- Apr 11, 2024
-
-
Alexey Bataev authored
If the operands of the potentially alternate node are going to produce buildvector sequences, which result in more instructions, than the original code, then suhinstructions should be vectorized as alternate node, better to end up with the buildvector node. Left column - experimental, Right - reference. Metric: size..text Program size..text results results0 diff test-suite :: SingleSource/Benchmarks/Adobe-C++/loop_unroll.test 413680.00 416272.00 0.6% test-suite :: External/SPEC/CFP2017rate/526.blender_r/526.blender_r.test 12351788.00 12354844.00 0.0% test-suite :: External/SPEC/CINT2017speed/625.x264_s/625.x264_s.test 664901.00 664949.00 0.0% test-suite :: External/SPEC/CINT2017rate/525.x264_r/525.x264_r.test 664901.00 664949.00 0.0% test-suite :: External/SPEC/CFP2017rate/511.povray_r/511.povray_r.test 1171371.00 1171355.00 -0.0% test-suite :: MultiSource/Benchmarks/7zip/7zip-benchmark.test 1036396.00 1036284.00 -0.0% test-suite :: MultiSource/Benchmarks/MiBench/consumer-jpeg/consumer-jpeg.test 111280.00 111248.00 -0.0% test-suite :: External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r.test 1392113.00 1391361.00 -0.1% test-suite :: External/SPEC/CFP2017speed/638.imagick_s/638.imagick_s.test 1392113.00 1391361.00 -0.1% test-suite :: MultiSource/Benchmarks/Prolangs-C/TimberWolfMC/timberwolfmc.test 281676.00 281452.00 -0.1% test-suite :: MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes.test 3025.00 3019.00 -0.2% test-suite :: MultiSource/Benchmarks/Prolangs-C/plot2fig/plot2fig.test 6351.00 6335.00 -0.3% Metric: SLP.NumVectorInstructions Program SLP.NumVectorInstructions results results0 diff test-suite :: MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes.test 15.00 16.00 6.7% test-suite :: External/SPEC/CINT2017rate/525.x264_r/525.x264_r.test 1703.00 1707.00 0.2% test-suite :: External/SPEC/CINT2017speed/625.x264_s/625.x264_s.test 1703.00 1707.00 0.2% test-suite :: External/SPEC/CFP2017rate/526.blender_r/526.blender_r.test 26241.00 26239.00 -0.0% test-suite :: External/SPEC/CFP2017rate/510.parest_r/510.parest_r.test 11761.00 11754.00 -0.1% test-suite :: MultiSource/Benchmarks/Prolangs-C/TimberWolfMC/timberwolfmc.test 824.00 822.00 -0.2% test-suite :: External/SPEC/CFP2017speed/638.imagick_s/638.imagick_s.test 5668.00 5654.00 -0.2% test-suite :: External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r.test 5668.00 5654.00 -0.2% test-suite :: External/SPEC/CINT2017rate/502.gcc_r/502.gcc_r.test 792.00 790.00 -0.3% test-suite :: External/SPEC/CINT2017speed/602.gcc_s/602.gcc_s.test 792.00 790.00 -0.3% test-suite :: MultiSource/Benchmarks/FreeBench/pifft/pifft.test 1389.00 1384.00 -0.4% test-suite :: MultiSource/Benchmarks/7zip/7zip-benchmark.test 596.00 590.00 -1.0% test-suite :: MultiSource/Benchmarks/Prolangs-C/plot2fig/plot2fig.test 6.00 5.00 -16.7% Metric: exec_time Program exec_time results results0 diff test-suite :: External/SPEC/CFP2017rate/526.blender_r/526.blender_r.test 99.14 100.00 0.9% Other changes are not significant (less than 0.1% percent with exectime less 5 secs). SingleSource/Benchmarks/Adobe-C++/loop_unroll - same small patterns remain scalar, smaller code. External/SPEC/CFP2017rate/526.blender_r/526.blender_r - many small changes, some extra stores gets vectorized. External/SPEC/CINT2017speed/625.x264_s/625.x264_s External/SPEC/CINT2017rate/525.x264_r/525.x264_r x264 has one change in a loop body, in function ssim_end4, some code remain scalar, resulting in less code size. External/SPEC/CFP2017rate/511.povray_r/511.povray_r - some extra code gets vectorized, looks like some other patterns were matched. MultiSource/Benchmarks/7zip/7zip-benchmark - extra stores were vectorized (looks like the graphs become profitable) MultiSource/Benchmarks/MiBench/consumer-jpeg/consumer-jpeg - small changes in vectorized code (some small part remain scalar). External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r External/SPEC/CFP2017speed/638.imagick_s/638.imagick_s Many changes cause by the fact that the code of one function becomes smaller (onvertLCHabToRGB) and this functions gets inlined after that. MultiSource/Benchmarks/Prolangs-C/TimberWolfMC/timberwolfmc - some small changes here and there, some extra code is vectorized, some remain scalar (2 x vectors) MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes - emits 2 scalars + 2 insertelems instead of insert, broadcast, alt code (3 instructions, total 5 insts) MultiSource/Benchmarks/Prolangs-C/plot2fig/plot2fig - small graph becomes profitable and gets vectorized. External/SPEC/CINT2017rate/502.gcc_r/502.gcc_r External/SPEC/CINT2017speed/602.gcc_s/602.gcc_s Some small graph becomes profitable and gets vectorized. MultiSource/Benchmarks/FreeBench/pifft/pifft - no changes in final code. Reviewers: RKSimon, dtcxzyw Reviewed By: RKSimon Pull Request: https://github.com/llvm/llvm-project/pull/84978 -
Noah Goldstein authored
Handles cases like `X ^ Y == X` / `X disjoint| Y == X`. Both of these cases have identical logic to the existing `add` case, so just converting the `add` code to a more general helper. Proofs: https://alive2.llvm.org/ce/z/Htm7pe Closes #87706
-
Noah Goldstein authored
-
Noah Goldstein authored
This strengthens our `isKnownNonEqual` logic with some fairly trivial cases. Proofs: https://alive2.llvm.org/ce/z/4pxRTj Closes #87705
-
Noah Goldstein authored
-
Noah Goldstein authored
Inserts don't modify the data, so if all elements that end up in the destination are non-zero the result is non-zero. Closes #87703
-
Noah Goldstein authored
-
Noah Goldstein authored
Shuffles don't modify the data, so if all elements that end up in the destination are non-zero the result is non-zero. Closes #87702
-
Noah Goldstein authored
-
Kevin P. Neal authored
Correct a strictfp test to follow the rules documented in the LangRef: https://llvm.org/docs/LangRef.html#constrained-floating-point-intrinsics This test needed the strictfp attribute added to a function definition. Test changes verified with D146845.
-
martinboehme authored
Previously, we were propagating storage locations the other way around, i.e. from initializers to result objects, using `RecordValue::getLoc()`. This gave the wrong behavior in some cases -- see the newly added or fixed tests in this patch. In addition, this patch now unblocks removing the `RecordValue` class entirely, as we no longer need `RecordValue::getLoc()`. With this patch, the test `TransferTest.DifferentReferenceLocInJoin` started to fail because the framework now always uses the same storge location for a `MaterializeTemporaryExpr`, meaning that the code under test no longer set up the desired state where a variable of reference type is mapped to two different storage locations in environments being joined. Rather than trying to modify this test to set up the test condition again, I have chosen to replace the test with an equivalent test in DataflowEnvironmentTest.cpp that sets up the test condition directly; because this test is more direct, it will also be less brittle in the face of future changes.
-
Aaron Ballman authored
'int' may not be sufficiently large to store a pointer representation anyway, so this is also a correctness fix.
-
Jun Wang authored
This patch introduces a new command-line option for clang, namely, amdgpu-precise-mem-op (or precise-memory in the backend). When this option is specified, a waitcnt instruction is generated after each memory load/store instruction. The counter values are always 0, but which counters are involved depends on the memory instruction. --------- Co-authored-by:Jun Wang <jun.wang7@amd.com>
-
Craig Topper authored
[RISCV] Remove interrupt handler special case from RISCVFrameLowering::determineCalleeSaves. (#88069) This code was trying to save temporary argument registers in interrupt handler functions that contain calls. With the exception that all FP registers are saved including the normally callee saved registers. If all of the callees use an FP ABI and the interrupt handler doesn't touch the normally callee saved FP registers, we don't need to save them. It doesn't appear that we need to special case functions with calls. The normal callee saved register handling will already check each of the calls and consider a register clobbered if the call doesn't explicitly say it is preserved. All of the test changes are from the removal of the FP callee saved registers. There are tests for interrupt handlers with F and D extension that use ilp32 or lp64 ABIs that are not affected by this change. They still save the FP callee saved registers as they should. gcc appears to have a bug where the D extension being enabled with the ilp32f or lp64f ABI does not save the FP callee saved regs. The callee would only save/restore the lower 32 bits and clobber the upper bits. LLVM saves the FP callee saved regs in this case and there is an unchanged test for it. The unnecessary save/restore was raised in this thread https://discourse.llvm.org/t/has-bugs-when-optimizing-save-restore-csrs-by-changing-csr-xlen-f32-interrupt/78200/1
-
higher-performance authored
Avoids the need to linearly re-scan all seen parent nodes to check for duplicates, which previously caused a slowdown for ancestry checks in Clang AST matchers. Fixes: #86881
-
Kojo Acquah authored
Patterns in `LowerContractionToSMMLAPattern` are designed to handle vector-to-matrix multiplication but not matrix-to-vector. This leads to the following error when processing `rhs` with rank < 2: ``` iree-compile: /usr/local/google/home/kooljblack/code/iree-build/llvm-project/tools/mlir/include/mlir/IR/BuiltinTypeInterfaces.h.inc:268: int64_t mlir::detail::ShapedTypeTrait<mlir::VectorType>::getDimSize(unsigned int) const [ConcreteType = mlir::VectorType]: Assertion `idx < getRank() && "invalid index for shaped type"' failed. ``` Updates to explicitly check the rhs rank and fail cases that cannot process.
-
David Green authored
-
Vyacheslav Levytskyy authored
This PR is a small improvement of parsing of base type name in builtins, allowing to understand `unsigned ...` types. The test case that fails without the fix is attached.
-
Simon Pilgrim authored
-
Aart Bik authored
The doc and examples of the [dis]assemble operations did not reflect all the recent changes on order of the operands. Also clarified some of the text.
-
erichkeane authored
This was added while we only had a partial implementation of clauses, so we don't need these anymore.
-
erichkeane authored
I missed these two in my last patch as the two patches crossed in review, so correct this now.
-
Mehdi Amini authored
Reverts llvm/llvm-project#88260 The test fails on the GCC7 buildbot.
-
Evgenii Stepanov authored
-
Craig Topper authored
We recently optimized the code when the Odd vector was undef to fix a poison bug. There are additional optimizations we can do if the even vector is undef. With Zvbb, we can use a single vwsll. Without Zvbb, we can use a vzext.vf2 and a vsll.
-
Jan Svoboda authored
When writing out a PCM, we compute the set of module maps that did affect the compilation and we strip the rest to make the output independent of them. The most common way to read a module map that is not affecting is with implicit module map search. The other option is to pass a bunch of unnecessary `-fmodule-map-file=<path>` arguments on the command-line, in which case the client should probably not give those to Clang anyway. This makes serialization of explicit modules faster, mostly due to reduced file system traffic.
-
Jan Svoboda authored
This makes it so that the importer doesn't need to stat all input files of a module that contain diagnostic pragmas, reducing file system traffic.
-
- Apr 10, 2024
-
-
Mark de Wever authored
With the release of Clang-18 we no longer officially support Clang-16.
-
Jordan Rupprecht authored
This test just checks for the stdout/stderr of clang, but it incidentally tries to write to `a.out` in the current directory, which may be write protected. Typically one would write `clang -o %t.o` for a writeable dir, but since we only care about stdout/stderr, throw away the object file and just write to /dev/null instead.
-
Krzysztof Parzyszek authored
This should work the same way as in clang.
-
Noah Goldstein authored
Instead of relying on known-bits for strictly positive, use the `isKnownPositive` API. This will use `isKnownNonZero` which is more accurate. Closes #88170
-
Noah Goldstein authored
-
Noah Goldstein authored
Adds support for: `{s,u}{add,sub,mul}.with.overflow` The logic is identical to the the non-overflow binops, we where just missing the cases. Closes #87701 -
Noah Goldstein authored
-
Noah Goldstein authored
-
Noah Goldstein authored
Previously missing. We compute by just applying the reduce function on the knownbits of each element. Closes #88169
-
Noah Goldstein authored
Previously missing, proofs for all implementations: https://alive2.llvm.org/ce/z/G8wpmG
-
Noah Goldstein authored
-
Craig Topper authored
[RISCV] Add MachineCombiner to fold (sh3add Z, (add X, (slli Y, 6))) -> (sh3add (sh3add Y, Z), X). (#87884) This improves a pattern that occurs in 531.deepsjeng_r. Reducing the dynamic instruction count by 0.5%. This may be possible to improve in SelectionDAG, but given the special cases around shXadd formation, it's not obvious it can be done in a robust way without adding multiple special cases. I've used a GEP with 2 indices because that mostly closely resembles the motivating case. Most of the test cases are the simplest GEP case. One test has a logical right shift on an index which is closer to the deepsjeng code. This requires special handling in isel to reverse a DAGCombiner canonicalization that turns a pair of shifts into (srl (and X, C1), C2).
-
Alexey Bataev authored
If the first node is a gather node with extractelement instructions, still need to put the vector value after all instructions, not after the very first one.
-
