SuccessChanges

Summary

  1. [X86][BtVer2] Improved latency and throughput of float/vector loads and (details)
  2. Fixing typo in llvm/IR/Intrinsics.td (details)
  3. [AMDGPU] Come back patch for the 'Assign register class for cross block (details)
  4. Revert "Add a pass to lower is.constant and objectsize intrinsics" (details)
Commit b744abb4f6a94926b1ed15b9c3bf56bce9aae28d by Andrea_DiBiagio
[X86][BtVer2] Improved latency and throughput of float/vector loads and
stores.
This patch introduces the following changes to the btver2 scheduling
model:
- The number of micro opcodes for YMM loads and stores is now 2 (it was
incorrectly set to 1 for both aligned and misaligned loads/stores).
- Increased the number of AGU resource cycles for YMM loads and stores
to 2cy (instead of 1cy).
- Removed JFPU01 and JFPX from the list of resources consumed by pure
float/vector loads (no MMX).
I verified with llvm-exegesis that pure XMM/YMM loads are no-pipe. Those
are dispatched to the FPU but not really issues on JFPU01.
Differential Revision: https://reviews.llvm.org/D68871
llvm-svn: 374765
The file was modifiedllvm/test/tools/llvm-mca/X86/BtVer2/resources-avx1.s
The file was modifiedllvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-3.s
The file was modifiedllvm/test/tools/llvm-mca/X86/BtVer2/load-store-alias.s
The file was modifiedllvm/test/tools/llvm-mca/X86/BtVer2/memcpy-like-test.s
The file was modifiedllvm/test/tools/llvm-mca/X86/BtVer2/resources-sse2.s
The file was modifiedllvm/test/tools/llvm-mca/X86/BtVer2/resources-sse1.s
The file was modifiedllvm/test/tools/llvm-mca/X86/BtVer2/resources-sse3.s
The file was modifiedllvm/lib/Target/X86/X86ScheduleBtVer2.td
Commit d34822ad4c42867ccdd24f8e50d57b37a7969680 by victor.campos
Fixing typo in llvm/IR/Intrinsics.td
Fixing typo in comment line.
llvm-svn: 374766
The file was modifiedllvm/include/llvm/IR/Intrinsics.td
Commit c4d256a59049d4b2f21da83f43b9caba2427885e by Alexander.Timofeev
[AMDGPU] Come back patch for the 'Assign register class for cross block
values according to the divergence.'
  Detailed description:
    After https://reviews.llvm.org/D59990 submit several issues were
discovered.
   Changes in common code were preserved but AMDGPU specific part was
reverted to keep the backend working correctly.
    Discovered issues were addressed in the following commits:
    https://reviews.llvm.org/D67662
   https://reviews.llvm.org/D67101
   https://reviews.llvm.org/D63953
   https://reviews.llvm.org/D63731
    This change brings back AMDGPU specific changes.
  Reviewed by: rampitec, arsenm
  Differential Revision: https://reviews.llvm.org/D68635
llvm-svn: 374767
The file was modifiedllvm/test/CodeGen/AMDGPU/multilevel-break.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/atomicrmw-nand.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/si-annotate-cf.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/sgpr-control-flow.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/fmin_legacy.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/llvm.amdgcn.qsad.pk.u16.u8.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/llvm.amdgcn.mqsad.pk.u16.u8.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/branch-relaxation.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/fabs.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll
The file was modifiedllvm/lib/Target/AMDGPU/SIISelLowering.h
The file was modifiedllvm/test/CodeGen/AMDGPU/extract_subvector_vec4_vec3.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/fdiv32-to-rcp-folding.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/implicit-def-muse.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/smrd.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/branch-uniformity.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/fneg.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/insert_vector_elt.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/llvm.amdgcn.div.scale.ll
The file was modifiedllvm/lib/Target/AMDGPU/SIISelLowering.cpp
The file was modifiedllvm/test/CodeGen/AMDGPU/control-flow-fastregalloc.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/fneg-fabs.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/fsub.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/si-fix-sgpr-copies.mir
The file was modifiedllvm/test/CodeGen/AMDGPU/loop_break.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/buffer-intrinsics-mmo-offsets.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/i1-copy-phi-uniform-branch.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/select-opt.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot-compute.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/uniform-loop-inside-nonuniform.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/valu-i1.ll
The file was modifiedllvm/lib/Target/AMDGPU/SIInstrInfo.cpp
The file was modifiedllvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
The file was modifiedllvm/test/CodeGen/AMDGPU/sgpr-copy.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/i1-copy-from-loop.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/use-sgpr-multiple-times.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/commute-shifts.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/subreg-coalescer-undef-use.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/llvm.amdgcn.fmed3.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/copy-illegal-type.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/wave32.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/cse-phi-incoming-val.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/madak.ll
Commit 1a21f98ac3c57d027908000b8bac356daec51416 by gribozavr
Revert "Add a pass to lower is.constant and objectsize intrinsics"
This reverts commit r374743. It broke the build with Ocaml enabled:
http://lab.llvm.org:8011/builders/clang-x86_64-debian-fast/builds/19218
llvm-svn: 374768
The file was modifiedllvm/lib/CodeGen/SelectionDAG/FastISel.cpp
The file was modifiedllvm/lib/CodeGen/TargetPassConfig.cpp
The file was modifiedllvm/include/llvm-c/Transforms/Scalar.h
The file was modifiedllvm/test/CodeGen/AArch64/O3-pipeline.ll
The file was addedllvm/test/CodeGen/Generic/is-constant.ll
The file was removedllvm/include/llvm/Transforms/Scalar/LowerConstantIntrinsics.h
The file was modifiedllvm/lib/Passes/PassRegistry.def
The file was modifiedllvm/test/Other/new-pm-thinlto-defaults.ll
The file was modifiedllvm/lib/Transforms/Scalar/Scalar.cpp
The file was modifiedllvm/test/CodeGen/X86/O3-pipeline.ll
The file was modifiedllvm/bindings/ocaml/transforms/scalar_opts/llvm_scalar_opts.mli
The file was addedllvm/test/Transforms/CodeGenPrepare/crash-on-large-allocas.ll
The file was modifiedllvm/test/CodeGen/ARM/O3-pipeline.ll
The file was removedllvm/test/Transforms/LowerConstantIntrinsics/constant-intrinsics.ll
The file was removedllvm/test/Transforms/LowerConstantIntrinsics/objectsize_basic.ll
The file was modifiedllvm/bindings/ocaml/transforms/scalar_opts/scalar_opts_ocaml.c
The file was modifiedllvm/test/Other/opt-Os-pipeline.ll
The file was modifiedllvm/include/llvm/Transforms/Scalar.h
The file was modifiedllvm/utils/gn/secondary/llvm/lib/Transforms/Scalar/BUILD.gn
The file was addedllvm/test/Transforms/CodeGenPrepare/builtin-condition.ll
The file was modifiedllvm/lib/Transforms/IPO/PassManagerBuilder.cpp
The file was modifiedllvm/test/CodeGen/X86/O0-pipeline.ll
The file was modifiedllvm/lib/CodeGen/CodeGenPrepare.cpp
The file was addedllvm/test/CodeGen/X86/is-constant.ll
The file was modifiedllvm/test/Other/opt-O2-pipeline.ll
The file was modifiedllvm/lib/Transforms/Scalar/CMakeLists.txt
The file was modifiedllvm/include/llvm/LinkAllPasses.h
The file was modifiedllvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
The file was modifiedllvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
The file was modifiedllvm/lib/Passes/PassBuilder.cpp
The file was addedllvm/test/CodeGen/X86/object-size.ll
The file was modifiedllvm/test/Transforms/CodeGenPrepare/X86/overflow-intrinsics.ll
The file was removedllvm/test/Transforms/LowerConstantIntrinsics/crash-on-large-allocas.ll
The file was modifiedllvm/test/CodeGen/AArch64/O0-pipeline.ll
The file was modifiedllvm/include/llvm/InitializePasses.h
The file was modifiedllvm/test/Other/opt-O3-pipeline.ll
The file was removedllvm/lib/Transforms/Scalar/LowerConstantIntrinsics.cpp
The file was modifiedllvm/test/Other/new-pm-defaults.ll
The file was addedllvm/test/Transforms/CodeGenPrepare/basic.ll
The file was modifiedllvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll