| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
implementation
... by using the existing 'goacc_asyncqueue' instead of re-coding parts of it.
Follow-up to commit 131d18e928a3ea1ab2d3bf61aa92d68a8a254609
"libgomp/nvptx: Prepare for reverse-offload callback handling",
and commit ea4b23d9c82d9be3b982c3519fe5e8e9d833a6a8
"libgomp: Handle OpenMP's reverse offloads".
libgomp/
* target.c (gomp_target_rev): Instead of 'dev_to_host_cpy',
'host_to_dev_cpy', 'token', take a single 'goacc_asyncqueue'.
* libgomp.h (gomp_target_rev): Adjust.
* libgomp-plugin.c (GOMP_PLUGIN_target_rev): Adjust.
* libgomp-plugin.h (GOMP_PLUGIN_target_rev): Adjust.
* plugin/plugin-gcn.c (process_reverse_offload): Adjust.
* plugin/plugin-nvptx.c (rev_off_dev_to_host_cpy)
(rev_off_host_to_dev_cpy): Remove.
(GOMP_OFFLOAD_run): Adjust.
|
|
Thereby considerably simplify the device plugins' 'GOMP_OFFLOAD_openacc_exec',
'GOMP_OFFLOAD_openacc_async_exec' functions: in terms of lines of code, but in
particular conceptually: no more device memory allocation, host to device data
copying, device memory deallocation -- 'GOMP_MAP_VARS_TARGET' does all that for
us.
This depends on commit 2b2340e236c0bba8aaca358ea25a5accd8249fbd
"Allow libgomp 'cbuf' buffering with OpenACC 'async' for 'ephemeral' data",
where I said that "a use will emerge later", which is this one here.
PR libgomp/90596
libgomp/
* target.c (gomp_map_vars_internal): Allow for
'param_kind == GOMP_MAP_VARS_OPENACC | GOMP_MAP_VARS_TARGET'.
* oacc-parallel.c (GOACC_parallel_keyed): Pass
'GOMP_MAP_VARS_TARGET' to 'goacc_map_vars'.
* plugin/plugin-gcn.c (alloc_by_agent, gcn_exec)
(GOMP_OFFLOAD_openacc_exec, GOMP_OFFLOAD_openacc_async_exec):
Adjust, simplify.
(gomp_offload_free): Remove.
* plugin/plugin-nvptx.c (nvptx_exec, GOMP_OFFLOAD_openacc_exec)
(GOMP_OFFLOAD_openacc_async_exec): Adjust, simplify.
(cuda_free_argmem): Remove.
* testsuite/libgomp.oacc-c-c++-common/acc_prof-parallel-1.c:
Adjust.
|
|
For 'OFFSET_INLINED', 'gomp_map_val' does the right thing, and we may then
simplify the device plugins accordingly.
This is a follow-up to
Subversion r279551 (Git commit a6163563f2ce502bd4ef444bd5de33570bb8eeb1)
"Add OpenACC 2.6's no_create",
Subversion r279622 (Git commit 5bcd470bf0749e1f56d05dd43aa9584ff2e3a090)
"Use gomp_map_val for OpenACC host-to-device address translation".
libgomp/
* target.c (gomp_map_vars_internal): Use 'OFFSET_INLINED' for
'GOMP_MAP_IF_PRESENT'.
* plugin/plugin-gcn.c (gcn_exec, GOMP_OFFLOAD_openacc_exec)
(GOMP_OFFLOAD_openacc_async_exec): Adjust.
* plugin/plugin-nvptx.c (nvptx_exec, GOMP_OFFLOAD_openacc_exec)
(GOMP_OFFLOAD_openacc_async_exec): Likewise.
* testsuite/libgomp.oacc-c-c++-common/no_create-1.c: Add 'async'
testing.
* testsuite/libgomp.oacc-c-c++-common/no_create-2.c: Likewise.
|
|
|
|
This commit enabled reverse offload for nvptx such that gomp_target_rev
actually gets called. And it fills the latter function to do all of
the following: finding the host function to the device func ptr and
copying the arguments to the host, processing the mapping/firstprivate,
calling the host function, copying back the data and freeing as needed.
The data handling is made easier by assuming that all host variables
either existed before (and are in the mapping) or that those are
devices variables not yet available on the host. Thus, the reverse
mapping can do without refcounts etc. Note that the spec disallows
inside a target region device-affecting constructs other than target
plus ancestor device-modifier and it also limits the clauses permitted
on this construct.
For the function addresses, an additional splay tree is used; for
the lookup of mapped variables, the existing splay-tree is used.
Unfortunately, its data structure requires a full walk of the tree;
Additionally, the just mapped variables are recorded in a separate
data structure an extra lookup. While the lookup is slow, assuming
that only few variables get mapped in each reverse offload construct
and that reverse offload is the exception and not performance critical,
this seems to be acceptable.
libgomp/ChangeLog:
* libgomp.h (struct target_mem_desc): Predeclare; move
below after 'reverse_splay_tree_node' and add rev_array
member.
(struct reverse_splay_tree_key_s, reverse_splay_compare): New.
(reverse_splay_tree_node, reverse_splay_tree,
reverse_splay_tree_key): New typedef.
(struct gomp_device_descr): Add mem_map_rev member.
* oacc-host.c (host_dispatch): NULL init .mem_map_rev.
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_get_num_devices): Claim
support for GOMP_REQUIRES_REVERSE_OFFLOAD.
* splay-tree.h (splay_tree_callback_stop): New typedef; like
splay_tree_callback but returning int not void.
(splay_tree_foreach_lazy): Define; like splay_tree_foreach but
taking splay_tree_callback_stop as argument.
* splay-tree.c (splay_tree_foreach_internal_lazy,
splay_tree_foreach_lazy): New; but early exit if callback returns
nonzero.
* target.c: Instatiate splay_tree_c with splay_tree_prefix 'reverse'.
(gomp_map_lookup_rev): New.
(gomp_load_image_to_device): Handle reverse-offload function
lookup table.
(gomp_unload_image_from_device): Free devicep->mem_map_rev.
(struct gomp_splay_tree_rev_lookup_data, gomp_splay_tree_rev_lookup,
gomp_map_rev_lookup, struct cpy_data, gomp_map_cdata_lookup_int,
gomp_map_cdata_lookup): New auxiliary structs and functions for
gomp_target_rev.
(gomp_target_rev): Implement reverse offloading and its mapping.
(gomp_target_init): Init current_device.mem_map_rev.root.
* testsuite/libgomp.fortran/reverse-offload-2.f90: New test.
* testsuite/libgomp.fortran/reverse-offload-3.f90: New test.
* testsuite/libgomp.fortran/reverse-offload-4.f90: New test.
* testsuite/libgomp.fortran/reverse-offload-5.f90: New test.
* testsuite/libgomp.fortran/reverse-offload-5a.f90: New test without
mapping of on-device allocated variables.
|
|
OpenMP permits that a 'target device(ancestor:1)' is called without being
enclosed in a target region - using the current device (i.e. the host) in
that case. This commit adds a testcase for this.
In case of nvptx, the missing on-device 'GOMP_target_ext' call causes that
it and also the associated on-device GOMP_REV_OFFLOAD_VAR variable are not
linked in from nvptx's libgomp.a. Thus, handle the failing cuModuleGetGlobal
gracefully by disabling reverse offload and assuming that the failure is fine.
libgomp/ChangeLog:
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_load_image): Use unsigned int
for 'i' to match 'fn_entries'; regard absent GOMP_REV_OFFLOAD_VAR
as valid and the code having no reverse-offload code.
* testsuite/libgomp.c-c++-common/reverse-offload-2.c: New test.
|
|
spurious SIGSEGVs
Per commit r13-3460-g131d18e928a3ea1ab2d3bf61aa92d68a8a254609
"libgomp/nvptx: Prepare for reverse-offload callback handling",
I'm seeing a lot of libgomp execution test regressions. Random
example, 'libgomp.c-c++-common/error-1.c':
[...]
GOMP_OFFLOAD_run: kernel main$_omp_fn$0: launch [(teams: 1), 1, 1] [(lanes: 32), (threads: 8), 1]
Thread 1 "a.out" received signal SIGSEGV, Segmentation fault.
0x00007ffff793b87d in GOMP_OFFLOAD_run (ord=<optimized out>, tgt_fn=<optimized out>, tgt_vars=<optimized out>, args=<optimized out>) at [...]/source-gcc/libgomp/plugin/plugin-nvptx.c:2127
2127 if (__atomic_load_n (&ptx_dev->rev_data->fn, __ATOMIC_ACQUIRE) != 0)
(gdb) print ptx_dev
$1 = (struct ptx_device *) 0x6a55a0
(gdb) print ptx_dev->rev_data
$2 = (struct rev_offload *) 0xffffffff00000000
(gdb) print ptx_dev->rev_data->fn
Cannot access memory at address 0xffffffff00000000
libgomp/
* plugin/plugin-nvptx.c (nvptx_open_device): Initialize
'ptx_dev->rev_data'.
|
|
This patch adds a stub 'gomp_target_rev' in the host's target.c, which will
later handle the reverse offload.
For nvptx, it adds support for forwarding the offload gomp_target_ext call
to the host by setting values in a struct on the device and querying it on
the host - invoking gomp_target_rev on the result.
include/ChangeLog:
* cuda/cuda.h (enum CUdevice_attribute): Add
CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING.
(CU_MEMHOSTALLOC_DEVICEMAP): Define.
(cuMemHostAlloc): Add prototype.
libgomp/ChangeLog:
* config/nvptx/icv-device.c (GOMP_DEVICE_NUM_VAR): Remove
'static' for this variable.
* config/nvptx/libgomp-nvptx.h: New file.
* config/nvptx/target.c: Include it.
(GOMP_ADDITIONAL_ICVS): Declare extern var.
(GOMP_REV_OFFLOAD_VAR): Declare var.
(GOMP_target_ext): Handle reverse offload.
* libgomp-plugin.h (GOMP_PLUGIN_target_rev): New prototype.
* libgomp-plugin.c (GOMP_PLUGIN_target_rev): New, call ...
* target.c (gomp_target_rev): ... this new stub function.
* libgomp.h (gomp_target_rev): Declare.
* libgomp.map (GOMP_PLUGIN_1.4): New; add GOMP_PLUGIN_target_rev.
* plugin/cuda-lib.def (cuMemHostAlloc): Add.
* plugin/plugin-nvptx.c: Include libgomp-nvptx.h.
(struct ptx_device): Add rev_data member.
(nvptx_open_device): Remove async_engines query, last used in
r10-304-g1f4c5b9b; add unified-address assert check.
(GOMP_OFFLOAD_get_num_devices): Claim unified address
support.
(GOMP_OFFLOAD_load_image): Free rev_fn_table if no
offload functions exist. Make offload var available
on host and device.
(rev_off_dev_to_host_cpy, rev_off_host_to_dev_cpy): New.
(GOMP_OFFLOAD_run): Handle reverse offload.
|
|
Add support to nvptx for reverse lookup of function name to prepare for
'omp target device(ancestor:1)'.
gcc/ChangeLog:
* config/nvptx/mkoffload.cc (struct id_map): Add 'dim' member.
(record_id): Store func name without quotes, store dim separately.
(process): For GOMP_REQUIRES_REVERSE_OFFLOAD, check that -march is
at least sm_35, create '$offload_func_table' global array and init
with reverse-offload function addresses.
* config/nvptx/nvptx.cc (write_fn_proto_1, write_fn_proto): New
force_public attribute to force .visible.
(nvptx_declare_function_name): For "omp target
device_ancestor_nohost" attribut, force .visible/TREE_PUBLIC.
libgomp/ChangeLog:
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_load_image): Read offload
function address table '$offload_func_table' if rev_fn_table
is not NULL.
|
|
Prepare for reverse-offloading function-pointer lookup by passing
a rev_fn_table argument to GOMP_OFFLOAD_load_image.
The argument will be NULL, unless GOMP_REQUIRES_REVERSE_OFFLOAD is
requested and devices not supported it, are filtered out.
(Up to and including this commit, no non-host device claims such
support and the caller currently always passes NULL.)
libgomp/ChangeLog:
* libgomp-plugin.h (GOMP_OFFLOAD_load_image): Add
'uint64_t **rev_fn_table' argument.
* oacc-host.c (host_load_image): Likewise.
* plugin/plugin-gcn.c (GOMP_OFFLOAD_load_image): Likewise;
currently unused.
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_load_image): Likewise.
* target.c (gomp_load_image_to_device): Update call but pass
NULL for now.
liboffloadmic/ChangeLog:
* plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_load_image):
Add (unused) uint64_t **rev_fn_table argument.
|
|
This patch considers the environment variable syntax extension for
device-specific variants of environment variables from OpenMP 5.1 (see
OpenMP 5.1 specification, p. 75 and p. 639). An environment variable (e.g.
OMP_NUM_TEAMS) can have different suffixes:
_DEV (e.g. OMP_NUM_TEAMS_DEV): affects all devices but not the host.
_DEV_<device> (e.g. OMP_NUM_TEAMS_DEV_42): affects only device with
number <device>.
no suffix (e.g. OMP_NUM_TEAMS): affects only the host.
In future OpenMP versions also suffix _ALL will be introduced (see discussion
https://github.com/OpenMP/spec/issues/3179). This is also considered in this
patch:
_ALL (e.g. OMP_NUM_TEAMS_ALL): affects all devices and the host.
The precedence is as follows (descending). For the host:
1. no suffix
2. _ALL
For devices:
1. _DEV_<device>
2. _DEV
3. _ALL
That means, _DEV_<device> is used whenever available. Otherwise _DEV is used if
available, and at last _ALL. If there is no value for any of the variable
variants, default values are used as already implemented before.
This patch concerns parsing (a), storing (b), output (c) and transmission to the
device (d):
(a) The actual number of devices and the numbering are not known when parsing
the environment variables. Thus all environment variables are iterated and
searched for device-specific ones.
(b) Only configured device-specific variables are stored. Thus, a linked list
is used.
(c) The output is done in omp_display_env (see specification p. 468f). Global
ICVs are tagged with [all], see https://github.com/OpenMP/spec/issues/3179.
ICVs which are not global but aren't handled device-specific yet are tagged
with [host]. omp_display_env outputs the initial values of the ICVs. That is
why a dedicated data structure is introduced for the inital values only
(gomp_initial_icv_list).
(d) Device-specific ICVs are transmitted to the device via GOMP_ADDITIONAL_ICVS.
libgomp/ChangeLog:
* config/gcn/icv-device.c (omp_get_default_device): Return device-
specific ICV.
(omp_get_max_teams): Added for GCN devices.
(omp_set_num_teams): Likewise.
(ialias): Likewise.
* config/nvptx/icv-device.c (omp_get_default_device): Return device-
specific ICV.
(omp_get_max_teams): Added for NVPTX devices.
(omp_set_num_teams): Likewise.
(ialias): Likewise.
* env.c (struct gomp_icv_list): New struct to store entries of initial
ICV values.
(struct gomp_offload_icv_list): New struct to store entries of device-
specific ICV values that are copied to the device and back.
(struct gomp_default_icv_values): New struct to store default values of
ICVs according to the OpenMP standard.
(parse_schedule): Generalized for different variants of OMP_SCHEDULE.
(print_env_var_error): Function that prints an error for invalid values
for ICVs.
(parse_unsigned_long_1): Removed getenv. Generalized.
(parse_unsigned_long): Likewise.
(parse_int_1): Likewise.
(parse_int): Likewise.
(parse_int_secure): Likewise.
(parse_unsigned_long_list): Likewise.
(parse_target_offload): Likewise.
(parse_bind_var): Likewise.
(parse_stacksize): Likewise.
(parse_boolean): Likewise.
(parse_wait_policy): Likewise.
(parse_allocator): Likewise.
(omp_display_env): Extended to output different variants of environment
variables.
(print_schedule): New helper function for omp_display_env which prints
the values of run_sched_var.
(print_proc_bind): New helper function for omp_display_env which prints
the values of proc_bind_var.
(enum gomp_parse_type): Collection of types used for parsing environment
variables.
(ENTRY): Preprocess string lengths of environment variables.
(OMP_VAR_CNT): Preprocess table size.
(OMP_HOST_VAR_CNT): Likewise.
(INT_MAX_STR_LEN): Constant for the maximal number of digits of a device
number.
(gomp_get_icv_flag): Returns if a flag for a particular ICV is set.
(gomp_set_icv_flag): Sets a flag for a particular ICV.
(print_device_specific_icvs): New helper function for omp_display_env to
print device specific ICV values.
(get_device_num): New helper function for parse_device_specific.
Extracts the device number from an environment variable name.
(get_icv_member_addr): Gets the memory address for a particular member
of an ICV struct.
(gomp_get_initial_icv_item): Get a list item of gomp_initial_icv_list.
(initialize_icvs): New function to initialize a gomp_initial_icvs
struct.
(add_initial_icv_to_list): Adds an ICV struct to gomp_initial_icv_list.
(startswith): Checks if a string starts with a given prefix.
(initialize_env): Extended to parse the new syntax of environment
variables.
* icv-device.c (omp_get_max_teams): Added.
(ialias): Likewise.
(omp_set_num_teams): Likewise.
* icv.c (omp_set_num_teams): Moved to icv-device.c.
(omp_get_max_teams): Likewise.
(ialias): Likewise.
* libgomp-plugin.h (GOMP_DEVICE_NUM_VAR): Removed.
(GOMP_ADDITIONAL_ICVS): New target-side struct that
holds the designated ICVs of the target device.
* libgomp.h (enum gomp_icvs): Collection of ICVs.
(enum gomp_device_num): Definition of device numbers for _ALL, _DEV, and
no suffix.
(enum gomp_env_suffix): Collection of possible suffixes of environment
variables.
(struct gomp_initial_icvs): Contains all ICVs for which we need to store
initial values.
(struct gomp_default_icv):New struct to hold ICVs for which we need
to store initial values.
(struct gomp_icv_list): Definition of a linked list that is used for
storing ICVs for the devices and also for _DEV, _ALL, and without
suffix.
(struct gomp_offload_icvs): New struct to hold ICVs that are copied to
a device.
(struct gomp_offload_icv_list): Definition of a linked list that holds
device-specific ICVs that are copied to devices.
(gomp_get_initial_icv_item): Get a list item of gomp_initial_icv_list.
(gomp_get_icv_flag): Returns if a flag for a particular ICV is set.
* libgomp.texi: Updated.
* plugin/plugin-gcn.c (GOMP_OFFLOAD_load_image): Extended to read
further ICVs from the offload image.
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_load_image): Likewise.
* target.c (gomp_get_offload_icv_item): Get a list item of
gomp_offload_icv_list.
(get_gomp_offload_icvs): New. Returns the ICV values
depending on the device num and the variable hierarchy.
(gomp_load_image_to_device): Extended to copy further ICVs to a device.
* testsuite/libgomp.c-c++-common/icv-5.c: New test.
* testsuite/libgomp.c-c++-common/icv-6.c: New test.
* testsuite/libgomp.c-c++-common/icv-7.c: New test.
* testsuite/libgomp.c-c++-common/icv-8.c: New test.
* testsuite/libgomp.c-c++-common/omp-display-env-1.c: New test.
* testsuite/libgomp.c-c++-common/omp-display-env-2.c: New test.
|
|
Handle reverse_offload, unified_address, and unified_shared_memory
requirements in libgomp by saving them alongside the offload table.
When the device lto1 runs, it extracts the data for mkoffload. The
latter than passes the value on to GOMP_offload_register_ver.
lto1 (either the host one, with -flto [+ ENABLE_OFFLOADING], or in the
offload-device lto1) also does the the consistency check is done,
erroring out when the 'omp requires' clause use is inconsistent.
For all in-principle supported devices, if a requirement cannot be fulfilled,
the device is excluded from the (supported) devices list. Currently, none of
those requirements are marked as supported for any of the non-host devices.
gcc/c/ChangeLog:
* c-parser.cc (c_parser_omp_target_data, c_parser_omp_target_update,
c_parser_omp_target_enter_data, c_parser_omp_target_exit_data): Set
OMP_REQUIRES_TARGET_USED.
(c_parser_omp_requires): Remove sorry.
gcc/ChangeLog:
* config/gcn/mkoffload.cc (process_asm): Write '#include <stdint.h>'.
(process_obj): Pass omp_requires_mask to GOMP_offload_register_ver.
(main): Ask lto1 to obtain omp_requires_mask and pass it on.
* config/nvptx/mkoffload.cc (process, main): Likewise.
* lto-cgraph.cc (omp_requires_to_name): New.
(input_offload_tables): Save omp_requires_mask.
(output_offload_tables): Read it, check for consistency,
save value for mkoffload.
* omp-low.cc (lower_omp_target): Force output_offloadtables
call for OMP_REQUIRES_TARGET_USED.
gcc/cp/ChangeLog:
* parser.cc (cp_parser_omp_target_data,
cp_parser_omp_target_enter_data, cp_parser_omp_target_exit_data,
cp_parser_omp_target_update): Set OMP_REQUIRES_TARGET_USED.
(cp_parser_omp_requires): Remove sorry.
gcc/fortran/ChangeLog:
* openmp.cc (gfc_match_omp_requires): Remove sorry.
* parse.cc (decode_omp_directive): Don't regard 'declare target'
as target usage for 'omp requires'; add more flags to
omp_requires_mask.
include/ChangeLog:
* gomp-constants.h (GOMP_VERSION): Bump to 2.
(GOMP_REQUIRES_UNIFIED_ADDRESS, GOMP_REQUIRES_UNIFIED_SHARED_MEMORY,
GOMP_REQUIRES_REVERSE_OFFLOAD, GOMP_REQUIRES_TARGET_USED):
New defines.
libgomp/ChangeLog:
* libgomp-plugin.h (GOMP_OFFLOAD_get_num_devices): Add
omp_requires_mask arg.
* plugin/plugin-gcn.c (GOMP_OFFLOAD_get_num_devices): Likewise;
return -1 when device available but omp_requires_mask != 0.
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_get_num_devices): Likewise.
* oacc-host.c (host_get_num_devices, host_openacc_get_property):
Update call.
* oacc-init.c (resolve_device, acc_init_1, acc_shutdown_1,
goacc_attach_host_thread_to_device, acc_get_num_devices,
acc_set_device_num, get_property_any): Likewise.
* target.c (omp_requires_mask): New global var.
(gomp_requires_to_name): New.
(GOMP_offload_register_ver): Handle passed omp_requires_mask.
(gomp_target_init): Handle omp_requires_mask.
* libgomp.texi (OpenMP 5.0): Update requires impl. status.
(OpenMP 5.1): Add a missed item.
(OpenMP 5.2): Mark linear-clause change as supported in C/C++.
* testsuite/libgomp.c-c++-common/requires-1-aux.c: New test.
* testsuite/libgomp.c-c++-common/requires-1.c: New test.
* testsuite/libgomp.c-c++-common/requires-2-aux.c: New test.
* testsuite/libgomp.c-c++-common/requires-2.c: New test.
* testsuite/libgomp.c-c++-common/requires-3-aux.c: New test.
* testsuite/libgomp.c-c++-common/requires-3.c: New test.
* testsuite/libgomp.c-c++-common/requires-4-aux.c: New test.
* testsuite/libgomp.c-c++-common/requires-4.c: New test.
* testsuite/libgomp.c-c++-common/requires-5-aux.c: New test.
* testsuite/libgomp.c-c++-common/requires-5.c: New test.
* testsuite/libgomp.c-c++-common/requires-6.c: New test.
* testsuite/libgomp.c-c++-common/requires-7-aux.c: New test.
* testsuite/libgomp.c-c++-common/requires-7.c: New test.
* testsuite/libgomp.fortran/requires-1-aux.f90: New test.
* testsuite/libgomp.fortran/requires-1.f90: New test.
liboffloadmic/ChangeLog:
* plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_get_num_devices):
Return -1 when device available but omp_requires_mask != 0.
gcc/testsuite/ChangeLog:
* c-c++-common/gomp/requires-4.c: Update dg-*.
* c-c++-common/gomp/reverse-offload-1.c: Likewise.
* c-c++-common/gomp/target-device-ancestor-2.c: Likewise.
* c-c++-common/gomp/target-device-ancestor-3.c: Likewise.
* c-c++-common/gomp/target-device-ancestor-4.c: Likewise.
* c-c++-common/gomp/target-device-ancestor-5.c: Likewise.
* gfortran.dg/gomp/target-device-ancestor-3.f90: Likewise.
* gfortran.dg/gomp/target-device-ancestor-4.f90: Likewise.
* gfortran.dg/gomp/target-device-ancestor-5.f90: Likewise.
* gfortran.dg/gomp/target-device-ancestor-2.f90: Likewise. Move
post-FE checks to ...
* gfortran.dg/gomp/target-device-ancestor-2a.f90: ... this new file.
* gfortran.dg/gomp/requires-8.f90: Update as we don't regard
'declare target' for the 'requires' usage requirement.
Co-authored-by: Chung-Lin Tang <cltang@codesourcery.com>
Co-authored-by: Thomas Schwinge <thomas@codesourcery.com>
|
|
'PLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H' and 'PLUGIN_NVPTX_LINK_LIBCUDA'
Including the GCC-shipped 'include/cuda/cuda.h' vs. system <cuda.h> and
'dlopen'ing the CUDA Driver library vs. linking it are separate concerns.
libgomp/
* plugin/Makefrag.am: Handle 'PLUGIN_NVPTX_DYNAMIC'.
* plugin/configfrag.ac (PLUGIN_NVPTX_DYNAMIC): Change
'AC_DEFINE_UNQUOTED' into 'AM_CONDITIONAL'.
* plugin/plugin-nvptx.c: Split 'PLUGIN_NVPTX_DYNAMIC' into
'PLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H' and
'PLUGIN_NVPTX_LINK_LIBCUDA'.
* Makefile.in: Regenerate.
* config.h.in: Likewise.
* configure: Likewise.
|
|
... so that it may be used by other projects that inherit GCC's 'include'
directory.
include/
* cuda/cuda.h: New file.
libgomp/
* plugin/cuda/cuda.h: Remove file.
* plugin/plugin-nvptx.c [PLUGIN_NVPTX_DYNAMIC]: Include
"cuda/cuda.h" instead of <cuda.h>.
* plugin/configfrag.ac <PLUGIN_NVPTX_DYNAMIC>: Don't set
'PLUGIN_NVPTX_CPPFLAGS'.
* configure: Regenerate.
|
|
In the patch that implemented omp_get_device_num(), there was an error where
the stringification of GOMP_DEVICE_NUM_VAR, which is the macro expanding to
the actual symbol used, was erroneously using the STRINGX() macro in the
libgomp offload image symbol search, and expansion of the variable name
string through the additional layer of preprocessor symbol was not properly
achieved.
This patch fixes this by changing to properly use XSTRING(), also from
include/symcat.h.
libgomp/ChangeLog:
* plugin/plugin-gcn.c (GOMP_OFFLOAD_load_image): Change uses of STRINGX
into XSTRING when looking for GOMP_DEVICE_NUM_VAR in offload image.
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_load_image): Likewise.
|
|
|
|
This patch implements the omp_get_device_num library routine, specified in
OpenMP 5.0.
GOMP_DEVICE_NUM_VAR is a macro symbol which defines name of a "device number"
variable, is defined on the device-side libgomp, has it's address returned to
host-side libgomp during device initialization, and the host libgomp then
sets its value to the designated device number.
libgomp/ChangeLog:
* icv-device.c (omp_get_device_num): New API function, host side.
* fortran.c (omp_get_device_num_): New interface function.
* libgomp-plugin.h (GOMP_DEVICE_NUM_VAR): Define macro symbol.
* libgomp.map (OMP_5.0.2): New version space with omp_get_device_num,
omp_get_device_num_.
* libgomp.texi (omp_get_device_num): Add documentation for new API
function.
* omp.h.in (omp_get_device_num): Add declaration.
* omp_lib.f90.in (omp_get_device_num): Likewise.
* omp_lib.h.in (omp_get_device_num): Likewise.
* target.c (gomp_load_image_to_device): If additional entry for device
number exists at end of returned entries from 'load_image_func' hook,
copy the assigned device number over to the device variable.
* config/gcn/icv-device.c (GOMP_DEVICE_NUM_VAR): Define static global.
(omp_get_device_num): New API function, device side.
* plugin/plugin-gcn.c ("symcat.h"): Add include.
(GOMP_OFFLOAD_load_image): Add addresses of device GOMP_DEVICE_NUM_VAR
at end of returned 'target_table' entries.
* config/nvptx/icv-device.c (GOMP_DEVICE_NUM_VAR): Define static global.
(omp_get_device_num): New API function, device side.
* plugin/plugin-nvptx.c ("symcat.h"): Add include.
(GOMP_OFFLOAD_load_image): Add addresses of device GOMP_DEVICE_NUM_VAR
at end of returned 'target_table' entries.
* testsuite/lib/libgomp.exp
(check_effective_target_offload_target_intelmic): New function for
testing for intelmic offloading.
* testsuite/libgomp.c-c++-common/target-45.c: New test.
* testsuite/libgomp.fortran/target10.f90: New test.
|
|
As recently again discussed in <https://gcc.gnu.org/PR97436> "[nvptx] -m32
support", nvptx offloading other than for 64-bit host has never been
implemented, tested, supported. So we simply should buildn't the nvptx libgomp
plugin in this case.
This avoids build problems if, for example, in a (standard) bi-arch
x86_64-pc-linux-gnu '-m64'/'-m32' build, libcuda is available only in a 64-bit
variant but not in a 32-bit one, which, for example, is the case if you build
GCC against the CUDA toolkit's 'stubs/libcuda.so' (see
<https://stackoverflow.com/a/52784819>).
This amends PR65099 commit a92defdab79a1268f4b9dcf42b937e4002a4cf15 (r225560)
"[nvptx offloading] Only 64-bit configurations are currently supported" to
match the way we're doing this for the HSA/GCN plugins.
libgomp/
PR libgomp/65099
* plugin/configfrag.ac (PLUGIN_NVPTX): Restrict to supported
configurations.
* configure: Regenerate.
* plugin/plugin-nvptx.c (nvptx_get_num_devices): Remove 64-bit
check.
|
|
2021-01-05 Julian Brown <julian@codesourcery.com>
libgomp/
* plugin/plugin-nvptx.c (SOFTSTACK_CACHE_LIMIT): New define.
(struct ptx_device): Add omp_stacks struct.
(nvptx_open_device): Initialise cached-stacks housekeeping info.
(nvptx_close_device): Free cached stacks block and mutex.
(nvptx_stacks_free): New function.
(nvptx_alloc): Add SUPPRESS_ERRORS parameter.
(GOMP_OFFLOAD_alloc): Add strategies for freeing soft-stacks block.
(nvptx_stacks_alloc): Rename to...
(nvptx_stacks_acquire): This. Cache stacks block between runs if same
size or smaller is required.
(nvptx_stacks_free): Remove.
(GOMP_OFFLOAD_run): Call nvptx_stacks_acquire and lock stacks block
during kernel execution.
|
|
|
|
Using this patch, when using GOMP_DEBUG=1 and launching a kernel in
GOMP_OFFLOAD_run (used by the omp implementation), we see the kernel launch
dimensions:
...
GOMP_OFFLOAD_run: kernel main$_omp_fn$0: \
launch [(teams: 1), 1, 1] [(lanes: 32), (threads: 1), 1]
...
Build on x86_64-linux with nvptx accelerator, tested libgomp.
libgomp/ChangeLog:
2020-10-08 Tom de Vries <tdevries@suse.de>
PR libgomp/81802
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_run): Report launch
dimensions.
|
|
By running libgomp test-case libgomp.c/target-28.c with GOMP_NVPTX_PTXRW=w
(using a maintenance patch that adds support for this env var), we dump the
ptx in target-28.exe to file. By editing one ptx file to rename
gomp_nvptx_main to gomp_nvptx_main2 in both declaration and call, and
running with GOMP_NVPTX_PTXRW=r, we trigger a link error:
...
$ GOMP_NVPTX_PTXRW=r ./target-28.exe
libgomp: cuLinkComplete error: unknown error
...
The error is somewhat uninformative.
Fix this by dumping the error log returned by the failing cuda call, such
that we have instead:
...
$ GOMP_NVPTX_PTXRW=r ./target-28.exe
libgomp: Link error log error : \
Undefined reference to 'gomp_nvptx_main2' in ''
libgomp: cuLinkComplete error: unknown error
...
Build on x86_64 with nvptx accelerator, tested libgomp.
libgomp/ChangeLog:
* plugin/plugin-nvptx.c (link_ptx): Print elog if cuLinkComplete call
fails.
|
|
Change test for CUDA callback context in nvptx_free() from using
GOMP_PLUGIN_acc_thread () into checking for CUDA_ERROR_NOT_PERMITTED,
for the former only works for OpenACC, but not OpenMP offloading.
2020-08-20 Chung-Lin Tang <cltang@codesourcery.com>
libgomp/
* plugin/plugin-nvptx.c (nvptx_free):
Change "GOMP_PLUGIN_acc_thread () == NULL" test into check of
CUDA_ERROR_NOT_PERMITTED status for cuMemGetAddressRange. Adjust
comments.
|
|
An OpenMP "nowait" clause on a target construct currently leads to
a call to GOMP_OFFLOAD_async_run in the plugin that is used for
offloading at execution time. The nvptx plugin contains only a stub
of this function that always produces a fatal error if called.
This commit changes the "nowait" implementation to ignore the clause
if the executing device's plugin does not implement GOMP_OFFLOAD_async_run.
The stub in the nvptx plugin is removed which effectively means that
programs containing "nowait" can now be executed with nvptx offloading
as if the clause had not been used.
This behavior is consistent with the OpenMP specification which says that
"[...] execution of the target task *may* be deferred" (emphasis added),
cf. OpenMP 5.0, page 172.
libgomp/
* plugin/plugin-nvptx.c: Remove GOMP_OFFLOAD_async_run stub.
* target.c (gomp_load_plugin_for_device): Make "async_run" loading
optional.
(gomp_target_task_fn): Assert "devicep->async_run_func".
(clear_unsupported_flags): New function to remove unsupported flags
(right now only GOMP_TARGET_FLAG_NOWAIT) that can be be ignored.
(GOMP_target_ext): Apply clear_unsupported_flags to flags.
* testsuite/libgomp.c/target-33.c:
Remove xfail for offload_target_nvptx.
* testsuite/libgomp.c/target-34.c: Likewise.
|
|
include/
* gomp-constants.h (enum gomp_device_property): Remove.
libgomp/
* libgomp-plugin.h (enum goacc_property): New. Adjust all users
to use this instead of 'enum gomp_device_property'.
(GOMP_OFFLOAD_get_property): Rename to...
(GOMP_OFFLOAD_openacc_get_property): ... this. Adjust all users.
* libgomp.h (struct gomp_device_descr): Move
'GOMP_OFFLOAD_openacc_get_property'...
(struct acc_dispatch_t): ... here. Adjust all users.
* plugin/plugin-hsa.c (GOMP_OFFLOAD_get_property): Remove.
liboffloadmic/
* plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_get_property):
Remove.
From-SVN: r280150
|
|
From-SVN: r279813
|
|
Add generic support for the OpenACC 2.6 `acc_get_property' and
`acc_get_property_string' routines, as well as full handlers for the
host and the NVPTX offload targets and minimal handlers for the HSA,
Intel MIC, and AMD GCN offload targets.
Included are C/C++ and Fortran tests that, in particular, print
the property values for acc_property_vendor, acc_property_memory,
acc_property_free_memory, acc_property_name, and acc_property_driver.
The output looks as follows:
Vendor: GNU
Name: GOMP
Total memory: 0
Free memory: 0
Driver: 1.0
with the host driver (where the memory related properties are not
supported for the host device and yield 0, conforming to the standard)
and output like:
Vendor: Nvidia
Total memory: 12651462656
Free memory: 12202737664
Name: TITAN V
Driver: CUDA Driver 9.1
with the NVPTX driver.
2019-12-22 Maciej W. Rozycki <macro@codesourcery.com>
Frederik Harwath <frederik@codesourcery.com>
Thomas Schwinge <tschwinge@codesourcery.com>
include/
* gomp-constants.h (gomp_device_property): New enum.
libgomp/
* libgomp.h (gomp_device_descr): Add `get_property_func' member.
* libgomp-plugin.h (gomp_device_property_value): New union.
(gomp_device_property_value): New prototype.
* openacc.h (acc_device_t): Add `acc_device_current' enumeration
constant.
(acc_device_property_t): New enum.
(acc_get_property, acc_get_property_string): New prototypes.
* oacc-init.c (acc_get_device_type): Also assert that result
is not `acc_device_current'.
(get_property_any, acc_get_property, acc_get_property_string):
New functions.
* openacc.f90 (openacc_kinds): Add `acc_device_current' and
`acc_property_memory', `acc_property_free_memory',
`acc_property_name', `acc_property_vendor' and
`acc_property_driver' constants. Add `acc_device_property' data
type.
(openacc_internal): Add `acc_get_property' and
`acc_get_property_string' interfaces. Add `acc_get_property_h',
`acc_get_property_string_h', `acc_get_property_l' and
`acc_get_property_string_l'.
* oacc-host.c (host_get_property): New function.
(host_dispatch): Wire it.
* target.c (gomp_load_plugin_for_device): Handle `get_property'.
* libgomp.map (OACC_2.6): Add `acc_get_property', `acc_get_property_h_',
`acc_get_property_string' and `acc_get_property_string_h_' symbols.
* libgomp.texi (OpenACC Runtime Library Routines): Add
`acc_get_property'.
(acc_get_property): New node.
* plugin/plugin-gcn.c (GOMP_OFFLOAD_get_property): New
function (stub).
* plugin/plugin-hsa.c (GOMP_OFFLOAD_get_property): New function.
* plugin/plugin-nvptx.c (CUDA_CALLS): Add `cuDeviceGetName',
`cuDeviceTotalMem', `cuDriverGetVersion' and `cuMemGetInfo'
calls.
(GOMP_OFFLOAD_get_property): New function.
(struct ptx_device): Add new field "name".
(cuda_driver_version_s): Add new static variable ...
(nvptx_init): ... and init from here.
* testsuite/libgomp.oacc-c-c++-common/acc_get_property.c: New test.
* testsuite/libgomp.oacc-c-c++-common/acc_get_property-2.c: New test.
* testsuite/libgomp.oacc-c-c++-common/acc_get_property-3.c: New test.
* testsuite/libgomp.oacc-c-c++-common/acc_get_property-aux.c: New file
with test helper functions.
* testsuite/libgomp.oacc-fortran/acc_get_property.f90: New test.
liboffloadmic/
* plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_get_property):
New function.
Reviewed-by: Thomas Schwinge <thomas@codesourcery.com>
Co-Authored-By: Frederik Harwath <frederik@codesourcery.com>
Co-Authored-By: Thomas Schwinge <tschwinge@codesourcery.com>
From-SVN: r279710
|
|
2019-11-13 Andrew Stubbs <ams@codesourcery.com>
Julian Brown <julian@codesourcery.com>
libgomp/
* libgomp-plugin.h (GOMP_OFFLOAD_openacc_async_construct): Add int
parameter.
* oacc-async.c (lookup_goacc_asyncqueue): Pass device number to the
queue constructor.
* oacc-host.c (host_openacc_async_construct): Add device parameter.
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_openacc_async_construct): Add
device parameter.
Co-Authored-By: Julian Brown <julian@codesourcery.com>
From-SVN: r278134
|
|
* configure.ac: Remove GCC_HEADER_STDINT(gstdint.h).
* libgomp.h: Include <stdint.h> instead of "gstdint.h".
* oacc-parallel.c: Don't include "libgomp_g.h".
* plugin/plugin-hsa.c: Include <stdint.h> instead of "gstdint.h".
* plugin/plugin-nvptx.c: Don't include "gstdint.h".
* aclocal.m4: Regenerated.
* config.h.in: Regenerated.
* configure: Regenerated.
* Makefile.in: Regenerated.
From-SVN: r276389
|
|
PR libgomp/90585
* plugin/plugin-hsa.c: Include gstdint.h. Include inttypes.h only if
HAVE_INTTYPES_H is defined.
(print_uint64_t): New typedef.
(PRIu64): Define if HAVE_INTTYPES_H is not defined.
(print_kernel_dispatch, run_kernel): Use PRIu64 macro instead of
"lu", cast uint64_t HSA_DEBUG and fprintf arguments to print_uint64_t.
(release_kernel_dispatch): Likewise. Cast shadow->debug to uintptr_t
before casting to void *.
* plugin/plugin-nvptx.c: Include gstdint.h instead of stdint.h.
* oacc-mem.c: Don't include config.h nor stdint.h.
* target.c: Don't include config.h.
* oacc-cuda.c: Likewise.
* oacc-host.c: Don't include stdint.h.
From-SVN: r271597
|
|
libgomp/
* acc_prof.h: New file.
* oacc-profiling.c: Likewise.
* Makefile.am (nodist_libsubinclude_HEADERS, libgomp_la_SOURCES):
Add these, respectively.
* Makefile.in: Regenerate.
* env.c (initialize_env): Call goacc_profiling_initialize.
* oacc-plugin.c (GOMP_PLUGIN_goacc_thread)
(GOMP_PLUGIN_goacc_profiling_dispatch): New functions.
* oacc-plugin.h (GOMP_PLUGIN_goacc_thread)
(GOMP_PLUGIN_goacc_profiling_dispatch): Declare.
* libgomp.map (OACC_2.5.1): Add acc_prof_lookup,
acc_prof_register, acc_prof_unregister, and acc_register_library.
(GOMP_PLUGIN_1.3): Add GOMP_PLUGIN_goacc_profiling_dispatch, and
GOMP_PLUGIN_goacc_thread.
* oacc-int.h (struct goacc_thread): Add prof_info, api_info,
prof_callbacks_enabled members.
(goacc_prof_enabled, goacc_profiling_initialize)
(_goacc_profiling_dispatch_p, _goacc_profiling_setup_p)
(goacc_profiling_dispatch): Declare.
(GOACC_PROF_ENABLED, GOACC_PROFILING_DISPATCH_P)
(GOACC_PROFILING_SETUP_P): Define.
* oacc-async.c (acc_async_test, acc_async_test_all, acc_wait)
(acc_wait_async, acc_wait_all, acc_wait_all_async): Update for
OpenACC Profiling Interface.
* oacc-cuda.c (acc_get_current_cuda_device)
(acc_get_current_cuda_context, acc_get_cuda_stream)
(acc_set_cuda_stream): Likewise.
* oacc-init.c (acc_init_1, goacc_attach_host_thread_to_device)
(acc_init, acc_set_device_type, acc_get_device_type)
(acc_get_device_num, goacc_lazy_initialize): Likewise.
* oacc-mem.c (acc_malloc, acc_free, memcpy_tofrom_device)
(acc_deviceptr, acc_hostptr, acc_is_present, acc_map_data)
(acc_unmap_data, present_create_copy, delete_copyout)
(update_dev_host): Likewise.
* oacc-parallel.c (GOACC_parallel_keyed, GOACC_data_start)
(GOACC_data_end, GOACC_enter_exit_data, GOACC_update, GOACC_wait):
Likewise.
* plugin/plugin-nvptx.c (nvptx_exec, nvptx_alloc, nvptx_free)
(GOMP_OFFLOAD_openacc_exec, GOMP_OFFLOAD_openacc_async_exec):
Likewise.
* libgomp.texi: Update.
* testsuite/libgomp.oacc-c-c++-common/acc_prof-dispatch-1.c: New
file.
* testsuite/libgomp.oacc-c-c++-common/acc_prof-init-1.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/acc_prof-kernels-1.c:
Likewise.
* testsuite/libgomp.oacc-c-c++-common/acc_prof-parallel-1.c:
Likewise.
* testsuite/libgomp.oacc-c-c++-common/acc_prof-valid_bytes-1.c:
Likewise.
* testsuite/libgomp.oacc-c-c++-common/acc_prof-version-1.c:
Likewise.
From-SVN: r271346
|
|
Reviewed-by: Thomas Schwinge <thomas@codesourcery.com>
libgomp/
* libgomp-plugin.h (struct goacc_asyncqueue): Declare.
(struct goacc_asyncqueue_list): Likewise.
(goacc_aq): Likewise.
(goacc_aq_list): Likewise.
(GOMP_OFFLOAD_openacc_register_async_cleanup): Remove.
(GOMP_OFFLOAD_openacc_async_test): Remove.
(GOMP_OFFLOAD_openacc_async_test_all): Remove.
(GOMP_OFFLOAD_openacc_async_wait): Remove.
(GOMP_OFFLOAD_openacc_async_wait_async): Remove.
(GOMP_OFFLOAD_openacc_async_wait_all): Remove.
(GOMP_OFFLOAD_openacc_async_wait_all_async): Remove.
(GOMP_OFFLOAD_openacc_async_set_async): Remove.
(GOMP_OFFLOAD_openacc_exec): Adjust declaration.
(GOMP_OFFLOAD_openacc_cuda_get_stream): Likewise.
(GOMP_OFFLOAD_openacc_cuda_set_stream): Likewise.
(GOMP_OFFLOAD_openacc_async_exec): Declare.
(GOMP_OFFLOAD_openacc_async_construct): Declare.
(GOMP_OFFLOAD_openacc_async_destruct): Declare.
(GOMP_OFFLOAD_openacc_async_test): Declare.
(GOMP_OFFLOAD_openacc_async_synchronize): Declare.
(GOMP_OFFLOAD_openacc_async_serialize): Declare.
(GOMP_OFFLOAD_openacc_async_queue_callback): Declare.
(GOMP_OFFLOAD_openacc_async_host2dev): Declare.
(GOMP_OFFLOAD_openacc_async_dev2host): Declare.
* libgomp.h (struct acc_dispatch_t): Define 'async' sub-struct.
(gomp_acc_insert_pointer): Adjust declaration.
(gomp_copy_host2dev): New declaration.
(gomp_copy_dev2host): Likewise.
(gomp_map_vars_async): Likewise.
(gomp_unmap_tgt): Likewise.
(gomp_unmap_vars_async): Likewise.
(gomp_fini_device): Likewise.
* oacc-async.c (get_goacc_thread): New function.
(get_goacc_thread_device): New function.
(lookup_goacc_asyncqueue): New function.
(get_goacc_asyncqueue): New function.
(acc_async_test): Adjust code to use new async design.
(acc_async_test_all): Likewise.
(acc_wait): Likewise.
(acc_wait_async): Likewise.
(acc_wait_all): Likewise.
(acc_wait_all_async): Likewise.
(goacc_async_free): New function.
(goacc_init_asyncqueues): Likewise.
(goacc_fini_asyncqueues): Likewise.
* oacc-cuda.c (acc_get_cuda_stream): Adjust code to use new async
design.
(acc_set_cuda_stream): Likewise.
* oacc-host.c (host_openacc_exec): Adjust parameters, remove 'async'.
(host_openacc_register_async_cleanup): Remove.
(host_openacc_async_exec): New function.
(host_openacc_async_test): Adjust parameters.
(host_openacc_async_test_all): Remove.
(host_openacc_async_wait): Remove.
(host_openacc_async_wait_async): Remove.
(host_openacc_async_wait_all): Remove.
(host_openacc_async_wait_all_async): Remove.
(host_openacc_async_set_async): Remove.
(host_openacc_async_synchronize): New function.
(host_openacc_async_serialize): New function.
(host_openacc_async_host2dev): New function.
(host_openacc_async_dev2host): New function.
(host_openacc_async_queue_callback): New function.
(host_openacc_async_construct): New function.
(host_openacc_async_destruct): New function.
(struct gomp_device_descr host_dispatch): Remove initialization of old
interface, add intialization of new async sub-struct.
* oacc-init.c (acc_shutdown_1): Adjust to use gomp_fini_device.
(goacc_attach_host_thread_to_device): Remove old async code usage.
* oacc-int.h (goacc_init_asyncqueues): New declaration.
(goacc_fini_asyncqueues): Likewise.
(goacc_async_copyout_unmap_vars): Likewise.
(goacc_async_free): Likewise.
(get_goacc_asyncqueue): Likewise.
(lookup_goacc_asyncqueue): Likewise.
* oacc-mem.c (memcpy_tofrom_device): Adjust code to use new async
design.
(present_create_copy): Adjust code to use new async design.
(delete_copyout): Likewise.
(update_dev_host): Likewise.
(gomp_acc_insert_pointer): Add async parameter, adjust code to use new
async design.
(gomp_acc_remove_pointer): Adjust code to use new async design.
* oacc-parallel.c (GOACC_parallel_keyed): Adjust code to use new async
design.
(GOACC_enter_exit_data): Likewise.
(goacc_wait): Likewise.
(GOACC_update): Likewise.
* oacc-plugin.c (GOMP_PLUGIN_async_unmap_vars): Change to assert fail
when called, warn as obsolete in comment.
* target.c (goacc_device_copy_async): New function.
(gomp_copy_host2dev): Remove 'static', add goacc_asyncqueue parameter,
add goacc_device_copy_async case.
(gomp_copy_dev2host): Likewise.
(gomp_map_vars_existing): Add goacc_asyncqueue parameter, adjust code.
(gomp_map_pointer): Likewise.
(gomp_map_fields_existing): Likewise.
(gomp_map_vars_internal): New always_inline function, renamed from
gomp_map_vars.
(gomp_map_vars): Implement by calling gomp_map_vars_internal.
(gomp_map_vars_async): Implement by calling gomp_map_vars_internal,
passing goacc_asyncqueue argument.
(gomp_unmap_tgt): Remove static, add attribute_hidden.
(gomp_unref_tgt): New function.
(gomp_unmap_vars_internal): New always_inline function, renamed from
gomp_unmap_vars.
(gomp_unmap_vars): Implement by calling gomp_unmap_vars_internal.
(gomp_unmap_vars_async): Implement by calling
gomp_unmap_vars_internal, passing goacc_asyncqueue argument.
(gomp_fini_device): New function.
(gomp_exit_data): Adjust gomp_copy_dev2host call.
(gomp_load_plugin_for_device): Remove old interface, adjust to load
new async interface.
(gomp_target_fini): Adjust code to call gomp_fini_device.
* plugin/plugin-nvptx.c (struct cuda_map): Remove.
(struct ptx_stream): Remove.
(struct nvptx_thread): Remove current_stream field.
(cuda_map_create): Remove.
(cuda_map_destroy): Remove.
(map_init): Remove.
(map_fini): Remove.
(map_pop): Remove.
(map_push): Remove.
(struct goacc_asyncqueue): Define.
(struct nvptx_callback): Define.
(struct ptx_free_block): Define.
(struct ptx_device): Remove null_stream, active_streams, async_streams,
stream_lock, and next fields.
(enum ptx_event_type): Remove.
(struct ptx_event): Remove.
(ptx_event_lock): Remove.
(ptx_events): Remove.
(init_streams_for_device): Remove.
(fini_streams_for_device): Remove.
(select_stream_for_async): Remove.
(nvptx_init): Remove ptx_events and ptx_event_lock references.
(nvptx_attach_host_thread_to_device): Remove CUDA_ERROR_NOT_PERMITTED
case.
(nvptx_open_device): Add free_blocks initialization, remove
init_streams_for_device call.
(nvptx_close_device): Remove fini_streams_for_device call, add
free_blocks destruct code.
(event_gc): Remove.
(event_add): Remove.
(nvptx_exec): Adjust parameters and code.
(nvptx_free): Likewise.
(nvptx_host2dev): Remove.
(nvptx_dev2host): Remove.
(nvptx_set_async): Remove.
(nvptx_async_test): Remove.
(nvptx_async_test_all): Remove.
(nvptx_wait): Remove.
(nvptx_wait_async): Remove.
(nvptx_wait_all): Remove.
(nvptx_wait_all_async): Remove.
(nvptx_get_cuda_stream): Remove.
(nvptx_set_cuda_stream): Remove.
(GOMP_OFFLOAD_alloc): Adjust code.
(GOMP_OFFLOAD_free): Likewise.
(GOMP_OFFLOAD_openacc_register_async_cleanup): Remove.
(GOMP_OFFLOAD_openacc_exec): Adjust parameters and code.
(GOMP_OFFLOAD_openacc_async_test_all): Remove.
(GOMP_OFFLOAD_openacc_async_wait): Remove.
(GOMP_OFFLOAD_openacc_async_wait_async): Remove.
(GOMP_OFFLOAD_openacc_async_wait_all): Remove.
(GOMP_OFFLOAD_openacc_async_wait_all_async): Remove.
(GOMP_OFFLOAD_openacc_async_set_async): Remove.
(cuda_free_argmem): New function.
(GOMP_OFFLOAD_openacc_async_exec): New plugin hook function.
(GOMP_OFFLOAD_openacc_create_thread_data): Adjust code.
(GOMP_OFFLOAD_openacc_cuda_get_stream): Adjust code.
(GOMP_OFFLOAD_openacc_cuda_set_stream): Adjust code.
(GOMP_OFFLOAD_openacc_async_construct): New plugin hook function.
(GOMP_OFFLOAD_openacc_async_destruct): New plugin hook function.
(GOMP_OFFLOAD_openacc_async_test): Remove and re-implement.
(GOMP_OFFLOAD_openacc_async_synchronize): New plugin hook function.
(GOMP_OFFLOAD_openacc_async_serialize): New plugin hook function.
(GOMP_OFFLOAD_openacc_async_queue_callback): New plugin hook function.
(cuda_callback_wrapper): New function.
(cuda_memcpy_sanity_check): New function.
(GOMP_OFFLOAD_host2dev): Remove and re-implement.
(GOMP_OFFLOAD_dev2host): Remove and re-implement.
(GOMP_OFFLOAD_openacc_async_host2dev): New plugin hook function.
(GOMP_OFFLOAD_openacc_async_dev2host): New plugin hook function.
From-SVN: r271128
|
|
I wrote a test-case:
...
int
main (void)
{
for (unsigned i = 0; i < 128; ++i)
{
acc_init (acc_device_nvidia);
acc_shutdown (acc_device_nvidia);
}
return 0;
}
...
and ran it under valgrind. The only leak location reported with a frequency
of 128, was the allocation of ptx_devices in nvptx_init.
Fix this by freeing ptx_devices in GOMP_OFFLOAD_fini_device, once
instantiated_devices drops to 0.
2019-01-24 Tom de Vries <tdevries@suse.de>
* plugin/plugin-nvptx.c (GOMP_OFFLOAD_fini_device): Free ptx_devices
once instantiated_devices drops to 0.
From-SVN: r268237
|
|
Consider test-case:
...
int
main (void)
{
#pragma acc parallel async
;
#pragma acc parallel async
;
#pragma acc wait
return 0;
}
...
This fails with:
...
libgomp: cuMemAlloc error: invalid argument
Segmentation fault (core dumped)
...
The cuMemAlloc error is due to the fact that we're try to allocate 0 bytes.
Fix this by preventing calling map_push with size zero argument in nvptx_exec.
This also has the consequence that for the abort-1.c test-case, we end up
calling cuMemFree during map_fini for the struct cuda_map allocated in
map_init, which fails because an abort happened. Fix this by calling
cuMemFree with CUDA_CALL_NOCHECK in cuda_map_destroy.
2019-01-23 Tom de Vries <tdevries@suse.de>
PR target/PR88946
* plugin/plugin-nvptx.c (cuda_map_destroy): Use CUDA_CALL_NOCHECK for
cuMemFree.
(nvptx_exec): Don't call map_push if mapnum == 0.
* testsuite/libgomp.oacc-c-c++-common/pr88946.c: New test.
From-SVN: r268178
|
|
There are currently two situations where this assert triggers:
...
libgomp/plugin/plugin-nvptx.c: map_fini: Assertion `!s->map->active' failed.
...
First, in abort-1.c, a parallel region triggering an abort:
...
int
main (void)
{
#pragma acc parallel
abort ();
return 0;
}
...
The abort is detected in nvptx_exec as the CUDA_ERROR_ILLEGAL_INSTRUCTION
return status of the cuStreamSynchronize call after kernel launch, which is
then handled by calling non-returning function GOMP_PLUGIN_fatal.
Consequently, the map_pop in nvptx_exec that in case of cuStreamSynchronize
success would remove or inactive the element added by the map_push earlier in
nvptx_exec, does not trigger. With the element no longer active, but still
marked active and a member of s->map, we run into the assert during
GOMP_OFFLOAD_fini_device, which is triggered from atexit handler
gomp_target_fini (which is triggered by the GOMP_PLUGIN_fatal mentioned above
calling exit).
Second, in pr88941.c, an async parallel region without wait:
...
int
main (void)
{
#pragma acc parallel async
;
/* no #pragma acc wait */
return 0;
}
...
Because nvptx_exec is handling an async region, it does not call map_pop for
the element added by map_push, but schedules an kernel execution completion
event to call map_pop. Again, we run into the assert during
GOMP_OFFLOAD_fini_device, which is triggered from atexit handler
gomp_target_fini, but the exit in this case is triggered by returning from main.
So either the kernel is still running, or the kernel has completed but the
corresponding event that is supposed to call map_pop is stuck in the event
queue, waiting for an event_gc.
Fix this by removing the assert, and skipping the freeing of device memory if
the map is still marked active (though in the async case, this is more a
workaround than an fix).
2019-01-23 Tom de Vries <tdevries@suse.de>
PR target/88941
PR target/88939
* plugin/plugin-nvptx.c (cuda_map_destroy): Handle map->active case.
(map_fini): Remove "assert (!s->map->active)".
* testsuite/libgomp.oacc-c-c++-common/pr88941.c: New test.
From-SVN: r268177
|
|
The map field of a struct ptx_stream is a FIFO. The FIFO is implemented as a
single linked list, with pop-from-the-front semantics.
The function map_pop pops an element, either by:
- deallocating the element, if there is more than one element
- or marking the element inactive, if there's only one element
The responsibility of map_push is to push an element to the back, as well as
selecting the element to push, by:
- allocating an element, or
- reusing the element at the front if inactive and big enough, or
- dropping the element at the front if inactive and not big enough, and
allocating one that's big enough
The current implemention gets at least the first and most basic scenario wrong:
> map = cuda_map_create (size);
We create an element, and assign it to map.
> for (t = s->map; t->next != NULL; t = t->next)
> ;
We determine the last element in the fifo.
> t->next = map;
We append the new element.
> s->map = map;
But here, we throw away the rest of the FIFO, and declare the FIFO to be just
the new element.
This problem causes the test-case asyncwait-1.c to fail intermittently on some
systems. The pr87835.c test-case added here is a a minimized and modified
version of asyncwait-1.c (avoiding the kernel construct) that is more likely to
fail.
Fix this by rewriting map_pop more robustly, by:
- seperating the function in two phases: select element, push element
- when reusing or dropping an element, making sure that the element is cleanly
popped from the queue
- rewriting the push element part in such a way that it can handle all cases
without needing if statements, such that each line is exercised for each of
the three cases.
2019-01-23 Tom de Vries <tdevries@suse.de>
PR target/87835
* plugin/plugin-nvptx.c (map_push): Fix adding of allocated element.
* testsuite/libgomp.oacc-c-c++-common/pr87835.c: New test.
From-SVN: r268176
|
|
Enable setting vector length using -fopenacc-dim, f.i. -fopenacc-dim=::128.
2019-01-12 Tom de Vries <tdevries@suse.de>
* config/nvptx/nvptx.c (nvptx_goacc_validate_dims_1): Alow setting
vector length using -fopenacc-dim.
* plugin/plugin-nvptx.c (nvptx_exec): Update error message.
From-SVN: r267896
|
|
Update message in nvptx libgomp plugin about insufficient resources to launch
kernel, to accommodate for the fact the vector_length can now be variable.
2019-01-12 Tom de Vries <tdevries@suse.de>
* plugin/plugin-nvptx.c (nvptx_exec): Update insufficient hardware
resources diagnostic.
From-SVN: r267890
|
|
When using a compiler build with:
...
+#define PTX_DEFAULT_VECTOR_LENGTH PTX_CTA_SIZE
...
consider a test-case:
...
int
main (void)
{
#pragma acc parallel vector_length (64)
#pragma acc loop worker
for (unsigned int i = 0; i < 32; i++)
#pragma acc loop vector
for (unsigned int j = 0; j < 64; j++)
;
return 0;
}
...
If num_workers is 16, either because:
- we add a "num_workers (16)" clause on the parallel directive, or
- we set "GOMP_OPENACC_DIM=:16:", or
- the libgomp plugin chooses 16 num_workers
we run into an illegal instruction at runtime, because a bar.sync instruction
tries to use a barrier 16. The instruction is illegal, because ptx supports
only 16 barriers per CTA, and the valid range is 0..15.
The problem is that with a warp-multiple vector length, we use a code generation
scheme with a per-worker barrier. And because barrier zero is reserved for
per-cta barrier, only the remaining 15 barriers can be used as per-worker
barrier, and consequently we can't use num_workers larger than 15.
This problem occurs only for vector_length 64. For vector_length 32, we use a
different code generation scheme, and for vector_length >= 96, the maximum
num_workers is not big enough not to trigger this problem.
Also, this problem only occurs for num_workers 16. As explained above,
num_workers 15 is safe to use, and 16 is already the maximum num_workers for
vector_length 64.
This patch fixes the problem in both the compiler (handling "num_workers (16)")
and in the libgomp nvptx plugin (with and without "GOMP_OPENACC_DIM=:16:").
2019-01-11 Tom de Vries <tdevries@suse.de>
* config/nvptx/nvptx.c (PTX_CTA_NUM_BARRIERS, PTX_PER_CTA_BARRIER)
(PTX_NUM_PER_CTA_BARRIER, PTX_FIRST_PER_WORKER_BARRIER)
(PTX_NUM_PER_WORKER_BARRIERS): Define.
(nvptx_apply_dim_limits): Prevent vector_length 64 and
num_workers 16.
* plugin/plugin-nvptx.c (nvptx_exec): Prevent vector_length 64 and
num_workers 16.
From-SVN: r267838
|
|
When using a compiler build with:
...
+#define PTX_DEFAULT_VECTOR_LENGTH PTX_CTA_SIZE
+#define PTX_MAX_VECTOR_LENGTH PTX_CTA_SIZE
...
and running the libgomp testsuite, we run into an execution failure in
parallel-loop-1.c, due to a cuda launch failure:
...
nvptx_exec: kernel f6_none_none$_omp_fn$0: launch gangs=480, workers=0, \
vectors=1024
libgomp: cuLaunchKernel error: invalid argument
...
because workers == 0.
The workers variable is set to 0 here in nvptx_exec:
...
workers = blocks / actual_vectors;
...
because actual_vectors is 1024, and blocks is 768:
...
cuOccupancyMaxPotentialBlockSize: grid = 10, block = 768
...
Fix this by ensuring that workers is at least one.
2019-01-09 Tom de Vries <tdevries@suse.de>
* plugin/plugin-nvptx.c (nvptx_exec): Make sure to launch with at least
one worker.
From-SVN: r267746
|
|
From-SVN: r267494
|
|
An OpenACC async queue is always synchronized with itself, so invocations like
"#pragma acc wait(0) async(0)", or "acc_wait_async (0, 0)" don't make a lot of
sense, but are still valid.
libgomp/
PR libgomp/88495
* plugin/plugin-nvptx.c (nvptx_wait_async): Don't refuse
"identical parameters".
* testsuite/libgomp.oacc-c-c++-common/asyncwait-nop-1.c: Update.
* testsuite/libgomp.oacc-c-c++-common/lib-80.c: Remove.
From-SVN: r267152
|
|
... which turn the operation into a no-op.
libgomp/
PR libgomp/88407
* plugin/plugin-nvptx.c (nvptx_async_test, nvptx_wait)
(nvptx_wait_async): Unseen async-argument is a no-op.
* testsuite/libgomp.oacc-c-c++-common/async_queue-1.c: Update.
* testsuite/libgomp.oacc-c-c++-common/data-2-lib.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/data-2.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/lib-79.c: Likewise.
* testsuite/libgomp.oacc-fortran/lib-12.f90: Likewise.
* testsuite/libgomp.oacc-c-c++-common/lib-71.c: Merge into...
* testsuite/libgomp.oacc-c-c++-common/lib-69.c: ... this. Update.
* testsuite/libgomp.oacc-c-c++-common/lib-77.c: Merge into...
* testsuite/libgomp.oacc-c-c++-common/lib-74.c: ... this. Update
From-SVN: r267150
|
|
acc_async_noval
Per my reading of the OpenACC specification (and as supported by secondary
documentation, such as code examples, or presentations), it's valid to call
"acc_get_cuda_stream"/"acc_set_cuda_stream" also with "acc_async_sync",
"acc_async_noval" arguments, not just with the nonnegative values as currently
implemented.
libgomp/
PR libgomp/88370
* libgomp.texi (acc_get_current_cuda_context, acc_get_cuda_stream)
(acc_set_cuda_stream): Clarify.
* oacc-cuda.c (acc_get_cuda_stream, acc_set_cuda_stream): Use
"async_valid_p".
* plugin/plugin-nvptx.c (nvptx_set_cuda_stream): Refuse "async ==
acc_async_sync".
* testsuite/libgomp.oacc-c-c++-common/acc_set_cuda_stream-1.c: New file.
* testsuite/libgomp.oacc-c-c++-common/async_queue-1.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/lib-84.c: Update.
* testsuite/libgomp.oacc-c-c++-common/lib-85.c: Likewise.
From-SVN: r267147
|
|
libgomp/
* plugin/plugin-nvptx.c (struct cuda_map): New.
(struct ptx_stream): Replace d, h, h_begin, h_end, h_next, h_prev,
h_tail with (cuda_map *) map.
(cuda_map_create): New function.
(cuda_map_destroy): New function.
(map_init): Update to use a linked list of cuda_map objects.
(map_fini): Likewise.
(map_pop): Likewise.
(map_push): Likewise. Return CUdeviceptr instead of void.
(init_streams_for_device): Remove stales references to ptx_stream
members.
(select_stream_for_async): Likewise.
(nvptx_exec): Update call to map_init.
From-SVN: r264397
|
|
The CUDA driver API starting version 6.5 offers a set of runtime functions to
calculate several occupancy-related measures, as a replacement for the occupancy
calculator spreadsheet.
This patch adds a heuristic for default runtime launch geometry, based on the
new runtime function cuOccupancyMaxPotentialBlockSize.
Build on x86_64 with nvptx accelerator and ran libgomp testsuite.
2018-08-13 Cesar Philippidis <cesar@codesourcery.com>
Tom de Vries <tdevries@suse.de>
PR target/85590
* plugin/cuda/cuda.h (CUoccupancyB2DSize): New typedef.
(cuOccupancyMaxPotentialBlockSize): Declare.
* plugin/cuda-lib.def (cuOccupancyMaxPotentialBlockSize): New
CUDA_ONE_CALL_MAYBE_NULL.
* plugin/plugin-nvptx.c (CUDA_VERSION < 6050): Define
CUoccupancyB2DSize and declare
cuOccupancyMaxPotentialBlockSize.
(nvptx_exec): Use cuOccupancyMaxPotentialBlockSize to set the
default num_gangs and num_workers when the driver supports it.
Co-Authored-By: Tom de Vries <tdevries@suse.de>
From-SVN: r263505
|
|
Cuda driver api functions cuLinkAddData and cuLinkCreate are available starting
version 5.5. In version 6.5, they are remapped onto _v2 versions.
The dlopen interface of the libgomp nvptx plugin uses the _v2 versions, so it
won't work with a cuda driver with driver api version lower than 6.5.
This patch fixes the problem by testing for the presence of the _v2 versions,
and falling back to the original versions in case of absence of the _v2
versions.
Build on x86_64 with nvptx accelerator and reg-tested libgomp, both with and
without --without-cuda-driver.
2018-08-08 Tom de Vries <tdevries@suse.de>
* plugin/cuda-lib.def (cuLinkAddData_v2, cuLinkCreate_v2): Declare using
CUDA_ONE_CALL_MAYBE_NULL.
* plugin/plugin-nvptx.c (cuLinkAddData, cuLinkCreate): Undef and declare.
(cuLinkAddData_v2, cuLinkCreate_v2): Declare.
(link_ptx): Fall back to cuLinkAddData/cuLinkCreate if the _v2 versions
are not found.
From-SVN: r263408
|
|
Cuda driver api function cuGetErrorString is available in version 6.0 and
higher.
Currently, when the driver that is used does not contain this function, the
libgomp nvptx plugin will not build (PLUGIN_NVPTX_DYNAMIC == 0) or run
(PLUGIN_NVPTX_DYNAMIC == 1).
This patch fixes this problem by testing for the presence of the function, and
handling absence.
Build on x86_64 with nvptx accelerator and reg-tested libgomp, both with and
without --without-cuda-driver.
2018-08-08 Tom de Vries <tdevries@suse.de>
* plugin/cuda-lib.def (cuGetErrorString): Use CUDA_ONE_CALL_MAYBE_NULL.
* plugin/plugin-nvptx.c (cuda_error): Handle if cuGetErrorString is not
present.
From-SVN: r263407
|
|
CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR is defined in cuda driver
api version 6.0 and higher.
Currently nvptx_open_device uses a hard-coded constant instead.
This patch fixes that by:
- defining CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR to the hardcoded
constant at toplevel, if not present in cuda.h, and
- using CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR in nvptx_open_device
Build on x86_64 with nvptx accelerator and reg-tested libgomp.
2018-08-08 Tom de Vries <tdevries@suse.de>
* plugin/plugin-nvptx.c
(CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR): Define.
(nvptx_open_device): Use
CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR.
From-SVN: r263406
|
|
Cuda driver api function cuGetErrorString is available in version 6.0 and
higher.
This patch:
- removes a comment saying the declaration is not available in cuda.h 6.0
- fixes the presence test to use CUDA_VERSION < 6000
- moves the declaration to toplevel
Build on x86_64 with nvptx accelerator and reg-tested libgomp.
2018-08-08 Tom de Vries <tdevries@suse.de>
* plugin/plugin-nvptx.c (cuda_error): Move declaration of cuGetErrorString ...
(cuGetErrorString): ... here. Guard with CUDA_VERSION < 6000.
From-SVN: r263405
|
