -1416,13 +1440,17 @@ unsigned ContinuationIndenter::getNewLineColumn(const LineState &State) { State.Stack.size() > 1) { return State.Stack[State.Stack.size() - 2].LastSpace; } - if (Style.AlignAfterOpenBracket == FormatStyle::BAS_BlockIndent && - (Current.is(tok::r_paren) || - (Current.is(tok::r_brace) && Current.MatchingParen && - Current.MatchingParen->is(BK_BracedInit))) && + if (Style.BreakBeforeCloseBracketBracedList && Current.is(tok::r_brace) && + Current.MatchingParen && Current.MatchingParen->is(BK_BracedInit) && State.Stack.size() > 1) { return State.Stack[State.Stack.size() - 2].LastSpace; } + if ((Style.BreakBeforeCloseBracketFunction || + Style.BreakBeforeCloseBracketIf || Style.BreakBeforeCloseBracketLoop || + Style.BreakBeforeCloseBracketSwitch) && + Current.is(tok::r_paren) && State.Stack.size() > 1) { + return State.Stack[State.Stack.size() - 2].LastSpace; + } if (Style.BreakBeforeTemplateCloser && Current.is(TT_TemplateCloser) && State.Stack.size() > 1) { return State.Stack[State.Stack.size() - 2].LastSpace; @@ -1844,8 +1872,8 @@ void ContinuationIndenter::moveStatePastFakeLParens(LineState &State, PrecedenceLevel < prec::Assignment) && (!Previous || Previous->isNot(tok::kw_return) || (!Style.isJava() && PrecedenceLevel > 0)) && - (Style.AlignAfterOpenBracket != FormatStyle::BAS_DontAlign || - PrecedenceLevel > prec::Comma || Current.NestingLevel == 0) && + (Style.AlignAfterOpenBracket || PrecedenceLevel > prec::Comma || + Current.NestingLevel == 0) && (!Style.isTableGen() || (Previous && Previous->isOneOf(TT_TableGenDAGArgListComma, TT_TableGenDAGArgListCommaToBreak)))) { @@ -1885,8 +1913,7 @@ void ContinuationIndenter::moveStatePastFakeLParens(LineState &State, if (PrecedenceLevel > prec::Unknown) NewParenState.LastSpace = std::max(NewParenState.LastSpace, State.Column); if (PrecedenceLevel != prec::Conditional && - Current.isNot(TT_UnaryOperator) && - Style.AlignAfterOpenBracket != FormatStyle::BAS_DontAlign) { + Current.isNot(TT_UnaryOperator) && Style.AlignAfterOpenBracket) { NewParenState.StartOfFunctionCall = State.Column; } diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp index edd126c..dd14fcd 100644 --- a/clang/lib/Format/Format.cpp +++ b/clang/lib/Format/Format.cpp @@ -32,6 +32,13 @@ using clang::format::FormatStyle; LLVM_YAML_IS_SEQUENCE_VECTOR(FormatStyle::RawStringFormat) +enum BracketAlignmentStyle : int8_t { + BAS_Align, + BAS_DontAlign, + BAS_AlwaysBreak, + BAS_BlockIndent +}; + namespace llvm { namespace yaml { template <> @@ -204,16 +211,16 @@ template <> struct MappingTraits<FormatStyle::BraceWrappingFlags> { } }; -template <> struct ScalarEnumerationTraits<FormatStyle::BracketAlignmentStyle> { - static void enumeration(IO &IO, FormatStyle::BracketAlignmentStyle &Value) { - IO.enumCase(Value, "Align", FormatStyle::BAS_Align); - IO.enumCase(Value, "DontAlign", FormatStyle::BAS_DontAlign); - IO.enumCase(Value, "AlwaysBreak", FormatStyle::BAS_AlwaysBreak); - IO.enumCase(Value, "BlockIndent", FormatStyle::BAS_BlockIndent); +template <> struct ScalarEnumerationTraits<BracketAlignmentStyle> { + static void enumeration(IO &IO, BracketAlignmentStyle &Value) { + IO.enumCase(Value, "Align", BAS_Align); + IO.enumCase(Value, "DontAlign", BAS_DontAlign); // For backward compatibility. - IO.enumCase(Value, "true", FormatStyle::BAS_Align); - IO.enumCase(Value, "false", FormatStyle::BAS_DontAlign); + IO.enumCase(Value, "true", BAS_Align); + IO.enumCase(Value, "false", BAS_DontAlign); + IO.enumCase(Value, "AlwaysBreak", BAS_AlwaysBreak); + IO.enumCase(Value, "BlockIndent", BAS_BlockIndent); } }; @@ -979,6 +986,54 @@ template <> struct MappingTraits<FormatStyle> { bool SpacesInCStyleCastParentheses = false; bool SpacesInParentheses = false; + if (IO.outputting()) { + IO.mapOptional("AlignAfterOpenBracket", Style.AlignAfterOpenBracket); + } else { + // For backward compatibility. + BracketAlignmentStyle LocalBAS = BAS_Align; + if (IsGoogleOrChromium) { + FormatStyle::LanguageKind Language = Style.Language; + if (Language == FormatStyle::LK_None) + Language = ((FormatStyle *)IO.getContext())->Language; + if (Language == FormatStyle::LK_JavaScript) + LocalBAS = BAS_AlwaysBreak; + else if (Language == FormatStyle::LK_Java) + LocalBAS = BAS_DontAlign; + } else if (BasedOnStyle.equals_insensitive("webkit")) { + LocalBAS = BAS_DontAlign; + } + IO.mapOptional("AlignAfterOpenBracket", LocalBAS); + Style.BreakAfterOpenBracketBracedList = false; + Style.BreakAfterOpenBracketFunction = false; + Style.BreakAfterOpenBracketIf = false; + Style.BreakAfterOpenBracketLoop = false; + Style.BreakAfterOpenBracketSwitch = false; + Style.BreakBeforeCloseBracketBracedList = false; + Style.BreakBeforeCloseBracketFunction = false; + Style.BreakBeforeCloseBracketIf = false; + Style.BreakBeforeCloseBracketLoop = false; + Style.BreakBeforeCloseBracketSwitch = false; + + switch (LocalBAS) { + case BAS_DontAlign: + Style.AlignAfterOpenBracket = false; + break; + case BAS_BlockIndent: + Style.BreakBeforeCloseBracketBracedList = true; + Style.BreakBeforeCloseBracketFunction = true; + Style.BreakBeforeCloseBracketIf = true; + [[fallthrough]]; + case BAS_AlwaysBreak: + Style.BreakAfterOpenBracketBracedList = true; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakAfterOpenBracketIf = true; + [[fallthrough]]; + case BAS_Align: + Style.AlignAfterOpenBracket = true; + break; + } + } + // For backward compatibility. if (!IO.outputting()) { IO.mapOptional("AlignEscapedNewlinesLeft", Style.AlignEscapedNewlines); @@ -1014,7 +1069,6 @@ template <> struct MappingTraits<FormatStyle> { } IO.mapOptional("AccessModifierOffset", Style.AccessModifierOffset); - IO.mapOptional("AlignAfterOpenBracket", Style.AlignAfterOpenBracket); IO.mapOptional("AlignArrayOfStructures", Style.AlignArrayOfStructures); IO.mapOptional("AlignConsecutiveAssignments", Style.AlignConsecutiveAssignments); @@ -1079,10 +1133,29 @@ template <> struct MappingTraits<FormatStyle> { IO.mapOptional("BreakAfterAttributes", Style.BreakAfterAttributes); IO.mapOptional("BreakAfterJavaFieldAnnotations", Style.BreakAfterJavaFieldAnnotations); + IO.mapOptional("BreakAfterOpenBracketBracedList", + Style.BreakAfterOpenBracketBracedList); + IO.mapOptional("BreakAfterOpenBracketFunction", + Style.BreakAfterOpenBracketFunction); + IO.mapOptional("BreakAfterOpenBracketIf", Style.BreakAfterOpenBracketIf); + IO.mapOptional("BreakAfterOpenBracketLoop", + Style.BreakAfterOpenBracketLoop); + IO.mapOptional("BreakAfterOpenBracketSwitch", + Style.BreakAfterOpenBracketSwitch); IO.mapOptional("BreakAfterReturnType", Style.BreakAfterReturnType); IO.mapOptional("BreakArrays", Style.BreakArrays); IO.mapOptional("BreakBeforeBinaryOperators", Style.BreakBeforeBinaryOperators); + IO.mapOptional("BreakBeforeCloseBracketBracedList", + Style.BreakBeforeCloseBracketBracedList); + IO.mapOptional("BreakBeforeCloseBracketFunction", + Style.BreakBeforeCloseBracketFunction); + IO.mapOptional("BreakBeforeCloseBracketIf", + Style.BreakBeforeCloseBracketIf); + IO.mapOptional("BreakBeforeCloseBracketLoop", + Style.BreakBeforeCloseBracketLoop); + IO.mapOptional("BreakBeforeCloseBracketSwitch", + Style.BreakBeforeCloseBracketSwitch); IO.mapOptional("BreakBeforeConceptDeclarations", Style.BreakBeforeConceptDeclarations); IO.mapOptional("BreakBeforeBraces", Style.BreakBeforeBraces); @@ -1561,7 +1634,7 @@ static void expandPresetsSpacesInParens(FormatStyle &Expanded) { FormatStyle getLLVMStyle(FormatStyle::LanguageKind Language) { FormatStyle LLVMStyle; LLVMStyle.AccessModifierOffset = -2; - LLVMStyle.AlignAfterOpenBracket = FormatStyle::BAS_Align; + LLVMStyle.AlignAfterOpenBracket = true; LLVMStyle.AlignArrayOfStructures = FormatStyle::AIAS_None; LLVMStyle.AlignConsecutiveAssignments = {}; LLVMStyle.AlignConsecutiveAssignments.PadOperators = true; @@ -1621,10 +1694,20 @@ FormatStyle getLLVMStyle(FormatStyle::LanguageKind Language) { LLVMStyle.BreakAdjacentStringLiterals = true; LLVMStyle.BreakAfterAttributes = FormatStyle::ABS_Leave; LLVMStyle.BreakAfterJavaFieldAnnotations = false; + LLVMStyle.BreakAfterOpenBracketBracedList = false; + LLVMStyle.BreakAfterOpenBracketFunction = false; + LLVMStyle.BreakAfterOpenBracketIf = false; + LLVMStyle.BreakAfterOpenBracketLoop = false; + LLVMStyle.BreakAfterOpenBracketSwitch = false; LLVMStyle.BreakAfterReturnType = FormatStyle::RTBS_None; LLVMStyle.BreakArrays = true; LLVMStyle.BreakBeforeBinaryOperators = FormatStyle::BOS_None; LLVMStyle.BreakBeforeBraces = FormatStyle::BS_Attach; + LLVMStyle.BreakBeforeCloseBracketBracedList = false; + LLVMStyle.BreakBeforeCloseBracketFunction = false; + LLVMStyle.BreakBeforeCloseBracketIf = false; + LLVMStyle.BreakBeforeCloseBracketLoop = false; + LLVMStyle.BreakBeforeCloseBracketSwitch = false; LLVMStyle.BreakBeforeConceptDeclarations = FormatStyle::BBCDS_Always; LLVMStyle.BreakBeforeInlineASMColon = FormatStyle::BBIAS_OnlyMultiline; LLVMStyle.BreakBeforeTemplateCloser = false; @@ -1877,7 +1960,7 @@ FormatStyle getGoogleStyle(FormatStyle::LanguageKind Language) { GoogleStyle.PenaltyReturnTypeOnItsOwnLine = 200; if (Language == FormatStyle::LK_Java) { - GoogleStyle.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + GoogleStyle.AlignAfterOpenBracket = false; GoogleStyle.AlignOperands = FormatStyle::OAS_DontAlign; GoogleStyle.AlignTrailingComments = {}; GoogleStyle.AlignTrailingComments.Kind = FormatStyle::TCAS_Never; @@ -1889,7 +1972,9 @@ FormatStyle getGoogleStyle(FormatStyle::LanguageKind Language) { GoogleStyle.SpaceAfterCStyleCast = true; GoogleStyle.SpacesBeforeTrailingComments = 1; } else if (Language == FormatStyle::LK_JavaScript) { - GoogleStyle.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + GoogleStyle.BreakAfterOpenBracketBracedList = true; + GoogleStyle.BreakAfterOpenBracketFunction = true; + GoogleStyle.BreakAfterOpenBracketIf = true; GoogleStyle.AlignOperands = FormatStyle::OAS_DontAlign; GoogleStyle.AllowShortFunctionsOnASingleLine = FormatStyle::SFS_Empty; // TODO: still under discussion whether to switch to SLS_All. @@ -2026,7 +2111,7 @@ FormatStyle getMozillaStyle() { FormatStyle getWebKitStyle() { FormatStyle Style = getLLVMStyle(); Style.AccessModifierOffset = -4; - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; Style.AlignOperands = FormatStyle::OAS_DontAlign; Style.AlignTrailingComments = {}; Style.AlignTrailingComments.Kind = FormatStyle::TCAS_Never; diff --git a/clang/lib/Format/FormatToken.cpp b/clang/lib/Format/FormatToken.cpp index d1c6264..28fdbcb 100644 --- a/clang/lib/Format/FormatToken.cpp +++ b/clang/lib/Format/FormatToken.cpp @@ -68,7 +68,7 @@ bool FormatToken::isBlockIndentedInitRBrace(const FormatStyle &Style) const { assert(MatchingParen); assert(MatchingParen->is(tok::l_brace)); if (Style.Cpp11BracedListStyle == FormatStyle::BLS_Block || - Style.AlignAfterOpenBracket != FormatStyle::BAS_BlockIndent) { + !Style.BreakBeforeCloseBracketBracedList) { return false; } const auto *LBrace = MatchingParen; @@ -198,7 +198,7 @@ void CommaSeparatedList::precomputeFormattingInfos(const FormatToken *Token) { return; // Column format doesn't really make sense if we don't align after brackets. - if (Style.AlignAfterOpenBracket == FormatStyle::BAS_DontAlign) + if (!Style.AlignAfterOpenBracket) return; FormatToken *ItemBegin = Token->Next; diff --git a/clang/lib/Format/FormatToken.h b/clang/lib/Format/FormatToken.h index 6f3d24a..d833130 100644 --- a/clang/lib/Format/FormatToken.h +++ b/clang/lib/Format/FormatToken.h @@ -666,6 +666,12 @@ public: (endsSequence(tok::identifier, tok::kw_if) && AllowConstexprMacro); } + bool isLoop(const FormatStyle &Style) const { + return isOneOf(tok::kw_for, tok::kw_while) || + (Style.isJavaScript() && isNot(tok::l_paren) && Previous && + Previous->is(tok::kw_for)); + } + bool closesScopeAfterBlock() const { if (getBlockKind() == BK_Block) return true; diff --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp index 021d8c6..8e227da 100644 --- a/clang/lib/Format/TokenAnnotator.cpp +++ b/clang/lib/Format/TokenAnnotator.cpp @@ -4427,10 +4427,8 @@ unsigned TokenAnnotator::splitPenalty(const AnnotatedLine &Line, if (Left.is(tok::l_paren) && Style.PenaltyBreakOpenParenthesis != 0) return Style.PenaltyBreakOpenParenthesis; - if (Left.is(tok::l_paren) && InFunctionDecl && - Style.AlignAfterOpenBracket != FormatStyle::BAS_DontAlign) { + if (Left.is(tok::l_paren) && InFunctionDecl && Style.AlignAfterOpenBracket) return 100; - } if (Left.is(tok::l_paren) && Left.Previous && (Left.Previous->isOneOf(tok::kw_for, tok::kw__Generic) || Left.Previous->isIf())) { @@ -4446,7 +4444,7 @@ unsigned TokenAnnotator::splitPenalty(const AnnotatedLine &Line, // If we aren't aligning after opening parens/braces we can always break // here unless the style does not want us to place all arguments on the // next line. - if (Style.AlignAfterOpenBracket == FormatStyle::BAS_DontAlign && + if (!Style.AlignAfterOpenBracket && (Left.ParameterCount <= 1 || Style.AllowAllArgumentsOnNextLine)) { return 0; } @@ -6226,24 +6224,31 @@ bool TokenAnnotator::canBreakBefore(const AnnotatedLine &Line, (Right.isBlockIndentedInitRBrace(Style))); } - // We only break before r_paren if we're in a block indented context. + // We can break before r_paren if we're in a block indented context or + // a control statement with an explicit style option. if (Right.is(tok::r_paren)) { - if (Style.AlignAfterOpenBracket != FormatStyle::BAS_BlockIndent || - !Right.MatchingParen) { + if (!Right.MatchingParen) return false; - } auto Next = Right.Next; if (Next && Next->is(tok::r_paren)) Next = Next->Next; if (Next && Next->is(tok::l_paren)) return false; const FormatToken *Previous = Right.MatchingParen->Previous; - return !(Previous && (Previous->is(tok::kw_for) || Previous->isIf())); + if (!Previous) + return false; + if (Previous->isIf()) + return Style.BreakBeforeCloseBracketIf; + if (Previous->isLoop(Style)) + return Style.BreakBeforeCloseBracketLoop; + if (Previous->is(tok::kw_switch)) + return Style.BreakBeforeCloseBracketSwitch; + return Style.BreakBeforeCloseBracketFunction; } if (Left.isOneOf(tok::r_paren, TT_TrailingAnnotation) && Right.is(TT_TrailingAnnotation) && - Style.AlignAfterOpenBracket == FormatStyle::BAS_BlockIndent) { + Style.BreakBeforeCloseBracketFunction) { return false; } diff --git a/clang/lib/Frontend/TextDiagnostic.cpp b/clang/lib/Frontend/TextDiagnostic.cpp index f5add2a..aea3e72 100644 --- a/clang/lib/Frontend/TextDiagnostic.cpp +++ b/clang/lib/Frontend/TextDiagnostic.cpp @@ -22,22 +22,16 @@ using namespace clang; -static const enum raw_ostream::Colors noteColor = raw_ostream::CYAN; -static const enum raw_ostream::Colors remarkColor = - raw_ostream::BLUE; -static const enum raw_ostream::Colors fixitColor = - raw_ostream::GREEN; -static const enum raw_ostream::Colors caretColor = - raw_ostream::GREEN; -static const enum raw_ostream::Colors warningColor = - raw_ostream::MAGENTA; -static const enum raw_ostream::Colors templateColor = - raw_ostream::CYAN; -static const enum raw_ostream::Colors errorColor = raw_ostream::RED; -static const enum raw_ostream::Colors fatalColor = raw_ostream::RED; +static constexpr raw_ostream::Colors NoteColor = raw_ostream::CYAN; +static constexpr raw_ostream::Colors RemarkColor = raw_ostream::BLUE; +static constexpr raw_ostream::Colors FixitColor = raw_ostream::GREEN; +static constexpr raw_ostream::Colors CaretColor = raw_ostream::GREEN; +static constexpr raw_ostream::Colors WarningColor = raw_ostream::MAGENTA; +static constexpr raw_ostream::Colors TemplateColor = raw_ostream::CYAN; +static constexpr raw_ostream::Colors ErrorColor = raw_ostream::RED; +static constexpr raw_ostream::Colors FatalColor = raw_ostream::RED; // Used for changing only the bold attribute. -static const enum raw_ostream::Colors savedColor = - raw_ostream::SAVEDCOLOR; +static constexpr raw_ostream::Colors SavedColor = raw_ostream::SAVEDCOLOR; // Magenta is taken for 'warning'. Red is already 'error' and 'cyan' // is already taken for 'note'. Green is already used to underline @@ -47,6 +41,43 @@ static constexpr raw_ostream::Colors CommentColor = raw_ostream::YELLOW; static constexpr raw_ostream::Colors LiteralColor = raw_ostream::GREEN; static constexpr raw_ostream::Colors KeywordColor = raw_ostream::BLUE; +namespace { +template <typename Sub> class ColumnsOrBytes { +public: + int V = 0; + ColumnsOrBytes(int V) : V(V) {} + bool isValid() const { return V != -1; } + Sub next() const { return Sub(V + 1); } + Sub prev() const { return Sub(V - 1); } + + bool operator>(Sub O) const { return V > O.V; } + bool operator<(Sub O) const { return V < O.V; } + bool operator<=(Sub B) const { return V <= B.V; } + bool operator!=(Sub C) const { return C.V != V; } + + Sub operator+(Sub B) const { return Sub(V + B.V); } + Sub &operator+=(Sub B) { + V += B.V; + return *static_cast<Sub *>(this); + } + Sub operator-(Sub B) const { return Sub(V - B.V); } + Sub &operator-=(Sub B) { + V -= B.V; + return *static_cast<Sub *>(this); + } +}; + +class Bytes final : public ColumnsOrBytes<Bytes> { +public: + Bytes(int V) : ColumnsOrBytes(V) {} +}; + +class Columns final : public ColumnsOrBytes<Columns> { +public: + Columns(int V) : ColumnsOrBytes(V) {} +}; +} // namespace + /// Add highlights to differences in template strings. static void applyTemplateHighlighting(raw_ostream &OS, StringRef Str, bool &Normal, bool Bold) { @@ -58,11 +89,11 @@ static void applyTemplateHighlighting(raw_ostream &OS, StringRef Str, Str = Str.substr(Pos + 1); if (Normal) - OS.changeColor(templateColor, true); + OS.changeColor(TemplateColor, true); else { OS.resetColor(); if (Bold) - OS.changeColor(savedColor, true); + OS.changeColor(SavedColor, true); } Normal = !Normal; } @@ -109,8 +140,8 @@ printableTextForNextCharacter(StringRef SourceLine, size_t *I, if (SourceLine[*I] == '\t') { assert(0 < TabStop && TabStop <= DiagnosticOptions::MaxTabStop && "Invalid -ftabstop value"); - unsigned Col = bytesSincePreviousTabOrLineBegin(SourceLine, *I); - unsigned NumSpaces = TabStop - (Col % TabStop); + unsigned LineBytes = bytesSincePreviousTabOrLineBegin(SourceLine, *I); + unsigned NumSpaces = TabStop - (LineBytes % TabStop); assert(0 < NumSpaces && NumSpaces <= TabStop && "Invalid computation of space amt"); ++(*I); @@ -220,97 +251,99 @@ static void expandTabs(std::string &SourceLine, unsigned TabStop) { /// (\\u3042 is represented in UTF-8 by three bytes and takes two columns to /// display) static void genColumnByteMapping(StringRef SourceLine, unsigned TabStop, - SmallVectorImpl<int> &BytesOut, - SmallVectorImpl<int> &ColumnsOut) { + SmallVectorImpl<Bytes> &BytesOut, + SmallVectorImpl<Columns> &ColumnsOut) { assert(BytesOut.empty()); assert(ColumnsOut.empty()); if (SourceLine.empty()) { - BytesOut.resize(1u, 0); - ColumnsOut.resize(1u, 0); + BytesOut.resize(1u, Bytes(0)); + ColumnsOut.resize(1u, Columns(0)); return; } ColumnsOut.resize(SourceLine.size() + 1, -1); - int Columns = 0; + Columns NumColumns = 0; size_t I = 0; while (I < SourceLine.size()) { - ColumnsOut[I] = Columns; - BytesOut.resize(Columns + 1, -1); - BytesOut.back() = I; + ColumnsOut[I] = NumColumns; + BytesOut.resize(NumColumns.V + 1, -1); + BytesOut.back() = Bytes(I); auto [Str, Printable] = printableTextForNextCharacter(SourceLine, &I, TabStop); - Columns += llvm::sys::locale::columnWidth(Str); + NumColumns += Columns(llvm::sys::locale::columnWidth(Str)); } - ColumnsOut.back() = Columns; - BytesOut.resize(Columns + 1, -1); - BytesOut.back() = I; + ColumnsOut.back() = NumColumns; + BytesOut.resize(NumColumns.V + 1, -1); + BytesOut.back() = Bytes(I); } namespace { struct SourceColumnMap { SourceColumnMap(StringRef SourceLine, unsigned TabStop) - : m_SourceLine(SourceLine) { + : SourceLine(SourceLine) { - genColumnByteMapping(SourceLine, TabStop, m_columnToByte, m_byteToColumn); + genColumnByteMapping(SourceLine, TabStop, ColumnToByte, ByteToColumn); - assert(m_byteToColumn.size()==SourceLine.size()+1); - assert(0 < m_byteToColumn.size() && 0 < m_columnToByte.size()); - assert(m_byteToColumn.size() - == static_cast<unsigned>(m_columnToByte.back()+1)); - assert(static_cast<unsigned>(m_byteToColumn.back()+1) - == m_columnToByte.size()); + assert(ByteToColumn.size() == SourceLine.size() + 1); + assert(0 < ByteToColumn.size() && 0 < ColumnToByte.size()); + assert(ByteToColumn.size() == + static_cast<unsigned>(ColumnToByte.back().V + 1)); + assert(static_cast<unsigned>(ByteToColumn.back().V + 1) == + ColumnToByte.size()); } - int columns() const { return m_byteToColumn.back(); } - int bytes() const { return m_columnToByte.back(); } + Columns columns() const { return ByteToColumn.back(); } + Bytes bytes() const { return ColumnToByte.back(); } /// Map a byte to the column which it is at the start of, or return -1 /// if it is not at the start of a column (for a UTF-8 trailing byte). - int byteToColumn(int n) const { - assert(0<=n && n<static_cast<int>(m_byteToColumn.size())); - return m_byteToColumn[n]; + Columns byteToColumn(Bytes N) const { + assert(0 <= N.V && N.V < static_cast<int>(ByteToColumn.size())); + return ByteToColumn[N.V]; } /// Map a byte to the first column which contains it. - int byteToContainingColumn(int N) const { - assert(0 <= N && N < static_cast<int>(m_byteToColumn.size())); - while (m_byteToColumn[N] == -1) - --N; - return m_byteToColumn[N]; + Columns byteToContainingColumn(Bytes N) const { + assert(0 <= N.V && N.V < static_cast<int>(ByteToColumn.size())); + while (!ByteToColumn[N.V].isValid()) + --N.V; + return ByteToColumn[N.V]; } /// Map a column to the byte which starts the column, or return -1 if /// the column the second or subsequent column of an expanded tab or similar /// multi-column entity. - int columnToByte(int n) const { - assert(0<=n && n<static_cast<int>(m_columnToByte.size())); - return m_columnToByte[n]; + Bytes columnToByte(Columns N) const { + assert(0 <= N.V && N.V < static_cast<int>(ColumnToByte.size())); + return ColumnToByte[N.V]; } /// Map from a byte index to the next byte which starts a column. - int startOfNextColumn(int N) const { - assert(0 <= N && N < static_cast<int>(m_byteToColumn.size() - 1)); - while (byteToColumn(++N) == -1) {} + Bytes startOfNextColumn(Bytes N) const { + assert(0 <= N.V && N.V < static_cast<int>(ByteToColumn.size() - 1)); + N = N.next(); + while (!byteToColumn(N).isValid()) + N = N.next(); return N; } /// Map from a byte index to the previous byte which starts a column. - int startOfPreviousColumn(int N) const { - assert(0 < N && N < static_cast<int>(m_byteToColumn.size())); - while (byteToColumn(--N) == -1) {} + Bytes startOfPreviousColumn(Bytes N) const { + assert(0 < N.V && N.V < static_cast<int>(ByteToColumn.size())); + N = N.prev(); + while (!byteToColumn(N).isValid()) + N = N.prev(); return N; } - StringRef getSourceLine() const { - return m_SourceLine; - } + StringRef getSourceLine() const { return SourceLine; } private: - const std::string m_SourceLine; - SmallVector<int,200> m_byteToColumn; - SmallVector<int,200> m_columnToByte; + StringRef SourceLine; + SmallVector<Columns, 200> ByteToColumn; + SmallVector<Bytes, 200> ColumnToByte; }; } // end anonymous namespace @@ -319,14 +352,15 @@ private: static void selectInterestingSourceRegion(std::string &SourceLine, std::string &CaretLine, std::string &FixItInsertionLine, - unsigned Columns, - const SourceColumnMap &map) { - unsigned CaretColumns = CaretLine.size(); - unsigned FixItColumns = llvm::sys::locale::columnWidth(FixItInsertionLine); - unsigned MaxColumns = std::max(static_cast<unsigned>(map.columns()), - std::max(CaretColumns, FixItColumns)); + Columns NonGutterColumns, + const SourceColumnMap &Map) { + Columns CaretColumns = Columns(CaretLine.size()); + Columns FixItColumns = + Columns(llvm::sys::locale::columnWidth(FixItInsertionLine)); + Columns MaxColumns = + std::max({Map.columns().V, CaretColumns.V, FixItColumns.V}); // if the number of columns is less than the desired number we're done - if (MaxColumns <= Columns) + if (MaxColumns <= NonGutterColumns) return; // No special characters are allowed in CaretLine. @@ -334,13 +368,13 @@ static void selectInterestingSourceRegion(std::string &SourceLine, // Find the slice that we need to display the full caret line // correctly. - unsigned CaretStart = 0, CaretEnd = CaretLine.size(); - for (; CaretStart != CaretEnd; ++CaretStart) - if (!isWhitespace(CaretLine[CaretStart])) + Columns CaretStart = 0, CaretEnd = CaretLine.size(); + for (; CaretStart != CaretEnd; CaretStart = CaretStart.next()) + if (!isWhitespace(CaretLine[CaretStart.V])) break; - for (; CaretEnd != CaretStart; --CaretEnd) - if (!isWhitespace(CaretLine[CaretEnd - 1])) + for (; CaretEnd != CaretStart; CaretEnd = CaretEnd.prev()) + if (!isWhitespace(CaretLine[CaretEnd.V - 1])) break; // caret has already been inserted into CaretLine so the above whitespace @@ -349,39 +383,38 @@ static void selectInterestingSourceRegion(std::string &SourceLine, // If we have a fix-it line, make sure the slice includes all of the // fix-it information. if (!FixItInsertionLine.empty()) { - unsigned FixItStart = 0, FixItEnd = FixItInsertionLine.size(); - for (; FixItStart != FixItEnd; ++FixItStart) - if (!isWhitespace(FixItInsertionLine[FixItStart])) - break; - - for (; FixItEnd != FixItStart; --FixItEnd) - if (!isWhitespace(FixItInsertionLine[FixItEnd - 1])) - break; - // We can safely use the byte offset FixItStart as the column offset // because the characters up until FixItStart are all ASCII whitespace // characters. - unsigned FixItStartCol = FixItStart; - unsigned FixItEndCol - = llvm::sys::locale::columnWidth(FixItInsertionLine.substr(0, FixItEnd)); - - CaretStart = std::min(FixItStartCol, CaretStart); - CaretEnd = std::max(FixItEndCol, CaretEnd); + Bytes FixItStart = 0; + Bytes FixItEnd = Bytes(FixItInsertionLine.size()); + while (FixItStart != FixItEnd && + isWhitespace(FixItInsertionLine[FixItStart.V])) + FixItStart = FixItStart.next(); + + while (FixItEnd != FixItStart && + isWhitespace(FixItInsertionLine[FixItEnd.V - 1])) + FixItEnd = FixItEnd.prev(); + + Columns FixItStartCol = Columns(FixItStart.V); + Columns FixItEndCol = Columns(llvm::sys::locale::columnWidth( + FixItInsertionLine.substr(0, FixItEnd.V))); + + CaretStart = std::min(FixItStartCol.V, CaretStart.V); + CaretEnd = std::max(FixItEndCol.V, CaretEnd.V); } // CaretEnd may have been set at the middle of a character // If it's not at a character's first column then advance it past the current // character. - while (static_cast<int>(CaretEnd) < map.columns() && - -1 == map.columnToByte(CaretEnd)) - ++CaretEnd; - - assert((static_cast<int>(CaretStart) > map.columns() || - -1!=map.columnToByte(CaretStart)) && - "CaretStart must not point to a column in the middle of a source" - " line character"); - assert((static_cast<int>(CaretEnd) > map.columns() || - -1!=map.columnToByte(CaretEnd)) && + while (CaretEnd < Map.columns() && !Map.columnToByte(CaretEnd).isValid()) + CaretEnd = CaretEnd.next(); + + assert( + (CaretStart > Map.columns() || Map.columnToByte(CaretStart).isValid()) && + "CaretStart must not point to a column in the middle of a source" + " line character"); + assert((CaretEnd > Map.columns() || Map.columnToByte(CaretEnd).isValid()) && "CaretEnd must not point to a column in the middle of a source line" " character"); @@ -390,70 +423,69 @@ static void selectInterestingSourceRegion(std::string &SourceLine, // number of columns we have, try to grow the slice to encompass // more context. - unsigned SourceStart = map.columnToByte(std::min<unsigned>(CaretStart, - map.columns())); - unsigned SourceEnd = map.columnToByte(std::min<unsigned>(CaretEnd, - map.columns())); + Bytes SourceStart = Map.columnToByte(std::min(CaretStart.V, Map.columns().V)); + Bytes SourceEnd = Map.columnToByte(std::min(CaretEnd.V, Map.columns().V)); - unsigned CaretColumnsOutsideSource = CaretEnd-CaretStart - - (map.byteToColumn(SourceEnd)-map.byteToColumn(SourceStart)); + Columns CaretColumnsOutsideSource = + CaretEnd - CaretStart - + (Map.byteToColumn(SourceEnd) - Map.byteToColumn(SourceStart)); - char const *front_ellipse = " ..."; - char const *front_space = " "; - char const *back_ellipse = "..."; - unsigned ellipses_space = strlen(front_ellipse) + strlen(back_ellipse); + constexpr StringRef FrontEllipse = " ..."; + constexpr StringRef FrontSpace = " "; + constexpr StringRef BackEllipse = "..."; + Columns EllipsesColumns = Columns(FrontEllipse.size() + BackEllipse.size()); - unsigned TargetColumns = Columns; + Columns TargetColumns = NonGutterColumns; // Give us extra room for the ellipses // and any of the caret line that extends past the source - if (TargetColumns > ellipses_space+CaretColumnsOutsideSource) - TargetColumns -= ellipses_space+CaretColumnsOutsideSource; + if (TargetColumns > EllipsesColumns + CaretColumnsOutsideSource) + TargetColumns -= EllipsesColumns + CaretColumnsOutsideSource; - while (SourceStart>0 || SourceEnd<SourceLine.size()) { + while (SourceStart > 0 || SourceEnd < SourceLine.size()) { bool ExpandedRegion = false; - if (SourceStart>0) { - unsigned NewStart = map.startOfPreviousColumn(SourceStart); + if (SourceStart > 0) { + Bytes NewStart = Map.startOfPreviousColumn(SourceStart); // Skip over any whitespace we see here; we're looking for // another bit of interesting text. // FIXME: Detect non-ASCII whitespace characters too. - while (NewStart && isWhitespace(SourceLine[NewStart])) - NewStart = map.startOfPreviousColumn(NewStart); + while (NewStart > 0 && isWhitespace(SourceLine[NewStart.V])) + NewStart = Map.startOfPreviousColumn(NewStart); // Skip over this bit of "interesting" text. - while (NewStart) { - unsigned Prev = map.startOfPreviousColumn(NewStart); - if (isWhitespace(SourceLine[Prev])) + while (NewStart > 0) { + Bytes Prev = Map.startOfPreviousColumn(NewStart); + if (isWhitespace(SourceLine[Prev.V])) break; NewStart = Prev; } - assert(map.byteToColumn(NewStart) != -1); - unsigned NewColumns = map.byteToColumn(SourceEnd) - - map.byteToColumn(NewStart); + assert(Map.byteToColumn(NewStart).isValid()); + Columns NewColumns = + Map.byteToColumn(SourceEnd) - Map.byteToColumn(NewStart); if (NewColumns <= TargetColumns) { SourceStart = NewStart; ExpandedRegion = true; } } - if (SourceEnd<SourceLine.size()) { - unsigned NewEnd = map.startOfNextColumn(SourceEnd); + if (SourceEnd < SourceLine.size()) { + Bytes NewEnd = Map.startOfNextColumn(SourceEnd); // Skip over any whitespace we see here; we're looking for // another bit of interesting text. // FIXME: Detect non-ASCII whitespace characters too. - while (NewEnd < SourceLine.size() && isWhitespace(SourceLine[NewEnd])) - NewEnd = map.startOfNextColumn(NewEnd); + while (NewEnd < SourceLine.size() && isWhitespace(SourceLine[NewEnd.V])) + NewEnd = Map.startOfNextColumn(NewEnd); // Skip over this bit of "interesting" text. - while (NewEnd < SourceLine.size() && isWhitespace(SourceLine[NewEnd])) - NewEnd = map.startOfNextColumn(NewEnd); + while (NewEnd < SourceLine.size() && isWhitespace(SourceLine[NewEnd.V])) + NewEnd = Map.startOfNextColumn(NewEnd); - assert(map.byteToColumn(NewEnd) != -1); - unsigned NewColumns = map.byteToColumn(NewEnd) - - map.byteToColumn(SourceStart); + assert(Map.byteToColumn(NewEnd).isValid()); + Columns NewColumns = + Map.byteToColumn(NewEnd) - Map.byteToColumn(SourceStart); if (NewColumns <= TargetColumns) { SourceEnd = NewEnd; ExpandedRegion = true; @@ -464,39 +496,41 @@ static void selectInterestingSourceRegion(std::string &SourceLine, break; } - CaretStart = map.byteToColumn(SourceStart); - CaretEnd = map.byteToColumn(SourceEnd) + CaretColumnsOutsideSource; + CaretStart = Map.byteToColumn(SourceStart); + CaretEnd = Map.byteToColumn(SourceEnd) + CaretColumnsOutsideSource; // [CaretStart, CaretEnd) is the slice we want. Update the various // output lines to show only this slice. - assert(CaretStart!=(unsigned)-1 && CaretEnd!=(unsigned)-1 && - SourceStart!=(unsigned)-1 && SourceEnd!=(unsigned)-1); + assert(CaretStart.isValid() && CaretEnd.isValid() && SourceStart.isValid() && + SourceEnd.isValid()); assert(SourceStart <= SourceEnd); assert(CaretStart <= CaretEnd); - unsigned BackColumnsRemoved - = map.byteToColumn(SourceLine.size())-map.byteToColumn(SourceEnd); - unsigned FrontColumnsRemoved = CaretStart; - unsigned ColumnsKept = CaretEnd-CaretStart; + Columns BackColumnsRemoved = + Map.byteToColumn(Bytes{static_cast<int>(SourceLine.size())}) - + Map.byteToColumn(SourceEnd); + Columns FrontColumnsRemoved = CaretStart; + Columns ColumnsKept = CaretEnd - CaretStart; // We checked up front that the line needed truncation - assert(FrontColumnsRemoved+ColumnsKept+BackColumnsRemoved > Columns); + assert(FrontColumnsRemoved + ColumnsKept + BackColumnsRemoved > + NonGutterColumns); // The line needs some truncation, and we'd prefer to keep the front // if possible, so remove the back - if (BackColumnsRemoved > strlen(back_ellipse)) - SourceLine.replace(SourceEnd, std::string::npos, back_ellipse); + if (BackColumnsRemoved > Columns(BackEllipse.size())) + SourceLine.replace(SourceEnd.V, std::string::npos, BackEllipse); // If that's enough then we're done - if (FrontColumnsRemoved+ColumnsKept <= Columns) + if (FrontColumnsRemoved + ColumnsKept <= Columns(NonGutterColumns)) return; // Otherwise remove the front as well - if (FrontColumnsRemoved > strlen(front_ellipse)) { - SourceLine.replace(0, SourceStart, front_ellipse); - CaretLine.replace(0, CaretStart, front_space); + if (FrontColumnsRemoved > Columns(FrontEllipse.size())) { + SourceLine.replace(0, SourceStart.V, FrontEllipse); + CaretLine.replace(0, CaretStart.V, FrontSpace); if (!FixItInsertionLine.empty()) - FixItInsertionLine.replace(0, CaretStart, front_space); + FixItInsertionLine.replace(0, CaretStart.V, FrontSpace); } } @@ -690,11 +724,21 @@ TextDiagnostic::printDiagnosticLevel(raw_ostream &OS, switch (Level) { case DiagnosticsEngine::Ignored: llvm_unreachable("Invalid diagnostic type"); - case DiagnosticsEngine::Note: OS.changeColor(noteColor, true); break; - case DiagnosticsEngine::Remark: OS.changeColor(remarkColor, true); break; - case DiagnosticsEngine::Warning: OS.changeColor(warningColor, true); break; - case DiagnosticsEngine::Error: OS.changeColor(errorColor, true); break; - case DiagnosticsEngine::Fatal: OS.changeColor(fatalColor, true); break; + case DiagnosticsEngine::Note: + OS.changeColor(NoteColor, true); + break; + case DiagnosticsEngine::Remark: + OS.changeColor(RemarkColor, true); + break; + case DiagnosticsEngine::Warning: + OS.changeColor(WarningColor, true); + break; + case DiagnosticsEngine::Error: + OS.changeColor(ErrorColor, true); + break; + case DiagnosticsEngine::Fatal: + OS.changeColor(FatalColor, true); + break; } } @@ -722,7 +766,7 @@ void TextDiagnostic::printDiagnosticMessage(raw_ostream &OS, if (ShowColors && !IsSupplemental) { // Print primary diagnostic messages in bold and without color, to visually // indicate the transition from continuation notes and other output. - OS.changeColor(savedColor, true); + OS.changeColor(SavedColor, true); Bold = true; } @@ -800,7 +844,7 @@ void TextDiagnostic::emitDiagnosticLoc(FullSourceLoc Loc, PresumedLoc PLoc, return; if (DiagOpts.ShowColors) - OS.changeColor(savedColor, true); + OS.changeColor(SavedColor, true); emitFilename(PLoc.getFilename(), Loc.getManager()); switch (DiagOpts.getFormat()) { @@ -961,41 +1005,40 @@ maybeAddRange(std::pair<unsigned, unsigned> A, std::pair<unsigned, unsigned> B, struct LineRange { unsigned LineNo; - unsigned StartCol; - unsigned EndCol; + Bytes StartByte; + Bytes EndByte; }; /// Highlight \p R (with ~'s) on the current source line. static void highlightRange(const LineRange &R, const SourceColumnMap &Map, std::string &CaretLine) { // Pick the first non-whitespace column. - unsigned StartColNo = R.StartCol; - while (StartColNo < Map.getSourceLine().size() && - (Map.getSourceLine()[StartColNo] == ' ' || - Map.getSourceLine()[StartColNo] == '\t')) - StartColNo = Map.startOfNextColumn(StartColNo); + Bytes StartByte = R.StartByte; + while (StartByte < Map.bytes() && (Map.getSourceLine()[StartByte.V] == ' ' || + Map.getSourceLine()[StartByte.V] == '\t')) + StartByte = Map.startOfNextColumn(StartByte); // Pick the last non-whitespace column. - unsigned EndColNo = - std::min(static_cast<size_t>(R.EndCol), Map.getSourceLine().size()); - while (EndColNo && (Map.getSourceLine()[EndColNo - 1] == ' ' || - Map.getSourceLine()[EndColNo - 1] == '\t')) - EndColNo = Map.startOfPreviousColumn(EndColNo); + Bytes EndByte = std::min(R.EndByte.V, Map.bytes().V); + while (EndByte.V != 0 && (Map.getSourceLine()[EndByte.V - 1] == ' ' || + Map.getSourceLine()[EndByte.V - 1] == '\t')) + EndByte = Map.startOfPreviousColumn(EndByte); // If the start/end passed each other, then we are trying to highlight a // range that just exists in whitespace. That most likely means we have // a multi-line highlighting range that covers a blank line. - if (StartColNo > EndColNo) + if (StartByte > EndByte) return; + assert(StartByte <= EndByte && "Invalid range!"); // Fill the range with ~'s. - StartColNo = Map.byteToContainingColumn(StartColNo); - EndColNo = Map.byteToContainingColumn(EndColNo); + Columns StartCol = Map.byteToContainingColumn(StartByte); + Columns EndCol = Map.byteToContainingColumn(EndByte); + + if (CaretLine.size() < static_cast<size_t>(EndCol.V)) + CaretLine.resize(EndCol.V, ' '); - assert(StartColNo <= EndColNo && "Invalid range!"); - if (CaretLine.size() < EndColNo) - CaretLine.resize(EndColNo, ' '); - std::fill(CaretLine.begin() + StartColNo, CaretLine.begin() + EndColNo, '~'); + std::fill(CaretLine.begin() + StartCol.V, CaretLine.begin() + EndCol.V, '~'); } static std::string buildFixItInsertionLine(FileID FID, unsigned LineNo, @@ -1006,7 +1049,7 @@ static std::string buildFixItInsertionLine(FileID FID, unsigned LineNo, std::string FixItInsertionLine; if (Hints.empty() || !DiagOpts.ShowFixits) return FixItInsertionLine; - unsigned PrevHintEndCol = 0; + Columns PrevHintEndCol = 0; for (const auto &H : Hints) { if (H.CodeToInsert.empty()) @@ -1024,12 +1067,13 @@ static std::string buildFixItInsertionLine(FileID FID, unsigned LineNo, // Note: When modifying this function, be very careful about what is a // "column" (printed width, platform-dependent) and what is a // "byte offset" (SourceManager "column"). - unsigned HintByteOffset = - SM.getColumnNumber(HintLocInfo.first, HintLocInfo.second) - 1; + Bytes HintByteOffset = + Bytes(SM.getColumnNumber(HintLocInfo.first, HintLocInfo.second)) + .prev(); // The hint must start inside the source or right at the end - assert(HintByteOffset < static_cast<unsigned>(map.bytes()) + 1); - unsigned HintCol = map.byteToContainingColumn(HintByteOffset); + assert(HintByteOffset < map.bytes().next()); + Columns HintCol = map.byteToContainingColumn(HintByteOffset); // If we inserted a long previous hint, push this one forwards, and add // an extra space to show that this is not part of the previous @@ -1043,11 +1087,11 @@ static std::string buildFixItInsertionLine(FileID FID, unsigned LineNo, // This should NOT use HintByteOffset, because the source might have // Unicode characters in earlier columns. - unsigned NewFixItLineSize = FixItInsertionLine.size() + - (HintCol - PrevHintEndCol) + - H.CodeToInsert.size(); + Columns NewFixItLineSize = Columns(FixItInsertionLine.size()) + + (HintCol - PrevHintEndCol) + + Columns(H.CodeToInsert.size()); if (NewFixItLineSize > FixItInsertionLine.size()) - FixItInsertionLine.resize(NewFixItLineSize, ' '); + FixItInsertionLine.resize(NewFixItLineSize.V, ' '); std::copy(H.CodeToInsert.begin(), H.CodeToInsert.end(), FixItInsertionLine.end() - H.CodeToInsert.size()); @@ -1095,28 +1139,29 @@ prepareAndFilterRanges(const SmallVectorImpl<CharSourceRange> &Ranges, if (EndLineNo < Lines.first || SM.getFileID(End) != FID) continue; - unsigned StartColumn = SM.getExpansionColumnNumber(Begin); - unsigned EndColumn = SM.getExpansionColumnNumber(End); - assert(StartColumn && "StartColumn must be valid, 0 is invalid"); - assert(EndColumn && "EndColumn must be valid, 0 is invalid"); + Bytes StartByte = SM.getExpansionColumnNumber(Begin); + Bytes EndByte = SM.getExpansionColumnNumber(End); + assert(StartByte.V != 0 && "StartByte must be valid, 0 is invalid"); + assert(EndByte.V != 0 && "EndByte must be valid, 0 is invalid"); if (R.isTokenRange()) - EndColumn += Lexer::MeasureTokenLength(End, SM, LangOpts); + EndByte += Bytes(Lexer::MeasureTokenLength(End, SM, LangOpts)); // Only a single line. if (StartLineNo == EndLineNo) { - LineRanges.push_back({StartLineNo, StartColumn - 1, EndColumn - 1}); + LineRanges.push_back({StartLineNo, StartByte.prev(), EndByte.prev()}); continue; } // Start line. - LineRanges.push_back({StartLineNo, StartColumn - 1, ~0u}); + LineRanges.push_back( + {StartLineNo, StartByte.prev(), std::numeric_limits<int>::max()}); // Middle lines. for (unsigned S = StartLineNo + 1; S != EndLineNo; ++S) - LineRanges.push_back({S, 0, ~0u}); + LineRanges.push_back({S, 0, std::numeric_limits<int>::max()}); // End line. - LineRanges.push_back({EndLineNo, 0, EndColumn - 1}); + LineRanges.push_back({EndLineNo, 0, EndByte.prev()}); } return LineRanges; @@ -1226,8 +1271,7 @@ highlightLines(StringRef FileData, unsigned StartLineNumber, if (TokenStartLine > EndLineNumber) break; - unsigned StartCol = - SM.getSpellingColumnNumber(T.getLocation(), &Invalid) - 1; + Bytes StartCol = SM.getSpellingColumnNumber(T.getLocation(), &Invalid) - 1; if (Invalid) continue; @@ -1235,14 +1279,14 @@ highlightLines(StringRef FileData, unsigned StartLineNumber, if (TokenStartLine == TokenEndLine) { SmallVector<TextDiagnostic::StyleRange> &LineRanges = SnippetRanges[TokenStartLine - StartLineNumber]; - appendStyle(LineRanges, T, StartCol, T.getLength()); + appendStyle(LineRanges, T, StartCol.V, T.getLength()); continue; } assert((TokenEndLine - TokenStartLine) >= 1); // For tokens that span multiple lines (think multiline comments), we // divide them into multiple StyleRanges. - unsigned EndCol = SM.getSpellingColumnNumber(T.getEndLoc(), &Invalid) - 1; + Bytes EndCol = SM.getSpellingColumnNumber(T.getEndLoc(), &Invalid) - 1; if (Invalid) continue; @@ -1258,9 +1302,9 @@ highlightLines(StringRef FileData, unsigned StartLineNumber, SnippetRanges[L - StartLineNumber]; if (L == TokenStartLine) // First line - appendStyle(LineRanges, T, StartCol, LineLength); + appendStyle(LineRanges, T, StartCol.V, LineLength); else if (L == TokenEndLine) // Last line - appendStyle(LineRanges, T, 0, EndCol); + appendStyle(LineRanges, T, 0, EndCol.V); else appendStyle(LineRanges, T, 0, LineLength); } @@ -1315,11 +1359,11 @@ void TextDiagnostic::emitSnippetAndCaret( const char *BufEnd = BufStart + BufData.size(); unsigned CaretLineNo = Loc.getLineNumber(); - unsigned CaretColNo = Loc.getColumnNumber(); + Bytes CaretByte = Loc.getColumnNumber(); // Arbitrarily stop showing snippets when the line is too long. static const size_t MaxLineLengthToPrint = 4096; - if (CaretColNo > MaxLineLengthToPrint) + if (CaretByte > MaxLineLengthToPrint) return; // Find the set of lines to include. @@ -1379,35 +1423,37 @@ void TextDiagnostic::emitSnippetAndCaret( std::string SourceLine(LineStart, LineEnd); // Remove trailing null bytes. while (!SourceLine.empty() && SourceLine.back() == '\0' && - (LineNo != CaretLineNo || SourceLine.size() > CaretColNo)) + (LineNo != CaretLineNo || + SourceLine.size() > static_cast<size_t>(CaretByte.V))) SourceLine.pop_back(); // Build the byte to column map. - const SourceColumnMap sourceColMap(SourceLine, DiagOpts.TabStop); + const SourceColumnMap SourceColMap(SourceLine, DiagOpts.TabStop); std::string CaretLine; // Highlight all of the characters covered by Ranges with ~ characters. for (const auto &LR : LineRanges) { if (LR.LineNo == LineNo) - highlightRange(LR, sourceColMap, CaretLine); + highlightRange(LR, SourceColMap, CaretLine); } // Next, insert the caret itself. if (CaretLineNo == LineNo) { - size_t Col = sourceColMap.byteToContainingColumn(CaretColNo - 1); - CaretLine.resize(std::max(Col + 1, CaretLine.size()), ' '); - CaretLine[Col] = '^'; + Columns Col = SourceColMap.byteToContainingColumn(CaretByte.prev()); + CaretLine.resize( + std::max(static_cast<size_t>(Col.V) + 1, CaretLine.size()), ' '); + CaretLine[Col.V] = '^'; } std::string FixItInsertionLine = - buildFixItInsertionLine(FID, LineNo, sourceColMap, Hints, SM, DiagOpts); + buildFixItInsertionLine(FID, LineNo, SourceColMap, Hints, SM, DiagOpts); // If the source line is too long for our terminal, select only the // "interesting" source region within that line. - unsigned Columns = DiagOpts.MessageLength; - if (Columns) + Columns MessageLength = DiagOpts.MessageLength; + if (MessageLength.V != 0) selectInterestingSourceRegion(SourceLine, CaretLine, FixItInsertionLine, - Columns, sourceColMap); + MessageLength, SourceColMap); // If we are in -fdiagnostics-print-source-range-info mode, we are trying // to produce easily machine parsable output. Add a space before the @@ -1425,7 +1471,7 @@ void TextDiagnostic::emitSnippetAndCaret( if (!CaretLine.empty()) { indentForLineNumbers(); if (DiagOpts.ShowColors) - OS.changeColor(caretColor, true); + OS.changeColor(CaretColor, true); OS << CaretLine << '\n'; if (DiagOpts.ShowColors) OS.resetColor(); @@ -1435,7 +1481,7 @@ void TextDiagnostic::emitSnippetAndCaret( indentForLineNumbers(); if (DiagOpts.ShowColors) // Print fixit line in color - OS.changeColor(fixitColor, false); + OS.changeColor(FixitColor, false); if (DiagOpts.ShowSourceRanges) OS << ' '; OS << FixItInsertionLine << '\n'; diff --git a/clang/lib/Lex/HeaderSearch.cpp b/clang/lib/Lex/HeaderSearch.cpp index 65c324c..f05c28fd 100644 --- a/clang/lib/Lex/HeaderSearch.cpp +++ b/clang/lib/Lex/HeaderSearch.cpp @@ -221,7 +221,7 @@ std::string HeaderSearch::getPrebuiltModuleFileName(StringRef ModuleName, // file. for (const std::string &Dir : HSOpts.PrebuiltModulePaths) { SmallString<256> Result(Dir); - llvm::sys::fs::make_absolute(Result); + FileMgr.makeAbsolutePath(Result); if (ModuleName.contains(':')) // The separator of C++20 modules partitions (':') is not good for file // systems, here clang and gcc choose '-' by default since it is not a @@ -246,7 +246,7 @@ std::string HeaderSearch::getPrebuiltImplicitModuleFileName(Module *Module) { StringRef ModuleCacheHash = HSOpts.DisableModuleHash ? "" : getModuleHash(); for (const std::string &Dir : HSOpts.PrebuiltModulePaths) { SmallString<256> CachePath(Dir); - llvm::sys::fs::make_absolute(CachePath); + FileMgr.makeAbsolutePath(CachePath); llvm::sys::path::append(CachePath, ModuleCacheHash); std::string FileName = getCachedModuleFileNameImpl(ModuleName, ModuleMapPath, CachePath); diff --git a/clang/lib/Parse/ParseOpenMP.cpp b/clang/lib/Parse/ParseOpenMP.cpp index 25199c7..31bc941 100644 --- a/clang/lib/Parse/ParseOpenMP.cpp +++ b/clang/lib/Parse/ParseOpenMP.cpp @@ -3221,6 +3221,7 @@ OMPClause *Parser::ParseOpenMPClause(OpenMPDirectiveKind DKind, else Clause = ParseOpenMPSingleExprClause(CKind, WrongDirective); break; + case OMPC_threadset: case OMPC_fail: case OMPC_proc_bind: case OMPC_atomic_default_mem_order: diff --git a/clang/lib/Sema/SemaAMDGPU.cpp b/clang/lib/Sema/SemaAMDGPU.cpp index e32f437..139c4ab 100644 --- a/clang/lib/Sema/SemaAMDGPU.cpp +++ b/clang/lib/Sema/SemaAMDGPU.cpp @@ -153,7 +153,48 @@ bool SemaAMDGPU::CheckAMDGCNBuiltinFunctionCall(unsigned BuiltinID, case AMDGPU::BI__builtin_amdgcn_image_sample_3d_v4f32_f32: case AMDGPU::BI__builtin_amdgcn_image_sample_3d_v4f16_f32: case AMDGPU::BI__builtin_amdgcn_image_sample_cube_v4f32_f32: - case AMDGPU::BI__builtin_amdgcn_image_sample_cube_v4f16_f32: { + case AMDGPU::BI__builtin_amdgcn_image_sample_cube_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_1d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_1d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_1darray_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_1darray_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_2d_f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_2d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_2d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_2darray_f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_2darray_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_2darray_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_3d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_3d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_cube_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_lz_cube_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_1d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_1d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_1darray_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_1darray_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_2d_f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_2d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_2d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_2darray_f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_2darray_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_2darray_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_3d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_3d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_cube_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_l_cube_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_1d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_1d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_1darray_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_1darray_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_2d_f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_2d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_2d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_2darray_f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_2darray_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_2darray_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_3d_v4f32_f32: + case AMDGPU::BI__builtin_amdgcn_image_sample_d_3d_v4f16_f32: + case AMDGPU::BI__builtin_amdgcn_image_gather4_lz_2d_v4f32_f32: { StringRef FeatureList( getASTContext().BuiltinInfo.getRequiredFeatures(BuiltinID)); if (!Builtin::evaluateRequiredTargetFeatures(FeatureList, diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp index 6d5cb0f..256f952 100644 --- a/clang/lib/Sema/SemaOpenMP.cpp +++ b/clang/lib/Sema/SemaOpenMP.cpp @@ -17216,6 +17216,10 @@ OMPClause *SemaOpenMP::ActOnOpenMPSimpleClause( static_cast<OpenMPSeverityClauseKind>(Argument), ArgumentLoc, StartLoc, LParenLoc, EndLoc); break; + case OMPC_threadset: + Res = ActOnOpenMPThreadsetClause(static_cast<OpenMPThreadsetKind>(Argument), + ArgumentLoc, StartLoc, LParenLoc, EndLoc); + break; case OMPC_if: case OMPC_final: case OMPC_num_threads: @@ -17355,6 +17359,23 @@ OMPClause *SemaOpenMP::ActOnOpenMPDefaultClause( OMPDefaultClause(M, MLoc, VCKind, VCKindLoc, StartLoc, LParenLoc, EndLoc); } +OMPClause *SemaOpenMP::ActOnOpenMPThreadsetClause(OpenMPThreadsetKind Kind, + SourceLocation KindLoc, + SourceLocation StartLoc, + SourceLocation LParenLoc, + SourceLocation EndLoc) { + if (Kind == OMPC_THREADSET_unknown) { + Diag(KindLoc, diag::err_omp_unexpected_clause_value) + << getListOfPossibleValues(OMPC_threadset, /*First=*/0, + /*Last=*/unsigned(OMPC_THREADSET_unknown)) + << getOpenMPClauseName(OMPC_threadset); + return nullptr; + } + + return new (getASTContext()) + OMPThreadsetClause(Kind, KindLoc, StartLoc, LParenLoc, EndLoc); +} + OMPClause *SemaOpenMP::ActOnOpenMPProcBindClause(ProcBindKind Kind, SourceLocation KindKwLoc, SourceLocation StartLoc, diff --git a/clang/lib/Sema/TreeTransform.h b/clang/lib/Sema/TreeTransform.h index 0c8c1d1..8c20078 100644 --- a/clang/lib/Sema/TreeTransform.h +++ b/clang/lib/Sema/TreeTransform.h @@ -10624,6 +10624,13 @@ TreeTransform<Derived>::TransformOMPDefaultClause(OMPDefaultClause *C) { template <typename Derived> OMPClause * +TreeTransform<Derived>::TransformOMPThreadsetClause(OMPThreadsetClause *C) { + // No need to rebuild this clause, no template-dependent parameters. + return C; +} + +template <typename Derived> +OMPClause * TreeTransform<Derived>::TransformOMPProcBindClause(OMPProcBindClause *C) { return getDerived().RebuildOMPProcBindClause( C->getProcBindKind(), C->getProcBindKindKwLoc(), C->getBeginLoc(), diff --git a/clang/lib/Serialization/ASTReader.cpp b/clang/lib/Serialization/ASTReader.cpp index c1b5cb7..e3106f8d 100644 --- a/clang/lib/Serialization/ASTReader.cpp +++ b/clang/lib/Serialization/ASTReader.cpp @@ -11255,6 +11255,9 @@ OMPClause *OMPClauseReader::readClause() { case llvm::omp::OMPC_mergeable: C = new (Context) OMPMergeableClause(); break; + case llvm::omp::OMPC_threadset: + C = new (Context) OMPThreadsetClause(); + break; case llvm::omp::OMPC_read: C = new (Context) OMPReadClause(); break; @@ -11658,6 +11661,17 @@ void OMPClauseReader::VisitOMPDefaultClause(OMPDefaultClause *C) { C->setDefaultVariableCategoryLocation(Record.readSourceLocation()); } +// Read the parameter of threadset clause. This will have been saved when +// OMPClauseWriter is called. +void OMPClauseReader::VisitOMPThreadsetClause(OMPThreadsetClause *C) { + C->setLParenLoc(Record.readSourceLocation()); + SourceLocation ThreadsetKindLoc = Record.readSourceLocation(); + C->setThreadsetKindLoc(ThreadsetKindLoc); + OpenMPThreadsetKind TKind = + static_cast<OpenMPThreadsetKind>(Record.readInt()); + C->setThreadsetKind(TKind); +} + void OMPClauseReader::VisitOMPProcBindClause(OMPProcBindClause *C) { C->setProcBindKind(static_cast<llvm::omp::ProcBindKind>(Record.readInt())); C->setLParenLoc(Record.readSourceLocation()); diff --git a/clang/lib/Serialization/ASTWriter.cpp b/clang/lib/Serialization/ASTWriter.cpp index 377e396..3ac338e 100644 --- a/clang/lib/Serialization/ASTWriter.cpp +++ b/clang/lib/Serialization/ASTWriter.cpp @@ -7913,6 +7913,12 @@ void OMPClauseWriter::VisitOMPDefaultClause(OMPDefaultClause *C) { Record.AddSourceLocation(C->getDefaultVCLoc()); } +void OMPClauseWriter::VisitOMPThreadsetClause(OMPThreadsetClause *C) { + Record.AddSourceLocation(C->getLParenLoc()); + Record.AddSourceLocation(C->getThreadsetKindLoc()); + Record.writeEnum(C->getThreadsetKind()); +} + void OMPClauseWriter::VisitOMPProcBindClause(OMPProcBindClause *C) { Record.push_back(unsigned(C->getProcBindKind())); Record.AddSourceLocation(C->getLParenLoc()); diff --git a/clang/test/CIR/CodeGen/builtin_prefetech.c b/clang/test/CIR/CodeGen/builtin_prefetch.c index cfe85b9..cfe85b9 100644 --- a/clang/test/CIR/CodeGen/builtin_prefetech.c +++ b/clang/test/CIR/CodeGen/builtin_prefetch.c diff --git a/clang/test/CXX/drs/cwg0xx.cpp b/clang/test/CXX/drs/cwg0xx.cpp index 805be67..10a4f1d 100644 --- a/clang/test/CXX/drs/cwg0xx.cpp +++ b/clang/test/CXX/drs/cwg0xx.cpp @@ -90,6 +90,8 @@ namespace cwg5 { // cwg5: 3.1 const C c = e; } // namespace cwg5 +// cwg6 is in cwg6.cpp + namespace cwg7 { // cwg7: 3.4 class A { public: ~A(); }; class B : virtual private A {}; // #cwg7-B diff --git a/clang/test/CXX/drs/cwg28xx.cpp b/clang/test/CXX/drs/cwg28xx.cpp index a6b2b99..d0ee191 100644 --- a/clang/test/CXX/drs/cwg28xx.cpp +++ b/clang/test/CXX/drs/cwg28xx.cpp @@ -61,6 +61,24 @@ namespace cwg2819 { // cwg2819: 19 c++26 #endif } // namespace cwg2819 +namespace cwg2823 { // cwg2823: no +#if __cplusplus >= 201103L + constexpr int *p = 0; + constexpr int *q1 = &*p; + // expected-error@-1 {{constexpr variable 'q1' must be initialized by a constant expression}} + // expected-note@-2 {{dereferencing a null pointer is not allowed in a constant expression}} + // FIXME: invalid: dereferencing a null pointer. + constexpr int *q2 = &p[0]; + + int arr[32]; + constexpr int *r = arr; + // FIXME: invalid: dereferencing a past-the-end pointer. + constexpr int *s1 = &*(r + 32); + // FIXME: invalid: dereferencing a past-the-end pointer. + constexpr int *s2 = &r[32]; +#endif +} + namespace cwg2847 { // cwg2847: 19 review 2024-03-01 #if __cplusplus >= 202002L diff --git a/clang/test/CXX/drs/cwg2xx.cpp b/clang/test/CXX/drs/cwg2xx.cpp index 37186e3..a4995dd 100644 --- a/clang/test/CXX/drs/cwg2xx.cpp +++ b/clang/test/CXX/drs/cwg2xx.cpp @@ -230,6 +230,38 @@ namespace cwg211 { // cwg211: 2.7 }; } // namespace cwg211 +namespace cwg212 { // cwg212: 2.7 + template<typename T> struct Base; + template<typename T> struct Derived; + + int *overload(void*); + float *overload(Base<int>*); + double *overload(Base<long>*); + + void f(Derived<int> *p) { + // OK, calls void* overload. + int *a = overload(p); + + Base<int> *q = p; + // expected-error@-1 {{cannot initialize a variable of type 'Base<int> *' with an lvalue of type 'Derived<int> *'}} + } + + template<typename T> struct Base {}; + template<typename T> struct Derived : Base<T> {}; + + void g(Derived<long> *p) { + // OK, instantiates and calls Base<long>* overlod. + double *b = overload(p); + (void)b; + } + + void h(Derived<float> *p) { + // OK, instantiates and converts. + Base<float> *q = p; + (void)q; + } +} + namespace cwg213 { // cwg213: 2.7 template <class T> struct A : T { void h(T t) { @@ -593,6 +625,9 @@ namespace cwg231 { // cwg231: 2.7 } } // namespace cwg231 +// 232 is NAD; the desired behavior is described in 2823. +// cwg232: dup 2823 + // cwg234: na // cwg235: na diff --git a/clang/test/CXX/drs/cwg6.cpp b/clang/test/CXX/drs/cwg6.cpp new file mode 100644 index 0000000..4752e72 --- /dev/null +++ b/clang/test/CXX/drs/cwg6.cpp @@ -0,0 +1,51 @@ +// RUN: %clang_cc1 -std=c++98 %s -triple x86_64-linux-gnu -emit-llvm -o - -fexceptions -fcxx-exceptions -pedantic-errors | FileCheck %s --check-prefixes CHECK +// RUN: %clang_cc1 -std=c++11 %s -triple x86_64-linux-gnu -emit-llvm -o - -fexceptions -fcxx-exceptions -pedantic-errors | FileCheck %s --check-prefixes CHECK +// RUN: %clang_cc1 -std=c++14 %s -triple x86_64-linux-gnu -emit-llvm -o - -fexceptions -fcxx-exceptions -pedantic-errors | FileCheck %s --check-prefixes CHECK +// RUN: %clang_cc1 -std=c++17 %s -triple x86_64-linux-gnu -emit-llvm -o - -fexceptions -fcxx-exceptions -pedantic-errors | FileCheck %s --check-prefixes CHECK +// RUN: %clang_cc1 -std=c++20 %s -triple x86_64-linux-gnu -emit-llvm -o - -fexceptions -fcxx-exceptions -pedantic-errors | FileCheck %s --check-prefixes CHECK +// RUN: %clang_cc1 -std=c++23 %s -triple x86_64-linux-gnu -emit-llvm -o - -fexceptions -fcxx-exceptions -pedantic-errors | FileCheck %s --check-prefixes CHECK +// RUN: %clang_cc1 -std=c++2c %s -triple x86_64-linux-gnu -emit-llvm -o - -fexceptions -fcxx-exceptions -pedantic-errors | FileCheck %s --check-prefixes CHECK + +#if __cplusplus == 199711L +#define static_assert(expr) __extension__ _Static_assert(expr) +#define noexcept throw() +#endif + +namespace cwg6 { // cwg6: 2.7 +#if __cplusplus >= 201103L +struct Counter { + int copies; + constexpr Counter(int copies) : copies(copies) {} + constexpr Counter(const Counter& other) : copies(other.copies + 1) {} +}; + +// Passing an lvalue by value makes a non-elidable copy. +constexpr int PassByValue(Counter c) { return c.copies; } +constexpr int PassByValue2(Counter c) { return PassByValue(c); } +constexpr int PassByValue3(Counter c) { return PassByValue2(c); } +static_assert(PassByValue(Counter(0)) == 0, "expect no copies"); +static_assert(PassByValue2(Counter(0)) == 1, "expect 1 copy"); +static_assert(PassByValue3(Counter(0)) == 2, "expect 2 copies"); +#endif + +struct A { + A() noexcept; + A(const A&) noexcept; + ~A() noexcept; +}; + +inline void f(A a) noexcept {} + +// CHECK-LABEL: define {{.*}} @_ZN4cwg64callEv +void call() { + A a; + // We copy the parameter here, even though object is not mutated by f and + // otherwise satisfies the criteria for the proposed CWG6 optimization. + // CHECK: call {{.*}} @_ZN4cwg61AC1ERKS0_( + // CHECK: call {{.*}} @_ZN4cwg61fENS_1AE( + f(a); + // CHECK: call {{.*}} @_ZN4cwg61AD1Ev( + // CHECK: call {{.*}} @_ZN4cwg61AD1Ev( +} + +} // namespace cwg6 diff --git a/clang/test/CodeGen/AArch64/neon-across.c b/clang/test/CodeGen/AArch64/neon-across.c index aa0387d..aae5097 100644 --- a/clang/test/CodeGen/AArch64/neon-across.c +++ b/clang/test/CodeGen/AArch64/neon-across.c @@ -113,9 +113,8 @@ uint64_t test_vaddlvq_u32(uint32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxv_s8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMAXV_S8_I:%.*]] = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMAXV_S8_I]] // int8_t test_vmaxv_s8(int8x8_t a) { return vmaxv_s8(a); @@ -124,9 +123,8 @@ int8_t test_vmaxv_s8(int8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxv_s16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMAXV_S16_I:%.*]] = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMAXV_S16_I]] // int16_t test_vmaxv_s16(int16x4_t a) { return vmaxv_s16(a); @@ -135,9 +133,8 @@ int16_t test_vmaxv_s16(int16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxv_u8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMAXV_U8_I:%.*]] = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMAXV_U8_I]] // uint8_t test_vmaxv_u8(uint8x8_t a) { return vmaxv_u8(a); @@ -146,9 +143,8 @@ uint8_t test_vmaxv_u8(uint8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxv_u16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMAXV_U16_I:%.*]] = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMAXV_U16_I]] // uint16_t test_vmaxv_u16(uint16x4_t a) { return vmaxv_u16(a); @@ -157,9 +153,8 @@ uint16_t test_vmaxv_u16(uint16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_s8 // CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMAXVQ_S8_I:%.*]] = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMAXVQ_S8_I]] // int8_t test_vmaxvq_s8(int8x16_t a) { return vmaxvq_s8(a); @@ -168,9 +163,8 @@ int8_t test_vmaxvq_s8(int8x16_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_s16 // CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMAXVQ_S16_I:%.*]] = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMAXVQ_S16_I]] // int16_t test_vmaxvq_s16(int16x8_t a) { return vmaxvq_s16(a); @@ -179,7 +173,7 @@ int16_t test_vmaxvq_s16(int16x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_s32 // CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VMAXVQ_S32_I:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMAXVQ_S32_I]] // int32_t test_vmaxvq_s32(int32x4_t a) { @@ -189,9 +183,8 @@ int32_t test_vmaxvq_s32(int32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_u8 // CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMAXVQ_U8_I:%.*]] = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMAXVQ_U8_I]] // uint8_t test_vmaxvq_u8(uint8x16_t a) { return vmaxvq_u8(a); @@ -200,9 +193,8 @@ uint8_t test_vmaxvq_u8(uint8x16_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_u16 // CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMAXVQ_U16_I:%.*]] = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMAXVQ_U16_I]] // uint16_t test_vmaxvq_u16(uint16x8_t a) { return vmaxvq_u16(a); @@ -211,7 +203,7 @@ uint16_t test_vmaxvq_u16(uint16x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_u32 // CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VMAXVQ_U32_I:%.*]] = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMAXVQ_U32_I]] // uint32_t test_vmaxvq_u32(uint32x4_t a) { @@ -221,9 +213,8 @@ uint32_t test_vmaxvq_u32(uint32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminv_s8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMINV_S8_I:%.*]] = call i8 @llvm.vector.reduce.smin.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMINV_S8_I]] // int8_t test_vminv_s8(int8x8_t a) { return vminv_s8(a); @@ -232,9 +223,8 @@ int8_t test_vminv_s8(int8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminv_s16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMINV_S16_I:%.*]] = call i16 @llvm.vector.reduce.smin.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMINV_S16_I]] // int16_t test_vminv_s16(int16x4_t a) { return vminv_s16(a); @@ -243,9 +233,8 @@ int16_t test_vminv_s16(int16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminv_u8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMINV_U8_I:%.*]] = call i8 @llvm.vector.reduce.umin.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMINV_U8_I]] // uint8_t test_vminv_u8(uint8x8_t a) { return vminv_u8(a); @@ -254,9 +243,8 @@ uint8_t test_vminv_u8(uint8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminv_u16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMINV_U16_I:%.*]] = call i16 @llvm.vector.reduce.umin.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMINV_U16_I]] // uint16_t test_vminv_u16(uint16x4_t a) { return vminv_u16(a); @@ -265,9 +253,8 @@ uint16_t test_vminv_u16(uint16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminvq_s8 // CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMINVQ_S8_I:%.*]] = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMINVQ_S8_I]] // int8_t test_vminvq_s8(int8x16_t a) { return vminvq_s8(a); @@ -276,9 +263,8 @@ int8_t test_vminvq_s8(int8x16_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminvq_s16 // CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMINVQ_S16_I:%.*]] = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMINVQ_S16_I]] // int16_t test_vminvq_s16(int16x8_t a) { return vminvq_s16(a); @@ -287,7 +273,7 @@ int16_t test_vminvq_s16(int16x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminvq_s32 // CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VMINVQ_S32_I:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMINVQ_S32_I]] // int32_t test_vminvq_s32(int32x4_t a) { @@ -297,9 +283,8 @@ int32_t test_vminvq_s32(int32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminvq_u8 // CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMINVQ_U8_I:%.*]] = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMINVQ_U8_I]] // uint8_t test_vminvq_u8(uint8x16_t a) { return vminvq_u8(a); @@ -308,9 +293,8 @@ uint8_t test_vminvq_u8(uint8x16_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminvq_u16 // CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMINVQ_U16_I:%.*]] = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMINVQ_U16_I]] // uint16_t test_vminvq_u16(uint16x8_t a) { return vminvq_u16(a); @@ -319,7 +303,7 @@ uint16_t test_vminvq_u16(uint16x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminvq_u32 // CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VMINVQ_U32_I:%.*]] = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMINVQ_U32_I]] // uint32_t test_vminvq_u32(uint32x4_t a) { @@ -329,9 +313,8 @@ uint32_t test_vminvq_u32(uint32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddv_s8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VADDV_S8_I:%.*]] = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VADDV_S8_I]] // int8_t test_vaddv_s8(int8x8_t a) { return vaddv_s8(a); @@ -340,9 +323,8 @@ int8_t test_vaddv_s8(int8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddv_s16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VADDV_S16_I:%.*]] = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VADDV_S16_I]] // int16_t test_vaddv_s16(int16x4_t a) { return vaddv_s16(a); @@ -351,9 +333,8 @@ int16_t test_vaddv_s16(int16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddv_u8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VADDV_U8_I:%.*]] = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VADDV_U8_I]] // uint8_t test_vaddv_u8(uint8x8_t a) { return vaddv_u8(a); @@ -362,9 +343,8 @@ uint8_t test_vaddv_u8(uint8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddv_u16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VADDV_U16_I:%.*]] = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VADDV_U16_I]] // uint16_t test_vaddv_u16(uint16x4_t a) { return vaddv_u16(a); @@ -373,9 +353,8 @@ uint16_t test_vaddv_u16(uint16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_s8 // CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VADDVQ_S8_I:%.*]] = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VADDVQ_S8_I]] // int8_t test_vaddvq_s8(int8x16_t a) { return vaddvq_s8(a); @@ -384,9 +363,8 @@ int8_t test_vaddvq_s8(int8x16_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_s16 // CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VADDVQ_S16_I:%.*]] = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VADDVQ_S16_I]] // int16_t test_vaddvq_s16(int16x8_t a) { return vaddvq_s16(a); @@ -395,7 +373,7 @@ int16_t test_vaddvq_s16(int16x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_s32 // CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VADDVQ_S32_I:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VADDVQ_S32_I]] // int32_t test_vaddvq_s32(int32x4_t a) { @@ -405,9 +383,8 @@ int32_t test_vaddvq_s32(int32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_u8 // CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VADDVQ_U8_I:%.*]] = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VADDVQ_U8_I]] // uint8_t test_vaddvq_u8(uint8x16_t a) { return vaddvq_u8(a); @@ -416,9 +393,8 @@ uint8_t test_vaddvq_u8(uint8x16_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_u16 // CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VADDVQ_U16_I:%.*]] = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VADDVQ_U16_I]] // uint16_t test_vaddvq_u16(uint16x8_t a) { return vaddvq_u16(a); @@ -427,7 +403,7 @@ uint16_t test_vaddvq_u16(uint16x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_u32 // CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VADDVQ_U32_I:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VADDVQ_U32_I]] // uint32_t test_vaddvq_u32(uint32x4_t a) { diff --git a/clang/test/CodeGen/AArch64/neon-intrinsics.c b/clang/test/CodeGen/AArch64/neon-intrinsics.c index 035e1ca..1c628bb 100644 --- a/clang/test/CodeGen/AArch64/neon-intrinsics.c +++ b/clang/test/CodeGen/AArch64/neon-intrinsics.c @@ -12643,7 +12643,7 @@ uint64_t test_vqrshld_u64(uint64_t a, int64_t b) { // CHECK-LABEL: define dso_local i64 @test_vpaddd_s64( // CHECK-SAME: <2 x i64> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VPADDD_S64_I:%.*]] = call i64 @llvm.aarch64.neon.uaddv.i64.v2i64(<2 x i64> [[A]]) +// CHECK-NEXT: [[VPADDD_S64_I:%.*]] = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[A]]) // CHECK-NEXT: ret i64 [[VPADDD_S64_I]] // int64_t test_vpaddd_s64(int64x2_t a) { @@ -23227,7 +23227,7 @@ uint64x2_t test_vpaddq_u64(uint64x2_t a, uint64x2_t b) { // CHECK-LABEL: define dso_local i64 @test_vpaddd_u64( // CHECK-SAME: <2 x i64> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VPADDD_U64_I:%.*]] = call i64 @llvm.aarch64.neon.uaddv.i64.v2i64(<2 x i64> [[A]]) +// CHECK-NEXT: [[VPADDD_U64_I:%.*]] = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[A]]) // CHECK-NEXT: ret i64 [[VPADDD_U64_I]] // uint64_t test_vpaddd_u64(uint64x2_t a) { @@ -23237,7 +23237,7 @@ uint64_t test_vpaddd_u64(uint64x2_t a) { // CHECK-LABEL: define dso_local i64 @test_vaddvq_s64( // CHECK-SAME: <2 x i64> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VADDVQ_S64_I:%.*]] = call i64 @llvm.aarch64.neon.saddv.i64.v2i64(<2 x i64> [[A]]) +// CHECK-NEXT: [[VADDVQ_S64_I:%.*]] = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[A]]) // CHECK-NEXT: ret i64 [[VADDVQ_S64_I]] // int64_t test_vaddvq_s64(int64x2_t a) { @@ -23247,7 +23247,7 @@ int64_t test_vaddvq_s64(int64x2_t a) { // CHECK-LABEL: define dso_local i64 @test_vaddvq_u64( // CHECK-SAME: <2 x i64> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VADDVQ_U64_I:%.*]] = call i64 @llvm.aarch64.neon.uaddv.i64.v2i64(<2 x i64> [[A]]) +// CHECK-NEXT: [[VADDVQ_U64_I:%.*]] = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[A]]) // CHECK-NEXT: ret i64 [[VADDVQ_U64_I]] // uint64_t test_vaddvq_u64(uint64x2_t a) { @@ -23878,7 +23878,7 @@ float64x1_t test_vrsqrts_f64(float64x1_t a, float64x1_t b) { // CHECK-LABEL: define dso_local i32 @test_vminv_s32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VMINV_S32_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VMINV_S32_I:%.*]] = call i32 @llvm.vector.reduce.smin.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMINV_S32_I]] // int32_t test_vminv_s32(int32x2_t a) { @@ -23888,7 +23888,7 @@ int32_t test_vminv_s32(int32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vminv_u32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VMINV_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VMINV_U32_I:%.*]] = call i32 @llvm.vector.reduce.umin.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMINV_U32_I]] // uint32_t test_vminv_u32(uint32x2_t a) { @@ -23898,7 +23898,7 @@ uint32_t test_vminv_u32(uint32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vmaxv_s32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VMAXV_S32_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VMAXV_S32_I:%.*]] = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMAXV_S32_I]] // int32_t test_vmaxv_s32(int32x2_t a) { @@ -23908,7 +23908,7 @@ int32_t test_vmaxv_s32(int32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vmaxv_u32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VMAXV_U32_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VMAXV_U32_I:%.*]] = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMAXV_U32_I]] // uint32_t test_vmaxv_u32(uint32x2_t a) { @@ -23918,7 +23918,7 @@ uint32_t test_vmaxv_u32(uint32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vaddv_s32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VADDV_S32_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VADDV_S32_I:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VADDV_S32_I]] // int32_t test_vaddv_s32(int32x2_t a) { @@ -23928,7 +23928,7 @@ int32_t test_vaddv_s32(int32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vaddv_u32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VADDV_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VADDV_U32_I:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VADDV_U32_I]] // uint32_t test_vaddv_u32(uint32x2_t a) { diff --git a/clang/test/CodeGen/X86/sse41-builtins.c b/clang/test/CodeGen/X86/sse41-builtins.c index 62cd392..35fa65a 100644 --- a/clang/test/CodeGen/X86/sse41-builtins.c +++ b/clang/test/CodeGen/X86/sse41-builtins.c @@ -307,6 +307,16 @@ __m128 test_mm_insert_ps(__m128 x, __m128 y) { return _mm_insert_ps(x, y, 4); } +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0x10), 1.0f, 10.0f, 3.0f, 4.0f))); // Insert Y[0] into X[1] +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0x00), 10.0f, 2.0f, 3.0f, 4.0f))); // Insert Y[0] into X[0] +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0x20), 1.0f, 2.0f, 10.0f, 4.0f))); // Insert Y[0] into X[2] +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0x30), 1.0f, 2.0f, 3.0f, 10.0f))); // Insert Y[0] into X[3] +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0x80), 30.0f, 2.0f, 3.0f, 4.0f))); // Insert Y[2] into X[0] +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0x01), 0.0f, 2.0f, 3.0f, 4.0f))); // Insert Y[0] into X[0], zero X[0] +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0x0A), 10.0f, 0.0f, 3.0f, 0.0f))); // Insert Y[0] into X[0], zero X[1] and X[3] +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0x0F), 0.0f, 0.0f, 0.0f, 0.0f))); // Insert Y[0] into X[0], zero all +TEST_CONSTEXPR((match_m128(_mm_insert_ps(((__m128)(__v4sf){1.0f, 2.0f, 3.0f, 4.0f}), ((__m128)(__v4sf){10.0f, 20.0f, 30.0f, 40.0f}), 0xCF), 0.0f, 0.0f, 0.0f, 0.0f))); // Insert Y[3] into X[0], zero all + __m128i test_mm_max_epi8(__m128i x, __m128i y) { // CHECK-LABEL: test_mm_max_epi8 // CHECK: call <16 x i8> @llvm.smax.v16i8(<16 x i8> %{{.*}}, <16 x i8> %{{.*}}) diff --git a/clang/test/CodeGen/builtins-extended-image.c b/clang/test/CodeGen/builtins-extended-image.c new file mode 100644 index 0000000..0dbf81d --- /dev/null +++ b/clang/test/CodeGen/builtins-extended-image.c @@ -0,0 +1,1528 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5 +// RUN: %clang_cc1 -triple amdgcn-- -target-cpu gfx1100 -target-feature +extended-image-insts %s -emit-llvm -o - | FileCheck %s + +typedef int int4 __attribute__((ext_vector_type(4))); +typedef float float4 __attribute__((ext_vector_type(4))); +typedef _Float16 half4 __attribute__((ext_vector_type(4))); + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_gather4_lz_2d_v4f32_f32_r( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0:[0-9]+]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x float> @llvm.amdgcn.image.gather4.lz.2d.v4f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP4]] +// +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_r(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(1, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_gather4_lz_2d_v4f32_f32_g( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x float> @llvm.amdgcn.image.gather4.lz.2d.v4f32.f32.v8i32.v4i32(i32 2, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP4]] +// +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_g(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(2, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_gather4_lz_2d_v4f32_f32_b( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x float> @llvm.amdgcn.image.gather4.lz.2d.v4f32.f32.v8i32.v4i32(i32 4, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP4]] +// +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_b(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(4, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_gather4_lz_2d_v4f32_f32_a( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x float> @llvm.amdgcn.image.gather4.lz.2d.v4f32.f32.v8i32.v4i32(i32 8, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP4]] +// +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_a(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(8, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_lz_1d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP1]], align 32 +// CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP3:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.lz.1d.v4f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP2]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP3]] +// +float4 test_amdgcn_image_sample_lz_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1d_v4f32_f32(100, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_l_1d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.l.1d.v4f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP4]] +// +float4 test_amdgcn_image_sample_l_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1d_v4f32_f32(100, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_d_1d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.d.1d.v4f32.f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP5]] +// +float4 test_amdgcn_image_sample_d_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1d_v4f32_f32(100, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_lz_2d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.lz.2d.v4f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP4]] +// +float4 test_amdgcn_image_sample_lz_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_v4f32_f32(100, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_l_2d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.l.2d.v4f32.f32.v8i32.v4i32(i32 10, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP5]] +// +float4 test_amdgcn_image_sample_l_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_v4f32_f32(10, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_d_2d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP6:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP6]], align 32 +// CHECK-NEXT: [[TMP7:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP8:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], float [[TMP4]], float [[TMP5]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP7]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP8]] +// +float4 test_amdgcn_image_sample_d_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_v4f32_f32(100, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_lz_3d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.lz.3d.v4f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP5]] +// +float4 test_amdgcn_image_sample_lz_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_3d_v4f32_f32(100, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_l_3d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.l.3d.v4f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP6]] +// +float4 test_amdgcn_image_sample_l_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_3d_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_d_3d_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP6:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP7:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP8:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP9:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP9]], align 32 +// CHECK-NEXT: [[TMP10:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP11:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.d.3d.v4f32.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], float [[TMP4]], float [[TMP5]], float [[TMP6]], float [[TMP7]], float [[TMP8]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP10]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP11]] +// +float4 test_amdgcn_image_sample_d_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_3d_v4f32_f32(1, f32, f32, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_lz_cube_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.lz.cube.v4f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP5]] +// +float4 test_amdgcn_image_sample_lz_cube_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_cube_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_l_cube_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.l.cube.v4f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP6]] +// +float4 test_amdgcn_image_sample_l_cube_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_cube_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_lz_1darray_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.lz.1darray.v4f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP4]] +// +float4 test_amdgcn_image_sample_lz_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1darray_v4f32_f32(1, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_l_1darray_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.l.1darray.v4f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP5]] +// +float4 test_amdgcn_image_sample_l_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1darray_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_d_1darray_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.d.1darray.v4f32.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP6]] +// +float4 test_amdgcn_image_sample_d_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1darray_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_lz_2darray_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.lz.2darray.v4f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP5]] +// +float4 test_amdgcn_image_sample_lz_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_l_2darray_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.l.2darray.v4f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP6]] +// +float4 test_amdgcn_image_sample_l_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x float> @test_amdgcn_image_sample_d_2darray_v4f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP6:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP7:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP7]], align 32 +// CHECK-NEXT: [[TMP8:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP9:%.*]] = call <4 x float> @llvm.amdgcn.image.sample.d.2darray.v4f32.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], float [[TMP4]], float [[TMP5]], float [[TMP6]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP8]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x float> [[TMP9]] +// +float4 test_amdgcn_image_sample_d_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_v4f32_f32(1, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_lz_1d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP1]], align 32 +// CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP3:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.lz.1d.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP2]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP3]] +// +half4 test_amdgcn_image_sample_lz_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1d_v4f16_f32(100, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_l_1d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.l.1d.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP4]] +// +half4 test_amdgcn_image_sample_l_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1d_v4f16_f32(100, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_d_1d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.d.1d.v4f16.f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP5]] +// +half4 test_amdgcn_image_sample_d_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1d_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_lz_2d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.lz.2d.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP4]] +// +half4 test_amdgcn_image_sample_lz_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_v4f16_f32(100, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_l_2d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.l.2d.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP5]] +// +half4 test_amdgcn_image_sample_l_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_d_2d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP6:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP6]], align 32 +// CHECK-NEXT: [[TMP7:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP8:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.d.2d.v4f16.f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], float [[TMP4]], float [[TMP5]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP7]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP8]] +// +half4 test_amdgcn_image_sample_d_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_v4f16_f32(100, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_lz_3d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.lz.3d.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP5]] +// +half4 test_amdgcn_image_sample_lz_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_3d_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_l_3d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.l.3d.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP6]] +// +half4 test_amdgcn_image_sample_l_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_3d_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_d_3d_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP6:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP7:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP8:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP9:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP9]], align 32 +// CHECK-NEXT: [[TMP10:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP11:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.d.3d.v4f16.f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], float [[TMP4]], float [[TMP5]], float [[TMP6]], float [[TMP7]], float [[TMP8]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP10]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP11]] +// +half4 test_amdgcn_image_sample_d_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_3d_v4f16_f32(100, f32, f32, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_lz_cube_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.lz.cube.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP5]] +// +half4 test_amdgcn_image_sample_lz_cube_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_cube_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_l_cube_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.l.cube.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP6]] +// +half4 test_amdgcn_image_sample_l_cube_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_cube_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_lz_1darray_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.lz.1darray.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP4]] +// +half4 test_amdgcn_image_sample_lz_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1darray_v4f16_f32(100, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_l_1darray_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.l.1darray.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP5]] +// +half4 test_amdgcn_image_sample_l_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1darray_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_d_1darray_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.d.1darray.v4f16.f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP6]] +// +half4 test_amdgcn_image_sample_d_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1darray_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_lz_2darray_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.lz.2darray.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP5]] +// +half4 test_amdgcn_image_sample_lz_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_l_2darray_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.l.2darray.v4f16.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP6]] +// +half4 test_amdgcn_image_sample_l_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local <4 x half> @test_amdgcn_image_sample_d_2darray_v4f16_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca <4 x half>, align 8, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP6:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP7:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP7]], align 32 +// CHECK-NEXT: [[TMP8:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP9:%.*]] = call <4 x half> @llvm.amdgcn.image.sample.d.2darray.v4f16.f32.f32.v8i32.v4i32(i32 100, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], float [[TMP4]], float [[TMP5]], float [[TMP6]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP8]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret <4 x half> [[TMP9]] +// +half4 test_amdgcn_image_sample_d_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_v4f16_f32(100, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local float @test_amdgcn_image_sample_lz_2d_f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP2]], align 32 +// CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP4:%.*]] = call float @llvm.amdgcn.image.sample.lz.2d.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP3]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret float [[TMP4]] +// +float test_amdgcn_image_sample_lz_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_f32_f32(1, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local float @test_amdgcn_image_sample_l_2d_f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call float @llvm.amdgcn.image.sample.l.2d.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret float [[TMP5]] +// +float test_amdgcn_image_sample_l_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local float @test_amdgcn_image_sample_d_2d_f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP6:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP6]], align 32 +// CHECK-NEXT: [[TMP7:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP8:%.*]] = call float @llvm.amdgcn.image.sample.d.2d.f32.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], float [[TMP4]], float [[TMP5]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP7]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret float [[TMP8]] +// +float test_amdgcn_image_sample_d_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_f32_f32(1, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local float @test_amdgcn_image_sample_lz_2darray_f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP3]], align 32 +// CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP5:%.*]] = call float @llvm.amdgcn.image.sample.lz.2darray.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP4]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret float [[TMP5]] +// +float test_amdgcn_image_sample_lz_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local float @test_amdgcn_image_sample_l_2darray_f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP4]], align 32 +// CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP6:%.*]] = call float @llvm.amdgcn.image.sample.l.2darray.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP5]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret float [[TMP6]] +// +float test_amdgcn_image_sample_l_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} + +// CHECK-LABEL: define dso_local float @test_amdgcn_image_sample_d_2darray_f32_f32( +// CHECK-SAME: <4 x float> noundef [[V4F32:%.*]], float noundef [[F32:%.*]], i32 noundef [[I32:%.*]], ptr [[TEX:%.*]], <4 x i32> noundef [[VEC4I32:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[V4F32_ADDR:%.*]] = alloca <4 x float>, align 16, addrspace(5) +// CHECK-NEXT: [[F32_ADDR:%.*]] = alloca float, align 4, addrspace(5) +// CHECK-NEXT: [[I32_ADDR:%.*]] = alloca i32, align 4, addrspace(5) +// CHECK-NEXT: [[TEX_ADDR:%.*]] = alloca ptr, align 32, addrspace(5) +// CHECK-NEXT: [[VEC4I32_ADDR:%.*]] = alloca <4 x i32>, align 16, addrspace(5) +// CHECK-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr +// CHECK-NEXT: [[V4F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[V4F32_ADDR]] to ptr +// CHECK-NEXT: [[F32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[F32_ADDR]] to ptr +// CHECK-NEXT: [[I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I32_ADDR]] to ptr +// CHECK-NEXT: [[TEX_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TEX_ADDR]] to ptr +// CHECK-NEXT: [[VEC4I32_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VEC4I32_ADDR]] to ptr +// CHECK-NEXT: store <4 x float> [[V4F32]], ptr [[V4F32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: store float [[F32]], ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store i32 [[I32]], ptr [[I32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: store ptr [[TEX]], ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: store <4 x i32> [[VEC4I32]], ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP6:%.*]] = load float, ptr [[F32_ADDR_ASCAST]], align 4 +// CHECK-NEXT: [[TMP7:%.*]] = load ptr, ptr [[TEX_ADDR_ASCAST]], align 32 +// CHECK-NEXT: [[TEX_RSRC_VAL:%.*]] = load <8 x i32>, ptr [[TMP7]], align 32 +// CHECK-NEXT: [[TMP8:%.*]] = load <4 x i32>, ptr [[VEC4I32_ADDR_ASCAST]], align 16 +// CHECK-NEXT: [[TMP9:%.*]] = call float @llvm.amdgcn.image.sample.d.2darray.f32.f32.f32.v8i32.v4i32(i32 1, float [[TMP0]], float [[TMP1]], float [[TMP2]], float [[TMP3]], float [[TMP4]], float [[TMP5]], float [[TMP6]], <8 x i32> [[TEX_RSRC_VAL]], <4 x i32> [[TMP8]], i1 false, i32 120, i32 110) +// CHECK-NEXT: ret float [[TMP9]] +// +float test_amdgcn_image_sample_d_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_f32_f32(1, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 120, 110); +} diff --git a/clang/test/CodeGenCXX/ubsan-coroutines.cpp b/clang/test/CodeGenCXX/ubsan-coroutines.cpp index 04ab050..60c89a4 100644 --- a/clang/test/CodeGenCXX/ubsan-coroutines.cpp +++ b/clang/test/CodeGenCXX/ubsan-coroutines.cpp @@ -1,6 +1,7 @@ // This test merely verifies that emitting the object file does not cause a // crash when the LLVM coroutines passes are run. // RUN: %clang_cc1 -emit-obj -std=c++2a -fsanitize=null %s -o %t.o +// UNSUPPORTED: target={{.*}}-zos{{.*}} namespace std { template <typename R, typename... T> struct coroutine_traits { diff --git a/clang/test/CodeGenHIP/maybe_undef-attr-verify.hip b/clang/test/CodeGenHIP/maybe_undef-attr-verify.hip index 571fba1..6dc57c4 100644 --- a/clang/test/CodeGenHIP/maybe_undef-attr-verify.hip +++ b/clang/test/CodeGenHIP/maybe_undef-attr-verify.hip @@ -20,7 +20,7 @@ #define __maybe_undef __attribute__((maybe_undef)) #define WARP_SIZE 64 -static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE__; +static constexpr int warpSize = WARP_SIZE; __device__ static inline unsigned int __lane_id() { return __builtin_amdgcn_mbcnt_hi( diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-wave32.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn-wave32.cl index d390418..31fd0e7 100644 --- a/clang/test/CodeGenOpenCL/builtins-amdgcn-wave32.cl +++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-wave32.cl @@ -1,5 +1,5 @@ // REQUIRES: amdgpu-registered-target -// RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -D__AMDGCN_WAVEFRONT_SIZE=32 -target-feature +wavefrontsize32 -emit-llvm -o - %s | FileCheck -enable-var-scope %s +// RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-feature +wavefrontsize32 -emit-llvm -o - %s | FileCheck -enable-var-scope %s // RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -emit-llvm -o - %s | FileCheck -enable-var-scope %s // RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -target-feature +wavefrontsize32 -emit-llvm -o - %s | FileCheck -enable-var-scope %s // RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1100 -target-feature +wavefrontsize32 -emit-llvm -o - %s | FileCheck -enable-var-scope %s @@ -48,7 +48,3 @@ void test_read_exec_lo(global uint* out) { void test_read_exec_hi(global uint* out) { *out = __builtin_amdgcn_read_exec_hi(); } - -#if __AMDGCN_WAVEFRONT_SIZE != 32 -#error Wrong wavesize detected -#endif diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-wave64.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn-wave64.cl index d851ec7..758b5aa 100644 --- a/clang/test/CodeGenOpenCL/builtins-amdgcn-wave64.cl +++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-wave64.cl @@ -50,7 +50,3 @@ void test_read_exec_lo(global ulong* out) { void test_read_exec_hi(global ulong* out) { *out = __builtin_amdgcn_read_exec_hi(); } - -#if defined(__AMDGCN_WAVEFRONT_SIZE__) && __AMDGCN_WAVEFRONT_SIZE__ != 64 -#error Wrong wavesize detected -#endif diff --git a/clang/test/DebugInfo/Generic/bit-int.c b/clang/test/DebugInfo/Generic/bit-int.c index 94b9301..88ecc13 100644 --- a/clang/test/DebugInfo/Generic/bit-int.c +++ b/clang/test/DebugInfo/Generic/bit-int.c @@ -4,5 +4,5 @@ unsigned _BitInt(17) a; _BitInt(2) b; -// CHECK: !DIBasicType(name: "_BitInt", size: 8, dataSize: 2, encoding: DW_ATE_signed) -// CHECK: !DIBasicType(name: "unsigned _BitInt", size: 32, dataSize: 17, encoding: DW_ATE_unsigned) +// CHECK: !DIBasicType(name: "_BitInt(2)", size: 8, dataSize: 2, encoding: DW_ATE_signed) +// CHECK: !DIBasicType(name: "unsigned _BitInt(17)", size: 32, dataSize: 17, encoding: DW_ATE_unsigned) diff --git a/clang/test/DebugInfo/Generic/macro-info.c b/clang/test/DebugInfo/Generic/macro-info.c new file mode 100644 index 0000000..ec49eb5 --- /dev/null +++ b/clang/test/DebugInfo/Generic/macro-info.c @@ -0,0 +1,35 @@ +// RUN: %clang_cc1 %s -debug-info-kind=standalone -emit-llvm -o - | FileCheck %s + +#define GLOBAL(num) global## num +#define DECL_GLOBAL(x) int x +#define SAME_ORDER(x, y) x; y +#define SWAP_ORDER(x,y) y; x + + + +SAME_ORDER( + int +// CHECK: DIGlobalVariable(name: "global",{{.*}} line: [[@LINE+1]] + GLOBAL // <- global + () = 42, + const char* s() { +// CHECK: DIGlobalVariable({{.*}}line: [[@LINE+1]],{{.*}} type: [[TYPEID:![0-9]+]] + return "1234567890"; + } +) + +SWAP_ORDER( + int GLOBAL( // <- global2 + 2) = 43, +// CHECK: DIGlobalVariable(name: "global3",{{.*}} line: [[@LINE+3]] +// CHECK: DIGlobalVariable(name: "global2",{{.*}} line: [[@LINE-3]] + DECL_GLOBAL( + GLOBAL( // <- global3 + 3)) = 44 +); + + +DECL_GLOBAL( +// CHECK: DIGlobalVariable(name: "global4",{{.*}} line: [[@LINE+1]] + GLOBAL( // <- global4 + 4)); diff --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl index 9fda2f3..6d049e7 100644 --- a/clang/test/Driver/amdgpu-macros.cl +++ b/clang/test/Driver/amdgpu-macros.cl @@ -154,26 +154,10 @@ // ARCH-GCN-DAG: #define __[[CPU]]__ 1 // ARCH-GCN-DAG: #define __[[FAMILY]]__ 1 // ARCH-GCN-DAG: #define __amdgcn_processor__ "[[CPU]]" -// ARCH-GCN-DAG: #define __AMDGCN_WAVEFRONT_SIZE [[WAVEFRONT_SIZE]] // ARCH-GCN-DAG: #define __GCC_DESTRUCTIVE_SIZE 128 // ARCH-GCN-DAG: #define __GCC_CONSTRUCTIVE_SIZE 128 // UNSAFEFPATOMIC-DAG: #define __AMDGCN_UNSAFE_FP_ATOMICS__ 1 -// RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 -mwavefrontsize64 \ -// RUN: %s 2>&1 | FileCheck --check-prefix=WAVE64 %s -// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1010 -mwavefrontsize64 \ -// RUN: %s 2>&1 | FileCheck --check-prefix=WAVE64 %s -// RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 -mwavefrontsize64 \ -// RUN: -mno-wavefrontsize64 %s 2>&1 | FileCheck --check-prefix=WAVE64 %s -// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1010 -mwavefrontsize64 \ -// RUN: -mno-wavefrontsize64 %s 2>&1 | FileCheck --check-prefix=WAVE32 %s -// RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 -mno-wavefrontsize64 \ -// RUN: -mwavefrontsize64 %s 2>&1 | FileCheck --check-prefix=WAVE64 %s -// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1010 -mno-wavefrontsize64 \ -// RUN: -mwavefrontsize64 %s 2>&1 | FileCheck --check-prefix=WAVE64 %s -// WAVE64-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64 -// WAVE32-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32 - // RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 \ // RUN: %s 2>&1 | FileCheck --check-prefix=CUMODE-ON %s // RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 -mcumode \ diff --git a/clang/test/Driver/fat-archive-unbundle-ext.c b/clang/test/Driver/fat-archive-unbundle-ext.c index e797acc..d658ad05 100644 --- a/clang/test/Driver/fat-archive-unbundle-ext.c +++ b/clang/test/Driver/fat-archive-unbundle-ext.c @@ -1,5 +1,5 @@ // REQUIRES: x86-registered-target -// UNSUPPORTED: target={{.*-windows.*}}, target={{.*}}-macosx{{.*}}, target={{.*-darwin.*}}, target={{.*}}-aix{{.*}} +// UNSUPPORTED: target={{.*-windows.*}}, target={{.*}}-macosx{{.*}}, target={{.*-darwin.*}}, target={{.*}}-aix{{.*}}, target={{.*}}-zos{{.*}} // Generate dummy fat object // RUN: %clang -O0 --target=%itanium_abi_triple %s -c -o %t.host.o diff --git a/clang/test/Driver/hip-macros.hip b/clang/test/Driver/hip-macros.hip index 516e01a..4c460d5 100644 --- a/clang/test/Driver/hip-macros.hip +++ b/clang/test/Driver/hip-macros.hip @@ -1,27 +1,4 @@ // REQUIRES: amdgpu-registered-target -// RUN: %clang -E -dM --offload-arch=gfx906 -mwavefrontsize64 \ -// RUN: --cuda-device-only -nogpuinc -nogpulib \ -// RUN: %s 2>&1 | FileCheck --check-prefixes=WAVE64 %s -// RUN: %clang -E -dM --offload-arch=gfx1010 -mwavefrontsize64 \ -// RUN: --cuda-device-only -nogpuinc -nogpulib \ -// RUN: %s 2>&1 | FileCheck --check-prefixes=WAVE64 %s -// RUN: %clang -E -dM --offload-arch=gfx906 -mwavefrontsize64 \ -// RUN: --cuda-device-only -nogpuinc -nogpulib \ -// RUN: -mno-wavefrontsize64 %s 2>&1 | FileCheck --check-prefixes=WAVE64 %s -// RUN: %clang -E -dM --offload-arch=gfx1010 -mwavefrontsize64 \ -// RUN: --cuda-device-only -nogpuinc -nogpulib \ -// RUN: -mno-wavefrontsize64 %s 2>&1 | FileCheck --check-prefixes=WAVE32 %s -// RUN: %clang -E -dM --offload-arch=gfx906 -mno-wavefrontsize64 \ -// RUN: --cuda-device-only -nogpuinc -nogpulib \ -// RUN: -mwavefrontsize64 %s 2>&1 | FileCheck --check-prefixes=WAVE64 %s -// RUN: %clang -E -dM --offload-arch=gfx1010 -mno-wavefrontsize64 \ -// RUN: --cuda-device-only -nogpuinc -nogpulib \ -// RUN: -mwavefrontsize64 %s 2>&1 | FileCheck --check-prefixes=WAVE64 %s -// WAVE64-DAG: #define __AMDGCN_WAVEFRONT_SIZE__ 64 -// WAVE32-DAG: #define __AMDGCN_WAVEFRONT_SIZE__ 32 -// WAVE64-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64 -// WAVE32-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32 - // RUN: %clang -E -dM --offload-arch=gfx906 --cuda-device-only -nogpuinc -nogpulib \ // RUN: %s 2>&1 | FileCheck --check-prefix=CUMODE-ON %s // RUN: %clang -E -dM --offload-arch=gfx906 --cuda-device-only -nogpuinc -nogpulib -mcumode \ diff --git a/clang/test/Driver/hip-wavefront-size-deprecation-diagnostics.hip b/clang/test/Driver/hip-wavefront-size-deprecation-diagnostics.hip deleted file mode 100644 index 8a60f5a..0000000 --- a/clang/test/Driver/hip-wavefront-size-deprecation-diagnostics.hip +++ /dev/null @@ -1,115 +0,0 @@ -// REQUIRES: amdgpu-registered-target -// RUN: %clang -xhip --offload-arch=gfx1030 --offload-host-only -pedantic -nogpuinc -nogpulib -nobuiltininc -fsyntax-only -Xclang -verify %s -// RUN: %clang -xhip --offload-arch=gfx1030 --offload-device-only -pedantic -nogpuinc -nogpulib -nobuiltininc -fsyntax-only -Xclang -verify %s - -// Test that deprecation warnings for the wavefront size macro are emitted properly. - -#define WRAPPED __AMDGCN_WAVEFRONT_SIZE__ - -#define DOUBLE_WRAPPED (WRAPPED) - -template <bool C, class T = void> struct my_enable_if {}; - -template <class T> struct my_enable_if<true, T> { - typedef T type; -}; - -__attribute__((host, device)) void use(int, const char*); - -template<int N> __attribute__((host, device)) int templatify(int x) { - return x + N; -} - -__attribute__((device)) const int GlobalConst = __AMDGCN_WAVEFRONT_SIZE__; // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} -constexpr int GlobalConstExpr = __AMDGCN_WAVEFRONT_SIZE__; // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - -#if defined(__HIP_DEVICE_COMPILE__) && (__AMDGCN_WAVEFRONT_SIZE__ == 64) // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} -int foo(void); -#endif - -__attribute__((device)) int device_var = __AMDGCN_WAVEFRONT_SIZE__; // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - -__attribute__((device)) -void device_fun() { - use(__AMDGCN_WAVEFRONT_SIZE, "device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE' has been marked as deprecated}} - use(__AMDGCN_WAVEFRONT_SIZE__, "device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(WRAPPED, "device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(DOUBLE_WRAPPED, "device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(templatify<__AMDGCN_WAVEFRONT_SIZE__>(42), "device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(GlobalConst, "device function"); - use(GlobalConstExpr, "device function"); -} - -__attribute__((global)) -void global_fun() { - // no warnings expected - use(__AMDGCN_WAVEFRONT_SIZE, "global function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE' has been marked as deprecated}} - use(__AMDGCN_WAVEFRONT_SIZE__, "global function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(WRAPPED, "global function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(DOUBLE_WRAPPED, "global function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(templatify<__AMDGCN_WAVEFRONT_SIZE__>(42), "global function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} -} - -int host_var = __AMDGCN_WAVEFRONT_SIZE__; // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} -int host_var_alt = __AMDGCN_WAVEFRONT_SIZE; // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE' has been marked as deprecated}} -int host_var_wrapped = WRAPPED; // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} -int host_var_double_wrapped = DOUBLE_WRAPPED; // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - -__attribute__((host)) -void host_fun() { - use(__AMDGCN_WAVEFRONT_SIZE, "host function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE' has been marked as deprecated}} - use(__AMDGCN_WAVEFRONT_SIZE__, "host function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(WRAPPED, "host function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(DOUBLE_WRAPPED, "host function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(templatify<__AMDGCN_WAVEFRONT_SIZE__>(42), "host function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(GlobalConst, "host function"); - use(GlobalConstExpr, "host function"); -} - -__attribute((host, device)) -void host_device_fun() { - use(__AMDGCN_WAVEFRONT_SIZE__, "host device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(WRAPPED, "host device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(DOUBLE_WRAPPED, "host device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - use(templatify<__AMDGCN_WAVEFRONT_SIZE__>(42), "host device function"); // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} -} - -template <unsigned int OuterWarpSize = __AMDGCN_WAVEFRONT_SIZE__> // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} -class FunSelector { -public: - template<unsigned int FunWarpSize = OuterWarpSize> - __attribute__((device)) - auto fun(void) - -> typename my_enable_if<(FunWarpSize <= __AMDGCN_WAVEFRONT_SIZE__), void>::type // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - { - use(1, "yay!"); - } - - template<unsigned int FunWarpSize = OuterWarpSize> - __attribute__((device)) - auto fun(void) - -> typename my_enable_if<(FunWarpSize > __AMDGCN_WAVEFRONT_SIZE__), void>::type // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - { - use(0, "nay!"); - } -}; - -__attribute__((device)) -void device_fun_selector_user() { - FunSelector<> f; - f.fun<>(); - f.fun<1>(); - f.fun<1000>(); - - my_enable_if<(1 <= __AMDGCN_WAVEFRONT_SIZE__), int>::type x = 42; // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} -} - -__attribute__((device)) my_enable_if<(1 <= __AMDGCN_WAVEFRONT_SIZE__), int>::type DeviceFunTemplateRet(void) { // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - return 42; -} - -__attribute__((device)) int DeviceFunTemplateArg(my_enable_if<(1 <= __AMDGCN_WAVEFRONT_SIZE__), int>::type x) { // expected-warning {{macro '__AMDGCN_WAVEFRONT_SIZE__' has been marked as deprecated}} - return x; -} - -// expected-note@* 0+ {{macro marked 'deprecated' here}} diff --git a/clang/test/Headers/cuda_with_openmp.cu b/clang/test/Headers/cuda_with_openmp.cu index efde4ec..8ea0de5 100644 --- a/clang/test/Headers/cuda_with_openmp.cu +++ b/clang/test/Headers/cuda_with_openmp.cu @@ -2,7 +2,7 @@ // Reported in https://bugs.llvm.org/show_bug.cgi?id=48014 ///==========================================================================/// -// REQUIRES: nvptx-registered-target +// REQUIRES: nvptx-registered-target, host-supports-cuda // RUN: %clang -x cuda -fopenmp -c %s -o - --cuda-path=%S/../Driver/Inputs/CUDA/usr/local/cuda -nocudalib -isystem %S/Inputs/include -isystem %S/../../lib/Headers -fsyntax-only diff --git a/clang/test/OpenMP/task_ast_print.cpp b/clang/test/OpenMP/task_ast_print.cpp index 30fb7ab..b059f18 100644 --- a/clang/test/OpenMP/task_ast_print.cpp +++ b/clang/test/OpenMP/task_ast_print.cpp @@ -1,8 +1,10 @@ // RUN: %clang_cc1 -verify -Wno-vla -fopenmp -ast-print %s | FileCheck %s +// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-version=60 -DOMP60 -ast-print %s | FileCheck %s --check-prefix=CHECK60 // RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp -std=c++11 -include-pch %t -verify -Wno-vla %s -ast-print | FileCheck %s // RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -ast-print %s | FileCheck %s +// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -fopenmp-version=60 -DOMP60 -ast-print %s | FileCheck %s --check-prefix=CHECK60 // RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp-simd -std=c++11 -include-pch %t -verify -Wno-vla %s -ast-print | FileCheck %s // RUN: %clang_cc1 -triple x86_64-pc-linux-gnu -fopenmp -ast-dump %s | FileCheck %s --check-prefix=DUMP @@ -101,8 +103,8 @@ T tmain(T argc, T *argv) { a = 2; #pragma omp task default(none), private(argc, b) firstprivate(argv) shared(d) if (argc > 0) final(S<T>::TS > 0) priority(argc) affinity(argc, argv[b:argc], arr[:], ([argc][sizeof(T)])argv) foo(); -#pragma omp taskgroup task_reduction(-: argc) -#pragma omp task if (C) mergeable priority(C) in_reduction(-: argc) +#pragma omp taskgroup task_reduction(+: argc) +#pragma omp task if (C) mergeable priority(C) in_reduction(+: argc) foo(); return 0; } @@ -119,8 +121,8 @@ T tmain(T argc, T *argv) { // CHECK-NEXT: a = 2; // CHECK-NEXT: #pragma omp task default(none) private(argc,b) firstprivate(argv) shared(d) if(argc > 0) final(S<T>::TS > 0) priority(argc) affinity(argc,argv[b:argc],arr[:],([argc][sizeof(T)])argv) // CHECK-NEXT: foo() -// CHECK-NEXT: #pragma omp taskgroup task_reduction(-: argc) -// CHECK-NEXT: #pragma omp task if(C) mergeable priority(C) in_reduction(-: argc) +// CHECK-NEXT: #pragma omp taskgroup task_reduction(+: argc) +// CHECK-NEXT: #pragma omp task if(C) mergeable priority(C) in_reduction(+: argc) // CHECK-NEXT: foo() // CHECK: template<> int tmain<int, 5>(int argc, int *argv) { // CHECK-NEXT: int b = argc, c, d, e, f, g; @@ -134,8 +136,8 @@ T tmain(T argc, T *argv) { // CHECK-NEXT: a = 2; // CHECK-NEXT: #pragma omp task default(none) private(argc,b) firstprivate(argv) shared(d) if(argc > 0) final(S<int>::TS > 0) priority(argc) affinity(argc,argv[b:argc],arr[:],([argc][sizeof(int)])argv) // CHECK-NEXT: foo() -// CHECK-NEXT: #pragma omp taskgroup task_reduction(-: argc) -// CHECK-NEXT: #pragma omp task if(5) mergeable priority(5) in_reduction(-: argc) +// CHECK-NEXT: #pragma omp taskgroup task_reduction(+: argc) +// CHECK-NEXT: #pragma omp task if(5) mergeable priority(5) in_reduction(+: argc) // CHECK-NEXT: foo() // CHECK: template<> long tmain<long, 1>(long argc, long *argv) { // CHECK-NEXT: long b = argc, c, d, e, f, g; @@ -149,8 +151,8 @@ T tmain(T argc, T *argv) { // CHECK-NEXT: a = 2; // CHECK-NEXT: #pragma omp task default(none) private(argc,b) firstprivate(argv) shared(d) if(argc > 0) final(S<long>::TS > 0) priority(argc) affinity(argc,argv[b:argc],arr[:],([argc][sizeof(long)])argv) // CHECK-NEXT: foo() -// CHECK-NEXT: #pragma omp taskgroup task_reduction(-: argc) -// CHECK-NEXT: #pragma omp task if(1) mergeable priority(1) in_reduction(-: argc) +// CHECK-NEXT: #pragma omp taskgroup task_reduction(+: argc) +// CHECK-NEXT: #pragma omp task if(1) mergeable priority(1) in_reduction(+: argc) // CHECK-NEXT: foo() enum Enum {}; @@ -199,6 +201,14 @@ int main(int argc, char **argv) { #pragma omp task depend(inout: omp_all_memory) foo(); // CHECK-NEXT: foo(); +#ifdef OMP60 +#pragma omp task threadset(omp_pool) +#pragma omp task threadset(omp_team) + foo(); +#endif + // CHECK60: #pragma omp task threadset(omp_pool) + // CHECK60: #pragma omp task threadset(omp_team) + // CHECK60-NEXT: foo(); return tmain<int, 5>(b, &b) + tmain<long, 1>(x, &x); } diff --git a/clang/test/OpenMP/task_codegen.cpp b/clang/test/OpenMP/task_codegen.cpp index c3e6d9e6b..ba8e694 100644 --- a/clang/test/OpenMP/task_codegen.cpp +++ b/clang/test/OpenMP/task_codegen.cpp @@ -41,6 +41,9 @@ // RUN: -emit-llvm -o - -DOMP51 | FileCheck %s \ // RUN: --implicit-check-not="{{__kmpc|__tgt}}" +// RUN: %clang_cc1 -verify -Wno-vla -triple x86_64-apple-darwin10 -fopenmp -fopenmp-version=60 -DOMP60 -fopenmp-enable-irbuilder -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK6 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=60 -DOMP60 -fopenmp-enable-irbuilder -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=60 -DOMP60 -fopenmp-enable-irbuilder -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK6 // expected-no-diagnostics #ifndef HEADER @@ -65,6 +68,7 @@ struct S { S(const S &s) : a(s.a) {} ~S() {} }; + int a; int main() { char b; @@ -147,6 +151,7 @@ int main() { + // s1 = S(); @@ -215,6 +220,19 @@ void test_omp_all_memory() } } #endif // OMP51 + +#ifdef OMP60 +void test_threadset() +{ +#pragma omp task threadset(omp_team) + { + } +#pragma omp task threadset(omp_pool) + { + } +} +#endif // OMP60 + #endif // CHECK1-LABEL: define {{[^@]+}}@main // CHECK1-SAME: () #[[ATTR0:[0-9]+]] { @@ -10243,3 +10261,18 @@ void test_omp_all_memory() // CHECK4-51-NEXT: call void @__cxx_global_var_init() // CHECK4-51-NEXT: ret void // +// CHECK6-LABEL: define void @_Z14test_threadsetv() +// CHECK6-NEXT: entry: +// CHECK6-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_23:%.*]], align 1 +// CHECK6-NEXT: [[AGG_CAPTURED2:%.*]] = alloca [[STRUCT_ANON_25:%.*]], align 1 +// CHECK6-NEXT: call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR:[0-9]+]]) +// CHECK6-NEXT: [[TMP0:%.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %omp_global_thread_num, i32 1, i64 40, i64 1, ptr @.omp_task_entry..[[ENTRY1:[0-9]+]]) +// CHECK6-NEXT: getelementptr inbounds nuw %struct.kmp_task_t_with_privates{{.*}}, ptr %0, i32 0, i32 0 +// CHECK6-NEXT: call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR:[0-9]+]]) +// CHECK6-NEXT: call i32 @__kmpc_omp_task(ptr @1, i32 %omp_global_thread_num1, ptr %0) +// CHECK6-NEXT: call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR2:[0-9]+]]) +// CHECK6-NEXT: [[TMP3:%.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %omp_global_thread_num3, i32 129, i64 40, i64 1, ptr @.omp_task_entry..[[ENTRY2:[0-9]+]]) +// CHECK6-NEXT: getelementptr inbounds nuw %struct.kmp_task_t_with_privates{{.*}}, ptr %3, i32 0, i32 0 +// CHECK6-NEXT: call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR2:[0-9]+]]) +// CHECK6-NEXT: call i32 @__kmpc_omp_task(ptr @1, i32 %omp_global_thread_num4, ptr %3) +// CHECK6-NEXT: ret void diff --git a/clang/test/OpenMP/task_threadset_messages.cpp b/clang/test/OpenMP/task_threadset_messages.cpp new file mode 100755 index 0000000..f553a2d --- /dev/null +++ b/clang/test/OpenMP/task_threadset_messages.cpp @@ -0,0 +1,99 @@ +// RUN: %clang_cc1 -verify=expected,omp45 -fopenmp -fopenmp-version=45 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected,omp50 -fopenmp -fopenmp-version=50 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected,omp51 -fopenmp -fopenmp-version=51 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected -DOMP60 -fopenmp -fopenmp-version=60 -std=c++11 -ferror-limit 200 -o - %s + +// RUN: %clang_cc1 -verify=expected,omp45 -fopenmp-simd -fopenmp-version=45 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected,omp50 -fopenmp-simd -fopenmp-version=50 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected,omp51 -fopenmp-simd -fopenmp-version=51 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected -DOMP60 -fopenmp-simd -fopenmp-version=60 -std=c++11 -ferror-limit 200 -o - %s + +#ifdef OMP60 +struct ComplexStruct { + int data[10]; + struct InnerStruct { + float value; + } inner; +}; + +// Template class with member functions using 'threadset'. +template <typename T> +class TemplateClass { +public: + void foo() { + #pragma omp task threadset(omp_pool) + { + T temp; + } + } + void bar() { + #pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 10; ++i) {} + } +}; + +// Valid uses of 'threadset' with 'omp_pool' and 'omp_team' in task directive. +void test_task_threadset_valid() { + int a; + #pragma omp task threadset(omp_pool) + #pragma omp task threadset(omp_team) + #pragma omp task threadset(omp_pool) if(1) + #pragma omp task threadset(omp_team) priority(5) + #pragma omp task threadset(omp_pool) depend(out: a) + #pragma omp parallel + { + #pragma omp task threadset(omp_pool) + { + #pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 5; ++i) {} + } + } + + TemplateClass<int> obj; + obj.foo(); + obj.bar(); +} + +// Invalid uses of 'threadset' with incorrect arguments in task directive. +void test_task_threadset_invalid_args() { + #pragma omp task threadset(invalid_arg) // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + #pragma omp task threadset(123) // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + #pragma omp task threadset(omp_pool, omp_team) // expected-error {{expected ')'}} expected-note {{to match this '('}} + #pragma omp task threadset() // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + {} +} + +// Valid uses of 'threadset' with 'omp_pool' and 'omp_team' in taskloop directive. +void test_taskloop_threadset_valid() { + #pragma omp taskloop threadset(omp_pool) + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_pool) grainsize(5) + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_team) num_tasks(2) + for (int i = 0; i < 10; ++i) {} +} + +// Invalid uses of 'threadset' with incorrect arguments in taskloop directive. +void test_taskloop_threadset_invalid_args() { + #pragma omp taskloop threadset(invalid_arg) // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(123) // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_pool, omp_team) // expected-error {{expected ')'}} expected-note {{to match this '('}} + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset() // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + for (int i = 0; i < 10; ++i) {} +} + +#else +void test_threadset_not_supported() { + #pragma omp task threadset(omp_pool) // omp45-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} omp50-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} omp51-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} + #pragma omp task threadset(omp_team) // omp45-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} omp50-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} omp51-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} + #pragma omp taskloop threadset(omp_team) // omp45-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} omp50-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} omp51-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_pool) // omp45-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} omp50-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} omp51-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} + for (int i = 0; i < 10; ++i) {} +} +#endif diff --git a/clang/test/OpenMP/taskloop_ast_print.cpp b/clang/test/OpenMP/taskloop_ast_print.cpp index 1b6d724..e4bf20a 100644 --- a/clang/test/OpenMP/taskloop_ast_print.cpp +++ b/clang/test/OpenMP/taskloop_ast_print.cpp @@ -1,8 +1,10 @@ // RUN: %clang_cc1 -verify -fopenmp -ast-print %s | FileCheck %s +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=60 -DOMP60 -ast-print %s | FileCheck %s --check-prefix=CHECK60 // RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp -std=c++11 -include-pch %t -verify %s -ast-print | FileCheck %s // RUN: %clang_cc1 -verify -fopenmp-simd -ast-print %s | FileCheck %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=60 -DOMP60 -ast-print %s | FileCheck %s --check-prefix=CHECK60 // RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp-simd -std=c++11 -include-pch %t -verify %s -ast-print | FileCheck %s // expected-no-diagnostics @@ -87,6 +89,20 @@ int main(int argc, char **argv) { // CHECK-NEXT: #pragma omp cancel taskgroup // CHECK-NEXT: #pragma omp cancellation point taskgroup // CHECK-NEXT: foo(); +#ifdef OMP60 +#pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 10; ++i) { +#pragma omp taskloop threadset(omp_pool) + for (int j = 0; j < 10; ++j) { + foo(); + } +} +#endif + // CHECK60: #pragma omp taskloop threadset(omp_team) + // CHECK60-NEXT: for (int i = 0; i < 10; ++i) { + // CHECK60: #pragma omp taskloop threadset(omp_pool) + // CHECK60-NEXT: for (int j = 0; j < 10; ++j) { + // CHECK60-NEXT: foo(); return (tmain<int, 5>(argc) + tmain<char, 1>(argv[0][0])); } diff --git a/clang/test/OpenMP/taskloop_codegen.cpp b/clang/test/OpenMP/taskloop_codegen.cpp index 69f8d3b..d119760 100644 --- a/clang/test/OpenMP/taskloop_codegen.cpp +++ b/clang/test/OpenMP/taskloop_codegen.cpp @@ -5,7 +5,12 @@ // RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp-simd -x c++ -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s // RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s + // SIMD-ONLY0-NOT: {{__kmpc|__tgt}} + +// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -fopenmp-version=60 -DOMP60 -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK6 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=60 -DOMP60 -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=60 -DOMP60 -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK6 // expected-no-diagnostics #ifndef HEADER #define HEADER @@ -241,4 +246,52 @@ void taskloop_with_class() { } } +#ifdef OMP60 +void test_threadset() +{ +#pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 10; ++i) { + } +#pragma omp taskloop threadset(omp_pool) + for (int i = 0; i < 10; ++i) { + } +} +#endif // OMP60 +// CHECK6-LABEL: define void @_Z14test_threadsetv() +// CHECK6-NEXT: entry: +// CHECK6-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_14:%.*]], align 1 +// CHECK6-NEXT: %[[TMP:.*]] = alloca i32, align 4 +// CHECK6-NEXT: [[AGG_CAPTURED1:%.*]] = alloca [[STRUCT_ANON_16:%.*]], align 1 +// CHECK6-NEXT: %[[TMP2:.*]] = alloca i32, align 4 +// CHECK6-NEXT: %[[TID0:.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR:[0-9]+]]) +// CHECK6-NEXT: call void @__kmpc_taskgroup(ptr @1, i32 %[[TID0:.*]]) +// CHECK6-NEXT: %[[TID1:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[TID0:.*]], i32 1, i64 80, i64 1, ptr @.omp_task_entry..[[ENTRY1:[0-9]+]]) +// CHECK6-NEXT: %[[TID2:.*]] = getelementptr inbounds nuw %struct.kmp_task_t_with_privates{{.*}}, ptr %[[TID1:.*]], i32 0, i32 0 +// CHECK6-NEXT: %[[TID3:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID2:.*]], i32 0, i32 5 +// CHECK6-NEXT: store i64 0, ptr %[[TID3:.*]], align 8 +// CHECK6-NEXT: %[[TID4:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID2:.*]], i32 0, i32 6 +// CHECK6-NEXT: store i64 9, ptr %[[TID4:.*]], align 8 +// CHECK6-NEXT: %[[TID5:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID2:.*]], i32 0, i32 7 +// CHECK6-NEXT: store i64 1, ptr %[[TID5:.*]], align 8 +// CHECK6-NEXT: %[[TID6:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID2:.*]], i32 0, i32 9 +// CHECK6-NEXT: call void @llvm.memset.p0.i64(ptr align 8 %[[TID6:.*]], i8 0, i64 8, i1 false) +// CHECK6-NEXT: %[[TID7:.*]] = load i64, ptr %[[TID5:.*]], align 8 +// CHECK6-NEXT: call void @__kmpc_taskloop(ptr @1, i32 %[[TID0:.*]], ptr %[[TID1:.*]], i32 1, ptr %[[TID3:.*]], ptr %4, i64 %[[TID7:.*]], i32 1, i32 0, i64 0, ptr null) +// CHECK6-NEXT: call void @__kmpc_end_taskgroup(ptr @1, i32 %[[TID0:.*]]) +// CHECK6-NEXT: call void @__kmpc_taskgroup(ptr @1, i32 %[[TID0:.*]]) +// CHECK6-NEXT: %[[TID8:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[TID0:.*]], i32 129, i64 80, i64 1, ptr @.omp_task_entry..[[ENTRY1:[0-9]+]]) +// CHECK6-NEXT: %[[TID9:.*]] = getelementptr inbounds nuw %struct.kmp_task_t_with_privates{{.*}}, ptr %[[TID8:.*]], i32 0, i32 0 +// CHECK6-NEXT: %[[TID10:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID9:.*]], i32 0, i32 5 +// CHECK6-NEXT: store i64 0, ptr %[[TID10:.*]], align 8 +// CHECK6-NEXT: %[[TID11:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID9:.*]], i32 0, i32 6 +// CHECK6-NEXT: store i64 9, ptr %[[TID11:.*]], align 8 +// CHECK6-NEXT: %[[TID12:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID9:.*]], i32 0, i32 7 +// CHECK6-NEXT: store i64 1, ptr %[[TID12:.*]], align 8 +// CHECK6-NEXT: %[[TID13:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID9:.*]], i32 0, i32 9 +// CHECK6-NEXT: call void @llvm.memset.p0.i64(ptr align 8 [[TID13:.*]], i8 0, i64 8, i1 false) +// CHECK6-NEXT: %[[TID14:.*]] = load i64, ptr [[TID12:.*]], align 8 +// CHECK6-NEXT: call void @__kmpc_taskloop(ptr @1, i32 %[[TID0:.*]], ptr %[[TID8:.*]], i32 1, ptr %[[TID10:.*]], ptr %[[TID11:.*]], i64 %[[TID14:.*]], i32 1, i32 0, i64 0, ptr null) +// CHECK6-NEXT: call void @__kmpc_end_taskgroup(ptr @1, i32 %[[TID0:.*]]) +// CHECK6-NEXT: ret void + #endif diff --git a/clang/test/Preprocessor/predefined-arch-macros.c b/clang/test/Preprocessor/predefined-arch-macros.c index a3c3697..cdb4632 100644 --- a/clang/test/Preprocessor/predefined-arch-macros.c +++ b/clang/test/Preprocessor/predefined-arch-macros.c @@ -4418,7 +4418,6 @@ // CHECK_AMDGCN_NONE-NOT: #define __HAS_FMAF__ // CHECK_AMDGCN_NONE-NOT: #define __HAS_FP64__ // CHECK_AMDGCN_NONE-NOT: #define __HAS_LDEXPF__ -// CHECK_AMDGCN_NONE-NOT: #define __AMDGCN_WAVEFRONT_SIZE__ // Begin r600 tests ---------------- @@ -4439,7 +4438,6 @@ // RUN: %clang -x hip -E -dM %s -o - 2>&1 --offload-host-only -nogpulib \ // RUN: -nogpuinc --offload-arch=gfx803 -target x86_64-unknown-linux \ // RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_HIP_HOST -// CHECK_HIP_HOST: #define __AMDGCN_WAVEFRONT_SIZE__ 64 // CHECK_HIP_HOST: #define __AMDGPU__ 1 // CHECK_HIP_HOST: #define __AMD__ 1 diff --git a/clang/test/SemaOpenCL/builtins-extended-image-param-gfx1100-err.cl b/clang/test/SemaOpenCL/builtins-extended-image-param-gfx1100-err.cl new file mode 100644 index 0000000..47dbdd4 --- /dev/null +++ b/clang/test/SemaOpenCL/builtins-extended-image-param-gfx1100-err.cl @@ -0,0 +1,227 @@ +// RUN: %clang_cc1 -triple amdgcn-- -target-cpu gfx1100 -target-feature +extended-image-insts -S -verify=expected -o - %s +// REQUIRES: amdgpu-registered-target + +#pragma OPENCL EXTENSION cl_khr_fp16 : enable + +typedef int int4 __attribute__((ext_vector_type(4))); +typedef float float4 __attribute__((ext_vector_type(4))); +typedef half half4 __attribute__((ext_vector_type(4))); + +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_r(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(1, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_gather4_lz_2d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_g(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(2, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_gather4_lz_2d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_b(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(4, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_gather4_lz_2d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_a(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(8, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_gather4_lz_2d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_lz_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1d_v4f32_f32(i32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_1d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_l_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1d_v4f32_f32(100, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_1d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_d_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1d_v4f32_f32(100, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_1d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_lz_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_v4f32_f32(100, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_2d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_l_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_v4f32_f32(100, f32, f32, f32, tex, vec4i32, 0, f32, 103); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_2d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_d_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_v4f32_f32(i32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_2d_v4f32_f32' must be a constant integer}} +} +float4 test_amdgcn_image_sample_lz_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_3d_v4f32_f32(i32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_3d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_l_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_3d_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_3d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_d_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_3d_v4f32_f32(1, f32, f32, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_3d_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_lz_cube_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_cube_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_cube_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_l_cube_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_cube_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_cube_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_lz_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1darray_v4f32_f32(1, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_1darray_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_l_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1darray_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_1darray_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_d_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1darray_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_1darray_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_lz_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_2darray_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_l_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_2darray_v4f32_f32' must be a constant integer}} +} + +float4 test_amdgcn_image_sample_d_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_v4f32_f32(1, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_2darray_v4f32_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_lz_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1d_v4f16_f32(23, f32, tex, vec4i32, 0, i32, 11); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_1d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_l_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1d_v4f16_f32(i32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_1d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_d_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1d_v4f16_f32(i32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_1d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_lz_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_v4f16_f32(100, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_2d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_l_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_2d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_d_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_v4f16_f32(100, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_2d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_lz_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_3d_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_3d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_l_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_3d_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_3d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_d_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_3d_v4f16_f32(100, f32, f32, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_3d_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_lz_cube_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_cube_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_cube_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_l_cube_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_cube_v4f16_f32(i32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_cube_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_lz_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1darray_v4f16_f32(i32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_1darray_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_l_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1darray_v4f16_f32(i32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_1darray_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_d_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1darray_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_1darray_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_lz_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_2darray_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_l_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_2darray_v4f16_f32' must be a constant integer}} +} + +half4 test_amdgcn_image_sample_d_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_v4f16_f32(100, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_2darray_v4f16_f32' must be a constant integer}} +} + +float test_amdgcn_image_sample_lz_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_f32_f32(1, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_2d_f32_f32' must be a constant integer}} +} + +float test_amdgcn_image_sample_l_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_f32_f32(1, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_2d_f32_f32' must be a constant integer}} +} + +float test_amdgcn_image_sample_d_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_f32_f32(1, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_2d_f32_f32' must be a constant integer}} +} + +float test_amdgcn_image_sample_lz_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_f32_f32(1, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_lz_2darray_f32_f32' must be a constant integer}} +} + +float test_amdgcn_image_sample_l_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_l_2darray_f32_f32' must be a constant integer}} +} + +float test_amdgcn_image_sample_d_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_f32_f32(1, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, f32, i32); //expected-error{{argument to '__builtin_amdgcn_image_sample_d_2darray_f32_f32' must be a constant integer}} +} diff --git a/clang/test/SemaOpenCL/builtins-extended-image-param-gfx942-err.cl b/clang/test/SemaOpenCL/builtins-extended-image-param-gfx942-err.cl new file mode 100644 index 0000000..e60f8c7 --- /dev/null +++ b/clang/test/SemaOpenCL/builtins-extended-image-param-gfx942-err.cl @@ -0,0 +1,227 @@ +// RUN: %clang_cc1 -triple amdgcn-- -target-cpu gfx942 -verify=GFX94 -S -o - %s +// REQUIRES: amdgpu-registered-target + +#pragma OPENCL EXTENSION cl_khr_fp16 : enable + +typedef int int4 __attribute__((ext_vector_type(4))); +typedef float float4 __attribute__((ext_vector_type(4))); +typedef half half4 __attribute__((ext_vector_type(4))); + +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_r(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(1, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_gather4_lz_2d_v4f32_f32_r' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_g(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(2, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_gather4_lz_2d_v4f32_f32_g' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_b(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(4, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_gather4_lz_2d_v4f32_f32_b' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_gather4_lz_2d_v4f32_f32_a(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_gather4_lz_2d_v4f32_f32(8, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_gather4_lz_2d_v4f32_f32_a' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_lz_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1d_v4f32_f32(105, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_1d_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_l_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1d_v4f32_f32(100, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_1d_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_d_1d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1d_v4f32_f32(100, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_1d_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_lz_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_v4f32_f32(100, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_2d_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_l_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_v4f32_f32(10, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_2d_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_d_2d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_v4f32_f32(105, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_2d_v4f32_f32' needs target feature extended-image-insts}} +} +float4 test_amdgcn_image_sample_lz_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_3d_v4f32_f32(105, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_3d_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_l_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_3d_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_3d_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_d_3d_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_3d_v4f32_f32(1, f32, f32, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_3d_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_lz_cube_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_cube_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_cube_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_l_cube_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_cube_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_cube_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_lz_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1darray_v4f32_f32(1, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_1darray_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_l_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1darray_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_1darray_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_d_1darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1darray_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_1darray_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_lz_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_v4f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_2darray_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_l_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_v4f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_2darray_v4f32_f32' needs target feature extended-image-insts}} +} + +float4 test_amdgcn_image_sample_d_2darray_v4f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_v4f32_f32(1, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_2darray_v4f32_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_lz_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1d_v4f16_f32(105, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_1d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_l_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1d_v4f16_f32(105, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_1d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_d_1d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1d_v4f16_f32(105, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_1d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_lz_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_v4f16_f32(100, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_2d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_l_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_2d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_d_2d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_v4f16_f32(100, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_2d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_lz_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_3d_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_3d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_l_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_3d_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_3d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_d_3d_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_3d_v4f16_f32(100, f32, f32, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_3d_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_lz_cube_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_cube_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_cube_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_l_cube_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_cube_v4f16_f32(105, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_cube_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_lz_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_1darray_v4f16_f32(105, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_1darray_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_l_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_1darray_v4f16_f32(105, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_1darray_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_d_1darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_1darray_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_1darray_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_lz_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_v4f16_f32(100, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_2darray_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_l_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_v4f16_f32(100, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_2darray_v4f16_f32' needs target feature extended-image-insts}} +} + +half4 test_amdgcn_image_sample_d_2darray_v4f16_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_v4f16_f32(100, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_2darray_v4f16_f32' needs target feature extended-image-insts}} +} + +float test_amdgcn_image_sample_lz_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2d_f32_f32(1, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_2d_f32_f32' needs target feature extended-image-insts}} +} + +float test_amdgcn_image_sample_l_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2d_f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_2d_f32_f32' needs target feature extended-image-insts}} +} + +float test_amdgcn_image_sample_d_2d_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2d_f32_f32(1, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_2d_f32_f32' needs target feature extended-image-insts}} +} + +float test_amdgcn_image_sample_lz_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_lz_2darray_f32_f32(1, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_lz_2darray_f32_f32' needs target feature extended-image-insts}} +} + +float test_amdgcn_image_sample_l_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_l_2darray_f32_f32(1, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_l_2darray_f32_f32' needs target feature extended-image-insts}} +} + +float test_amdgcn_image_sample_d_2darray_f32_f32(float4 v4f32, float f32, int i32, __amdgpu_texture_t tex, int4 vec4i32) { + + return __builtin_amdgcn_image_sample_d_2darray_f32_f32(1, f32, f32, f32, f32, f32, f32, f32, tex, vec4i32, 0, 101, 121); //GFX94-error{{'test_amdgcn_image_sample_d_2darray_f32_f32' needs target feature extended-image-insts}} +} diff --git a/clang/tools/libclang/CIndex.cpp b/clang/tools/libclang/CIndex.cpp index fc27fd2..08776d9 100644 --- a/clang/tools/libclang/CIndex.cpp +++ b/clang/tools/libclang/CIndex.cpp @@ -2406,6 +2406,8 @@ void OMPClauseEnqueue::VisitOMPCompareClause(const OMPCompareClause *) {} void OMPClauseEnqueue::VisitOMPFailClause(const OMPFailClause *) {} +void OMPClauseEnqueue::VisitOMPThreadsetClause(const OMPThreadsetClause *) {} + void OMPClauseEnqueue::VisitOMPAbsentClause(const OMPAbsentClause *) {} void OMPClauseEnqueue::VisitOMPHoldsClause(const OMPHoldsClause *) {} diff --git a/clang/unittests/Format/AlignBracketsTest.cpp b/clang/unittests/Format/AlignBracketsTest.cpp index ea8db51..10ca5fb 100644 --- a/clang/unittests/Format/AlignBracketsTest.cpp +++ b/clang/unittests/Format/AlignBracketsTest.cpp @@ -28,7 +28,7 @@ TEST_F(AlignBracketsTest, AlignsAfterOpenBracket) { "SomeLongVariableName->someFunction(foooooooo(aaaaaaaaaaaaaaa,\n" " aaaaaaaaaaaaaaaaaaaaa));"); FormatStyle Style = getLLVMStyle(); - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; verifyFormat("void aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa(\n" " aaaaaaaaaaa aaaaaaaa, aaaaaaaaa aaaaaaa) {}", Style); @@ -64,7 +64,7 @@ TEST_F(AlignBracketsTest, AlignsAfterOpenBracket) { Style); Style.ColumnLimit = 80; - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; Style.BinPackArguments = false; Style.BinPackParameters = FormatStyle::BPPS_OnePerLine; verifyFormat("void aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa(\n" @@ -115,7 +115,9 @@ TEST_F(AlignBracketsTest, AlignsAfterOpenBracket) { " XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXZZZZZZZZZZZZZZZZZZZZZZZZZ()));", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakBeforeCloseBracketFunction = true; + Style.BreakBeforeCloseBracketBracedList = true; Style.BinPackArguments = false; Style.BinPackParameters = FormatStyle::BPPS_OnePerLine; verifyFormat("void aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa(\n" @@ -254,7 +256,8 @@ TEST_F(AlignBracketsTest, AlignAfterOpenBracketBlockIndent) { "argument5));", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakBeforeCloseBracketFunction = true; verifyFormat(Short, Style); verifyFormat( @@ -378,7 +381,8 @@ TEST_F(AlignBracketsTest, AlignAfterOpenBracketBlockIndentIfStatement) { "}", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakBeforeCloseBracketFunction = true; verifyFormat("if (foo()) {\n" " return;\n" @@ -440,7 +444,8 @@ TEST_F(AlignBracketsTest, AlignAfterOpenBracketBlockIndentForStatement) { "}", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakBeforeCloseBracketFunction = true; verifyFormat("for (int i = 0; i < 5; ++i) {\n" " doSomething();\n" @@ -457,7 +462,8 @@ TEST_F(AlignBracketsTest, AlignAfterOpenBracketBlockIndentForStatement) { TEST_F(AlignBracketsTest, AlignAfterOpenBracketBlockIndentInitializers) { auto Style = getLLVMStyleWithColumns(60); - Style.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Style.BreakAfterOpenBracketBracedList = true; + Style.BreakBeforeCloseBracketBracedList = true; // Aggregate initialization. verifyFormat("int LooooooooooooooooooooooooongVariable[2] = {\n" " 10000000, 20000000\n" @@ -611,13 +617,13 @@ TEST_F(AlignBracketsTest, AllowAllArgumentsOnNextLineDontAlign) { StringRef Input = "functionCall(paramA, paramB, paramC);\n" "void functionDecl(int A, int B, int C);"; Style.AllowAllArgumentsOnNextLine = false; - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; verifyFormat(StringRef("functionCall(paramA, paramB,\n" " paramC);\n" "void functionDecl(int A, int B,\n" " int C);"), Input, Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_Align; + Style.AlignAfterOpenBracket = true; verifyFormat(StringRef("functionCall(paramA, paramB,\n" " paramC);\n" "void functionDecl(int A, int B,\n" @@ -625,13 +631,14 @@ TEST_F(AlignBracketsTest, AllowAllArgumentsOnNextLineDontAlign) { Input, Style); // However, BAS_AlwaysBreak and BAS_BlockIndent should take precedence over // AllowAllArgumentsOnNextLine. - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; verifyFormat(StringRef("functionCall(\n" " paramA, paramB, paramC);\n" "void functionDecl(\n" " int A, int B, int C);"), Input, Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakBeforeCloseBracketFunction = true; verifyFormat("functionCall(\n" " paramA, paramB, paramC\n" ");\n" @@ -639,11 +646,12 @@ TEST_F(AlignBracketsTest, AllowAllArgumentsOnNextLineDontAlign) { " int A, int B, int C\n" ");", Input, Style); + Style.BreakBeforeCloseBracketFunction = false; // When AllowAllArgumentsOnNextLine is set, we prefer breaking before the // first argument. Style.AllowAllArgumentsOnNextLine = true; - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; verifyFormat(StringRef("functionCall(\n" " paramA, paramB, paramC);\n" "void functionDecl(\n" @@ -651,13 +659,14 @@ TEST_F(AlignBracketsTest, AllowAllArgumentsOnNextLineDontAlign) { Input, Style); // It wouldn't fit on one line with aligned parameters so this setting // doesn't change anything for BAS_Align. - Style.AlignAfterOpenBracket = FormatStyle::BAS_Align; + Style.AlignAfterOpenBracket = true; + Style.BreakAfterOpenBracketFunction = false; verifyFormat(StringRef("functionCall(paramA, paramB,\n" " paramC);\n" "void functionDecl(int A, int B,\n" " int C);"), Input, Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.BreakAfterOpenBracketFunction = true; verifyFormat(StringRef("functionCall(\n" " paramA, paramB, paramC);\n" "void functionDecl(\n" @@ -678,13 +687,14 @@ TEST_F(AlignBracketsTest, FormatsDeclarationBreakAlways) { // Ensure AlignAfterOpenBracket interacts correctly with BinPackParameters set // to BPPS_AlwaysOnePerLine. - BreakAlways.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + BreakAlways.BreakAfterOpenBracketFunction = true; verifyFormat( "void someLongFunctionName(\n" " int aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa,\n" " int b);", BreakAlways); - BreakAlways.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + BreakAlways.BreakAfterOpenBracketFunction = true; + BreakAlways.BreakBeforeCloseBracketFunction = true; verifyFormat( "void someLongFunctionName(\n" " int aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa,\n" @@ -734,7 +744,7 @@ TEST_F(AlignBracketsTest, FormatsDefinitionBreakAlways) { // Ensure AlignAfterOpenBracket interacts correctly with BinPackParameters set // to BPPS_AlwaysOnePerLine. - BreakAlways.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + BreakAlways.BreakAfterOpenBracketFunction = true; verifyFormat( "void someLongFunctionName(\n" " int aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa,\n" @@ -743,7 +753,8 @@ TEST_F(AlignBracketsTest, FormatsDefinitionBreakAlways) { " aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa, b);\n" "}", BreakAlways); - BreakAlways.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + BreakAlways.BreakAfterOpenBracketFunction = true; + BreakAlways.BreakBeforeCloseBracketFunction = true; verifyFormat( "void someLongFunctionName(\n" " int aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa,\n" @@ -761,17 +772,17 @@ TEST_F(AlignBracketsTest, ParenthesesAndOperandAlignment) { verifyFormat("int a = f(aaaaaaaaaaaaaaaaaaaaaa &&\n" " bbbbbbbbbbbbbbbbbbbbbb);", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_Align; + Style.AlignAfterOpenBracket = true; Style.AlignOperands = FormatStyle::OAS_DontAlign; verifyFormat("int a = f(aaaaaaaaaaaaaaaaaaaaaa &&\n" " bbbbbbbbbbbbbbbbbbbbbb);", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; Style.AlignOperands = FormatStyle::OAS_Align; verifyFormat("int a = f(aaaaaaaaaaaaaaaaaaaaaa &&\n" " bbbbbbbbbbbbbbbbbbbbbb);", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; Style.AlignOperands = FormatStyle::OAS_DontAlign; verifyFormat("int a = f(aaaaaaaaaaaaaaaaaaaaaa &&\n" " bbbbbbbbbbbbbbbbbbbbbb);", @@ -781,7 +792,10 @@ TEST_F(AlignBracketsTest, ParenthesesAndOperandAlignment) { TEST_F(AlignBracketsTest, BlockIndentAndNamespace) { auto Style = getLLVMStyleWithColumns(120); Style.AllowShortNamespacesOnASingleLine = true; - Style.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakAfterOpenBracketBracedList = true; + Style.BreakBeforeCloseBracketFunction = true; + Style.BreakBeforeCloseBracketBracedList = true; verifyNoCrash( "namespace {\n" diff --git a/clang/unittests/Format/ConfigParseTest.cpp b/clang/unittests/Format/ConfigParseTest.cpp index 6488e38..43b2117 100644 --- a/clang/unittests/Format/ConfigParseTest.cpp +++ b/clang/unittests/Format/ConfigParseTest.cpp @@ -172,6 +172,16 @@ TEST(ConfigParseTest, ParsesConfigurationBools) { CHECK_PARSE_BOOL(BinPackLongBracedList); CHECK_PARSE_BOOL(BreakAdjacentStringLiterals); CHECK_PARSE_BOOL(BreakAfterJavaFieldAnnotations); + CHECK_PARSE_BOOL(BreakAfterOpenBracketBracedList); + CHECK_PARSE_BOOL(BreakAfterOpenBracketFunction); + CHECK_PARSE_BOOL(BreakAfterOpenBracketIf); + CHECK_PARSE_BOOL(BreakAfterOpenBracketLoop); + CHECK_PARSE_BOOL(BreakAfterOpenBracketSwitch); + CHECK_PARSE_BOOL(BreakBeforeCloseBracketBracedList); + CHECK_PARSE_BOOL(BreakBeforeCloseBracketFunction); + CHECK_PARSE_BOOL(BreakBeforeCloseBracketIf); + CHECK_PARSE_BOOL(BreakBeforeCloseBracketLoop); + CHECK_PARSE_BOOL(BreakBeforeCloseBracketSwitch); CHECK_PARSE_BOOL(BreakBeforeTemplateCloser); CHECK_PARSE_BOOL(BreakBeforeTernaryOperators); CHECK_PARSE_BOOL(BreakStringLiterals); @@ -533,20 +543,23 @@ TEST(ConfigParseTest, ParsesConfiguration) { CHECK_PARSE("EnumTrailingComma: Remove", EnumTrailingComma, FormatStyle::ETC_Remove); - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; - CHECK_PARSE("AlignAfterOpenBracket: Align", AlignAfterOpenBracket, - FormatStyle::BAS_Align); - CHECK_PARSE("AlignAfterOpenBracket: DontAlign", AlignAfterOpenBracket, - FormatStyle::BAS_DontAlign); + Style.AlignAfterOpenBracket = false; + CHECK_PARSE("AlignAfterOpenBracket: Align", AlignAfterOpenBracket, true); + CHECK_PARSE("AlignAfterOpenBracket: DontAlign", AlignAfterOpenBracket, false); + // For backward compatibility: CHECK_PARSE("AlignAfterOpenBracket: AlwaysBreak", AlignAfterOpenBracket, - FormatStyle::BAS_AlwaysBreak); + true); + CHECK_PARSE("AlignAfterOpenBracket: AlwaysBreak\n" + "BreakAfterOpenBracketIf: false", + BreakAfterOpenBracketIf, false); + CHECK_PARSE("BreakAfterOpenBracketLoop: true\n" + "AlignAfterOpenBracket: AlwaysBreak", + BreakAfterOpenBracketLoop, true); + CHECK_PARSE("AlignAfterOpenBracket: false", AlignAfterOpenBracket, false); CHECK_PARSE("AlignAfterOpenBracket: BlockIndent", AlignAfterOpenBracket, - FormatStyle::BAS_BlockIndent); - // For backward compatibility: - CHECK_PARSE("AlignAfterOpenBracket: false", AlignAfterOpenBracket, - FormatStyle::BAS_DontAlign); - CHECK_PARSE("AlignAfterOpenBracket: true", AlignAfterOpenBracket, - FormatStyle::BAS_Align); + true); + Style.AlignAfterOpenBracket = false; + CHECK_PARSE("AlignAfterOpenBracket: true", AlignAfterOpenBracket, true); Style.AlignEscapedNewlines = FormatStyle::ENAS_Left; CHECK_PARSE("AlignEscapedNewlines: DontAlign", AlignEscapedNewlines, diff --git a/clang/unittests/Format/FormatTest.cpp b/clang/unittests/Format/FormatTest.cpp index d45babe..ca9e792 100644 --- a/clang/unittests/Format/FormatTest.cpp +++ b/clang/unittests/Format/FormatTest.cpp @@ -5126,7 +5126,8 @@ TEST_F(FormatTest, DesignatedInitializers) { TEST_F(FormatTest, BracedInitializerIndentWidth) { auto Style = getLLVMStyleWithColumns(60); Style.BinPackArguments = true; - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakAfterOpenBracketBracedList = true; Style.BracedInitializerIndentWidth = 6; // Non-initializing braces are unaffected by BracedInitializerIndentWidth. @@ -5302,7 +5303,8 @@ TEST_F(FormatTest, BracedInitializerIndentWidth) { Style); // Aligning after open braces unaffected by BracedInitializerIndentWidth. - Style.AlignAfterOpenBracket = FormatStyle::BAS_Align; + Style.AlignAfterOpenBracket = true; + Style.BreakAfterOpenBracketBracedList = false; verifyFormat("SomeStruct s{\"xxxxxxxxxxxxx\", \"yyyyyyyyyyyyy\",\n" " \"zzzzzzzzzzzzz\"};", Style); @@ -7459,7 +7461,7 @@ TEST_F(FormatTest, ExpressionIndentationBreakingBeforeOperators) { Style.IndentWidth = 4; Style.TabWidth = 4; Style.UseTab = FormatStyle::UT_Always; - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; Style.AlignOperands = FormatStyle::OAS_DontAlign; verifyFormat("return someVeryVeryLongConditionThatBarelyFitsOnALine\n" "\t&& (someOtherLongishConditionPart1\n" @@ -7470,7 +7472,7 @@ TEST_F(FormatTest, ExpressionIndentationBreakingBeforeOperators) { Style); Style = getLLVMStyleWithColumns(20); - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; Style.BinPackParameters = FormatStyle::BPPS_OnePerLine; Style.BreakBeforeBinaryOperators = FormatStyle::BOS_NonAssignment; Style.ContinuationIndentWidth = 2; @@ -7632,7 +7634,7 @@ TEST_F(FormatTest, NoOperandAlignment) { " * cccccccccccccccccccccccccccccccccccc;", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; verifyFormat("return (a > b\n" " // comment1\n" " // comment2\n" @@ -11248,7 +11250,7 @@ TEST_F(FormatTest, BreakBeforeTemplateCloser) { TEST_F(FormatTest, WrapsTemplateParameters) { FormatStyle Style = getLLVMStyle(); - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; Style.BreakBeforeBinaryOperators = FormatStyle::BOS_None; verifyFormat( "template <typename... a> struct q {};\n" @@ -11256,7 +11258,7 @@ TEST_F(FormatTest, WrapsTemplateParameters) { " aaaaaaaaaaaaaaaaa, aaaaaaaaaaaaaaaaa, aaaaaaaaaaaaaaaaa>\n" " y;", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_DontAlign; + Style.AlignAfterOpenBracket = false; Style.BreakBeforeBinaryOperators = FormatStyle::BOS_All; verifyFormat( "template <typename... a> struct r {};\n" @@ -11264,7 +11266,7 @@ TEST_F(FormatTest, WrapsTemplateParameters) { " aaaaaaaaaaaaaaaaa, aaaaaaaaaaaaaaaaa, aaaaaaaaaaaaaaaaa>\n" " y;", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; Style.BreakBeforeBinaryOperators = FormatStyle::BOS_None; verifyFormat("template <typename... a> struct s {};\n" "extern s<\n" @@ -11274,7 +11276,7 @@ TEST_F(FormatTest, WrapsTemplateParameters) { "aaaaaaaaaaaaaaaaaaaaaa>\n" " y;", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; Style.BreakBeforeBinaryOperators = FormatStyle::BOS_All; verifyFormat("template <typename... a> struct t {};\n" "extern t<\n" @@ -14302,7 +14304,7 @@ TEST_F(FormatTest, LayoutCxx11BraceInitializers) { "};", NoBinPacking); - NoBinPacking.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + NoBinPacking.BreakAfterOpenBracketBracedList = true; verifyFormat("static uint8 CddDp83848Reg[] = {\n" " CDDDP83848_BMCR_REGISTER,\n" " CDDDP83848_BMSR_REGISTER,\n" @@ -15972,13 +15974,14 @@ TEST_F(FormatTest, BreaksStringLiteralOperands) { // In a function call with two operands, with AlignAfterOpenBracket enabled, // the first must be broken with a line break before it. FormatStyle Style = getLLVMStyleWithColumns(25); - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; verifyFormat("someFunction(\n" " \"long long long \"\n" " \"long\",\n" " a);", "someFunction(\"long long long long\", a);", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Style.BreakAfterOpenBracketFunction = true; + Style.BreakBeforeCloseBracketFunction = true; verifyFormat("someFunction(\n" " \"long long long \"\n" " \"long\",\n" @@ -17773,7 +17776,7 @@ TEST_F(FormatTest, ConfigurableSpacesInParens) { Spaces.ColumnLimit = 80; Spaces.IndentWidth = 4; - Spaces.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Spaces.BreakAfterOpenBracketFunction = true; verifyFormat("void foo( ) {\n" " size_t foo = (*(function))(\n" " Foooo, Barrrrr, Foooo, Barrrr, FoooooooooLooooong, " @@ -17798,7 +17801,8 @@ TEST_F(FormatTest, ConfigurableSpacesInParens) { "}", Spaces); - Spaces.AlignAfterOpenBracket = FormatStyle::BAS_BlockIndent; + Spaces.BreakAfterOpenBracketFunction = true; + Spaces.BreakBeforeCloseBracketFunction = true; verifyFormat("void foo( ) {\n" " size_t foo = (*(function))(\n" " Foooo, Barrrrr, Foooo, Barrrr, FoooooooooLooooong, " @@ -22827,7 +22831,7 @@ TEST_F(FormatTest, ConstructorInitializerIndentWidth) { ": aaaaaaaaaaaaa(aaaaaaaaaaaaaa), aaaaaaaaaaaaa(aaaaaaaaaaaaaa),\n" " aaaaaaaaaaaaa(aaaaaaaaaaaaaa) {}", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; verifyFormat( "SomeLongTemplateVariableName<\n" " aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa, aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa>", @@ -24082,7 +24086,7 @@ TEST_F(FormatTest, FormatsLambdas) { " return aFunkyFunctionCall(qux);\n" " }} {}", Style); - Style.AlignAfterOpenBracket = FormatStyle::BAS_AlwaysBreak; + Style.BreakAfterOpenBracketFunction = true; // FIXME: The following test should pass, but fails at the time of writing. #if 0 // As long as all the non-lambda arguments fit on a single line, AlwaysBreak diff --git a/clang/unittests/Format/FormatTestJS.cpp b/clang/unittests/Format/FormatTestJS.cpp index 91577b9a..4847151 100644 --- a/clang/unittests/Format/FormatTestJS.cpp +++ b/clang/unittests/Format/FormatTestJS.cpp @@ -2883,7 +2883,7 @@ TEST_F(FormatTestJS, DontBreakFieldsAsGoToLabels) { TEST_F(FormatTestJS, BreakAfterOpenBracket) { auto Style = getGoogleStyle(FormatStyle::LK_JavaScript); - EXPECT_EQ(Style.AlignAfterOpenBracket, FormatStyle::BAS_AlwaysBreak); + EXPECT_EQ(Style.BreakAfterOpenBracketFunction, true); verifyFormat("ctrl.onCopy(/** @type {!WizEvent}*/ (\n" " {event, targetElement: {el: () => selectedElement}}));", Style); diff --git a/clang/www/cxx_dr_status.html b/clang/www/cxx_dr_status.html index b7da22c..0312c9d 100755 --- a/clang/www/cxx_dr_status.html +++ b/clang/www/cxx_dr_status.html @@ -81,7 +81,7 @@ <td><a href="https://cplusplus.github.io/CWG/issues/6.html">6</a></td> <td>NAD</td> <td>Should the optimization that allows a class object to alias another object also allow the case of a parameter in an inline function to alias its argument?</td> - <td class="unknown" align="center">Unknown</td> + <td class="full" align="center">Yes</td> </tr> <tr id="7"> <td><a href="https://cplusplus.github.io/CWG/issues/7.html">7</a></td> @@ -1318,7 +1318,7 @@ accessible?</td> <td><a href="https://cplusplus.github.io/CWG/issues/212.html">212</a></td> <td>CD4</td> <td>Implicit instantiation is not described clearly enough</td> - <td class="unknown" align="center">Unknown</td> + <td class="full" align="center">Yes</td> </tr> <tr id="213"> <td><a href="https://cplusplus.github.io/CWG/issues/213.html">213</a></td> @@ -1438,7 +1438,7 @@ accessible?</td> <td><a href="https://cplusplus.github.io/CWG/issues/232.html">232</a></td> <td>NAD</td> <td>Is indirection through a null pointer undefined behavior?</td> - <td class="unknown" align="center">Unknown</td> + <td class="none" align="center">Duplicate of <a href="#2823">2823</a></td> </tr> <tr id="233"> <td><a href="https://cplusplus.github.io/CWG/issues/233.html">233</a></td> @@ -3113,11 +3113,11 @@ of class templates</td> <td>Default initialization of POD classes?</td> <td class="na" align="center">N/A</td> </tr> - <tr class="open" id="511"> + <tr id="511"> <td><a href="https://cplusplus.github.io/CWG/issues/511.html">511</a></td> - <td>open</td> + <td>NAD</td> <td>POD-structs with template assignment operators</td> - <td align="center">Not resolved</td> + <td class="unknown" align="center">Unknown</td> </tr> <tr id="512"> <td><a href="https://cplusplus.github.io/CWG/issues/512.html">512</a></td> @@ -10895,7 +10895,7 @@ and <I>POD class</I></td> </tr> <tr class="open" id="1845"> <td><a href="https://cplusplus.github.io/CWG/issues/1845.html">1845</a></td> - <td>drafting</td> + <td>review</td> <td>Point of instantiation of a variable template specialization</td> <td align="center">Not resolved</td> </tr> @@ -12081,7 +12081,7 @@ and <I>POD class</I></td> </tr> <tr class="open" id="2042"> <td><a href="https://cplusplus.github.io/CWG/issues/2042.html">2042</a></td> - <td>drafting</td> + <td>review</td> <td>Exceptions and deallocation functions</td> <td align="center">Not resolved</td> </tr> @@ -12335,7 +12335,7 @@ and <I>POD class</I></td> <td><a href="https://cplusplus.github.io/CWG/issues/2084.html">2084</a></td> <td>CD4</td> <td>NSDMIs and deleted union default constructors</td> - <td class="unknown" align="center">Unknown</td> + <td class="full" align="center">Clang 3.1</td> </tr> <tr id="2085"> <td><a href="https://cplusplus.github.io/CWG/issues/2085.html">2085</a></td> @@ -12837,7 +12837,7 @@ and <I>POD class</I></td> </tr> <tr class="open" id="2168"> <td><a href="https://cplusplus.github.io/CWG/issues/2168.html">2168</a></td> - <td>open</td> + <td>review</td> <td>Narrowing conversions and +/- infinity</td> <td align="center">Not resolved</td> </tr> @@ -14237,11 +14237,11 @@ and <I>POD class</I></td> <td>Constexpr virtual functions and temporary objects</td> <td class="unknown" align="center">Unknown</td> </tr> - <tr class="open" id="2401"> + <tr id="2401"> <td><a href="https://cplusplus.github.io/CWG/issues/2401.html">2401</a></td> - <td>drafting</td> + <td>C++20</td> <td>Array decay vs prohibition of subobject non-type arguments</td> - <td align="center">Not resolved</td> + <td class="unknown" align="center">Unknown</td> </tr> <tr id="2402"> <td><a href="https://cplusplus.github.io/CWG/issues/2402.html">2402</a></td> @@ -15171,7 +15171,7 @@ and <I>POD class</I></td> </tr> <tr class="open" id="2555"> <td><a href="https://cplusplus.github.io/CWG/issues/2555.html">2555</a></td> - <td>drafting</td> + <td>tentatively ready</td> <td>Ineffective redeclaration prevention for <I>using-declarator</I>s</td> <td align="center">Not resolved</td> </tr> @@ -15311,23 +15311,23 @@ and <I>POD class</I></td> <td>Undefined behavior for preprocessing directives in macro arguments</td> <td align="center">Not resolved</td> </tr> - <tr class="open" id="2578"> + <tr id="2578"> <td><a href="https://cplusplus.github.io/CWG/issues/2578.html">2578</a></td> - <td>open</td> + <td>CD7</td> <td>Undefined behavior when creating an invalid string literal via stringizing</td> - <td align="center">Not resolved</td> + <td class="unknown" align="center">Unknown</td> </tr> - <tr class="open" id="2579"> + <tr id="2579"> <td><a href="https://cplusplus.github.io/CWG/issues/2579.html">2579</a></td> - <td>open</td> + <td>CD7</td> <td>Undefined behavior when token pasting does not create a preprocessing token</td> - <td align="center">Not resolved</td> + <td class="unknown" align="center">Unknown</td> </tr> - <tr class="open" id="2580"> + <tr id="2580"> <td><a href="https://cplusplus.github.io/CWG/issues/2580.html">2580</a></td> - <td>open</td> + <td>CD7</td> <td>Undefined behavior with <TT>#line</TT></td> - <td align="center">Not resolved</td> + <td class="unknown" align="center">Unknown</td> </tr> <tr class="open" id="2581"> <td><a href="https://cplusplus.github.io/CWG/issues/2581.html">2581</a></td> @@ -16790,7 +16790,7 @@ objects</td> <td><a href="https://cplusplus.github.io/CWG/issues/2823.html">2823</a></td> <td>CD7</td> <td>Implicit undefined behavior when dereferencing pointers</td> - <td class="unknown" align="center">Unknown</td> + <td class="none" align="center">No</td> </tr> <tr id="2824"> <td><a href="https://cplusplus.github.io/CWG/issues/2824.html">2824</a></td> @@ -17104,7 +17104,7 @@ objects</td> </tr> <tr class="open" id="2875"> <td><a href="https://cplusplus.github.io/CWG/issues/2875.html">2875</a></td> - <td>review</td> + <td>tentatively ready</td> <td>Missing support for round-tripping null pointer values through indirection/address operators</td> <td align="center">Not resolved</td> </tr> @@ -17400,7 +17400,7 @@ objects</td> </tr> <tr class="open" id="2923"> <td><a href="https://cplusplus.github.io/CWG/issues/2923.html">2923</a></td> - <td>review</td> + <td>tentatively ready</td> <td>Note about infinite loops and execution steps</td> <td align="center">Not resolved</td> </tr> @@ -17760,7 +17760,7 @@ objects</td> </tr> <tr class="open" id="2983"> <td><a href="https://cplusplus.github.io/CWG/issues/2983.html">2983</a></td> - <td>open</td> + <td>review</td> <td>Non-type template parameters are not variables</td> <td align="center">Not resolved</td> </tr> @@ -17868,7 +17868,7 @@ objects</td> </tr> <tr class="open" id="3001"> <td><a href="https://cplusplus.github.io/CWG/issues/3001.html">3001</a></td> - <td>review</td> + <td>tentatively ready</td> <td>Inconsistent restrictions for <TT>static_cast</TT> on pointers to out-of-lifetime objects</td> <td align="center">Not resolved</td> </tr> @@ -17932,7 +17932,7 @@ objects</td> </tr> <tr class="open" id="3011"> <td><a href="https://cplusplus.github.io/CWG/issues/3011.html">3011</a></td> - <td>open</td> + <td>tentatively ready</td> <td>Parenthesized aggregate initialization for <I>new-expression</I>s</td> <td align="center">Not resolved</td> </tr> @@ -17992,7 +17992,7 @@ objects</td> </tr> <tr class="open" id="3021"> <td><a href="https://cplusplus.github.io/CWG/issues/3021.html">3021</a></td> - <td>open</td> + <td>drafting</td> <td>Subsumption rules for fold expanded constraints</td> <td align="center">Not resolved</td> </tr> @@ -18058,7 +18058,7 @@ objects</td> </tr> <tr class="open" id="3032"> <td><a href="https://cplusplus.github.io/CWG/issues/3032.html">3032</a></td> - <td>open</td> + <td>tentatively ready</td> <td>Template argument disambiguation</td> <td align="center">Not resolved</td> </tr> @@ -18184,7 +18184,7 @@ objects</td> </tr> <tr class="open" id="3053"> <td><a href="https://cplusplus.github.io/CWG/issues/3053.html">3053</a></td> - <td>open</td> + <td>tentatively ready</td> <td>Allowing <TT>#undef likely</TT></td> <td align="center">Not resolved</td> </tr> @@ -18265,6 +18265,210 @@ objects</td> <td>tentatively ready</td> <td>Declarative <I>nested-name-specifier</I> in explicit instantiation</td> <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3067"> + <td><a href="https://cplusplus.github.io/CWG/issues/3067.html">3067</a></td> + <td>open</td> + <td>Array-to-pointer conversion with object type mismatch</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3068"> + <td><a href="https://cplusplus.github.io/CWG/issues/3068.html">3068</a></td> + <td>open</td> + <td>Access checking in friends involving <I>qualified-id</I>s</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3069"> + <td><a href="https://cplusplus.github.io/CWG/issues/3069.html">3069</a></td> + <td>open</td> + <td>Reference to wrong placeholder</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3070"> + <td><a href="https://cplusplus.github.io/CWG/issues/3070.html">3070</a></td> + <td>open</td> + <td>Trivial assignment can skip member subobjects</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3071"> + <td><a href="https://cplusplus.github.io/CWG/issues/3071.html">3071</a></td> + <td>open</td> + <td>Negative <TT>tuple_size</TT> in structured bindings</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3072"> + <td><a href="https://cplusplus.github.io/CWG/issues/3072.html">3072</a></td> + <td>open</td> + <td>Incorrect examples for lambda SFINAE</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3073"> + <td><a href="https://cplusplus.github.io/CWG/issues/3073.html">3073</a></td> + <td>open</td> + <td>Dependence of <I>R</I> on <TT>T2</TT> is unclear</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3074"> + <td><a href="https://cplusplus.github.io/CWG/issues/3074.html">3074</a></td> + <td>tentatively ready</td> + <td>Redundant ill-formedness for module macros</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3075"> + <td><a href="https://cplusplus.github.io/CWG/issues/3075.html">3075</a></td> + <td>tentatively ready</td> + <td>Unclear matching of import directive</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3076"> + <td><a href="https://cplusplus.github.io/CWG/issues/3076.html">3076</a></td> + <td>tentatively ready</td> + <td>Remove unnecessary IFNDR for malformed <I>header-name-token</I>s</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3077"> + <td><a href="https://cplusplus.github.io/CWG/issues/3077.html">3077</a></td> + <td>tentatively ready</td> + <td>Undesirable formation of <TT>import</TT> directive with <I>string-literal</I></td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3078"> + <td><a href="https://cplusplus.github.io/CWG/issues/3078.html">3078</a></td> + <td>review</td> + <td>Different treatment of <TT>#include</TT> <I>pp-tokens</I> and <I>header-name-tokens</I></td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3079"> + <td><a href="https://cplusplus.github.io/CWG/issues/3079.html">3079</a></td> + <td>open</td> + <td>Allow <I>empty-declaration</I>s in anonymous unions</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3080"> + <td><a href="https://cplusplus.github.io/CWG/issues/3080.html">3080</a></td> + <td>tentatively ready</td> + <td>Clarify kinds of permitted template template arguments</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3081"> + <td><a href="https://cplusplus.github.io/CWG/issues/3081.html">3081</a></td> + <td>review</td> + <td>Require glvalue when splicing direct base class relationship</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3082"> + <td><a href="https://cplusplus.github.io/CWG/issues/3082.html">3082</a></td> + <td>tentatively ready</td> + <td>Allow for call-compatible function types in <TT>reinterpret_cast</TT></td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3083"> + <td><a href="https://cplusplus.github.io/CWG/issues/3083.html">3083</a></td> + <td>tentatively ready</td> + <td>Remove redundant restrictions on class and enum definitions</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3084"> + <td><a href="https://cplusplus.github.io/CWG/issues/3084.html">3084</a></td> + <td>tentatively ready</td> + <td><I>compound-statement</I>s inside <I>iteration-statement</I>s</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3085"> + <td><a href="https://cplusplus.github.io/CWG/issues/3085.html">3085</a></td> + <td>tentatively ready</td> + <td>Apply restriction inside for-range-declaration</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3086"> + <td><a href="https://cplusplus.github.io/CWG/issues/3086.html">3086</a></td> + <td>tentatively ready</td> + <td>Destringizing should consider all sorts of encoding-prefixes</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3087"> + <td><a href="https://cplusplus.github.io/CWG/issues/3087.html">3087</a></td> + <td>open</td> + <td>Destringizing for raw string literals</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3088"> + <td><a href="https://cplusplus.github.io/CWG/issues/3088.html">3088</a></td> + <td>open</td> + <td>Clarify macro treatment of identifiers with special meaning</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3089"> + <td><a href="https://cplusplus.github.io/CWG/issues/3089.html">3089</a></td> + <td>tentatively ready</td> + <td>const-default-constructible improperly handles std::meta::info</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3090"> + <td><a href="https://cplusplus.github.io/CWG/issues/3090.html">3090</a></td> + <td>tentatively ready</td> + <td>Internal linkage from header units</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3091"> + <td><a href="https://cplusplus.github.io/CWG/issues/3091.html">3091</a></td> + <td>review</td> + <td>Linking of translation units as sequences of tokens</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3092"> + <td><a href="https://cplusplus.github.io/CWG/issues/3092.html">3092</a></td> + <td>tentatively ready</td> + <td><I>base-specifier</I>s are not "declared"</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3093"> + <td><a href="https://cplusplus.github.io/CWG/issues/3093.html">3093</a></td> + <td>open</td> + <td>Missing integration of direct base class relationships</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3094"> + <td><a href="https://cplusplus.github.io/CWG/issues/3094.html">3094</a></td> + <td>review</td> + <td>Rework phases for string literal concatenation and token formation</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3095"> + <td><a href="https://cplusplus.github.io/CWG/issues/3095.html">3095</a></td> + <td>open</td> + <td>Type-dependent packs that are not structured binding packs</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3096"> + <td><a href="https://cplusplus.github.io/CWG/issues/3096.html">3096</a></td> + <td>open</td> + <td>Value-dependence of size of structured binding pack with non-dependent initializer</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3097"> + <td><a href="https://cplusplus.github.io/CWG/issues/3097.html">3097</a></td> + <td>tentatively ready</td> + <td>Lambda expression introduces a scope</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3098"> + <td><a href="https://cplusplus.github.io/CWG/issues/3098.html">3098</a></td> + <td>tentatively ready</td> + <td>Remove redundancy "names or designates"</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3099"> + <td><a href="https://cplusplus.github.io/CWG/issues/3099.html">3099</a></td> + <td>open</td> + <td>Instantiation of type aliases from alias templates is unspecified</td> + <td align="center">Not resolved</td> + </tr> + <tr class="open" id="3100"> + <td><a href="https://cplusplus.github.io/CWG/issues/3100.html">3100</a></td> + <td>open</td> + <td>Destruction order for objects with static storage duration</td> + <td align="center">Not resolved</td> </tr></table> </div> |