[PATCH] D81172: [AMDGPU] Implement hardware bug workaround for image instructions

[Rodrigo Dominguez via Phabricator via llvm-commits]

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

This implements a workaround for a hardware bug in gfx8 and gfx9,
where register usage is not estimated correctly for image_store and
image_gather4 instructions when D16 <https://reviews.llvm.org/D16> is used.

Change-Id: I4e30744da6796acac53a9b5ad37ac1c2035c8899


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D81172

Files:
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/lib/Target/AMDGPU/SIISelLowering.h
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.d16.dim.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.gather4.d16.dim.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D81172.268499.patch
Type: text/x-patch
Size: 11634 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200604/52112ba1/attachment.bin>