[PATCH] D78622: [AMDGPU] Use SGPR instead of SReg classes

Jay Foad via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Apr 22 03:12:49 PDT 2020


foad created this revision.
foad added reviewers: arsenm, rampitec, kerbowa.
Herald added subscribers: llvm-commits, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

12994a70cf7 did this for 128-bit classes:

  SGPR_128 only includes the real allocatable SGPRs, and SReg_128 adds
  the additional non-allocatable TTMP registers. There's no point in
  allocating SReg_128 vregs. This shrinks the size of the classes
  regalloc needs to consider, which is usually good.

This patch extends it to all classes > 64 bits, for consistency.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D78622

Files:
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
  llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
  llvm/lib/Target/AMDGPU/SIRegisterInfo.td
  llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-concat-vectors.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-extract-vector-elt.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-extract.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-implicit-def.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-insert-vector-elt.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-insert.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-merge-values.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-trunc.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-unmerge-values.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.s.buffer.load.ll
  llvm/test/CodeGen/AMDGPU/coalescer-subranges-another-copymi-not-live.mir
  llvm/test/CodeGen/AMDGPU/coalescer-subranges-another-prune-error.mir
  llvm/test/CodeGen/AMDGPU/coalescer-subreg-join.mir
  llvm/test/CodeGen/AMDGPU/coalescer-with-subregs-bad-identical.mir
  llvm/test/CodeGen/AMDGPU/memory_clause.mir
  llvm/test/CodeGen/AMDGPU/merge-image-load.mir
  llvm/test/CodeGen/AMDGPU/merge-image-sample.mir
  llvm/test/CodeGen/AMDGPU/optimize-exec-masking-pre-ra.mir
  llvm/test/CodeGen/AMDGPU/subreg-split-live-in-error.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D78622.259219.patch
Type: text/x-patch
Size: 190079 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200422/f689d32c/attachment-0001.bin>


More information about the llvm-commits mailing list