[PATCH] D29805: AMDGPU: Use ds_{read|write}_b128

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Feb 9 18:21:07 PST 2017


arsenm created this revision.
Herald added subscribers: tpr, tony-tye, yaxunl, nhaehnle, wdng, kzhuravl.

It's not clear to me if this is always better than
doing ds_write2_b64 This adds the constraint of
 a 128-bit register input instead of a pair of
 64-bit.


https://reviews.llvm.org/D29805

Files:
  lib/Target/AMDGPU/AMDGPUInstructions.td
  lib/Target/AMDGPU/AMDGPUSubtarget.h
  lib/Target/AMDGPU/DSInstructions.td
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIInstrInfo.td
  test/CodeGen/AMDGPU/ds_read2_superreg.ll
  test/CodeGen/AMDGPU/indirect-private-64.ll
  test/CodeGen/AMDGPU/load-local-f32.ll
  test/CodeGen/AMDGPU/load-local-f64.ll
  test/CodeGen/AMDGPU/load-local-i16.ll
  test/CodeGen/AMDGPU/load-local-i32.ll
  test/CodeGen/AMDGPU/load-local-i64.ll
  test/CodeGen/AMDGPU/load-local-i8.ll
  test/CodeGen/AMDGPU/local-64.ll
  test/CodeGen/AMDGPU/reorder-stores.ll
  test/CodeGen/AMDGPU/split-vector-memoperand-offsets.ll
  test/CodeGen/AMDGPU/store-local.ll
  test/CodeGen/AMDGPU/store-v3i64.ll
  test/MC/AMDGPU/ds.s

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D29805.87935.patch
Type: text/x-patch
Size: 56162 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170210/fe18ef11/attachment.bin>


More information about the llvm-commits mailing list