[PATCH] D47078: AMDGPU: Make v2i16/v2f16 legal on VI

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: rampitec, cfang.
Herald added subscribers: eraman, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, kzhuravl.

This usually results in better code. Fixes using
inline asm with short2, and also fixes having a different
ABI for function parameters between VI and gfx9.

     

Partially cleans up the mess used for lowering of the d16
operations. Making v4f16 legal will help clean this up more,
 but this requires additional work.


https://reviews.llvm.org/D47078

Files:
  lib/Target/AMDGPU/AMDGPU.td
  lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  lib/Target/AMDGPU/BUFInstructions.td
  lib/Target/AMDGPU/MIMGInstructions.td
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIISelLowering.h
  lib/Target/AMDGPU/SIInstructions.td
  test/CodeGen/AMDGPU/add.v2i16.ll
  test/CodeGen/AMDGPU/ashr.v2i16.ll
  test/CodeGen/AMDGPU/extract_vector_elt-i16.ll
  test/CodeGen/AMDGPU/fabs.f16.ll
  test/CodeGen/AMDGPU/fcanonicalize.f16.ll
  test/CodeGen/AMDGPU/fmax3.ll
  test/CodeGen/AMDGPU/fmin3.ll
  test/CodeGen/AMDGPU/fneg-fabs.f16.ll
  test/CodeGen/AMDGPU/fneg.f16.ll
  test/CodeGen/AMDGPU/half.ll
  test/CodeGen/AMDGPU/immv216.ll
  test/CodeGen/AMDGPU/inlineasm-illegal-type.ll
  test/CodeGen/AMDGPU/insert_vector_elt.ll
  test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
  test/CodeGen/AMDGPU/kernel-args.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.buffer.store.format.d16.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.image.d16.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.image.dim.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.store.d16.ll
  test/CodeGen/AMDGPU/llvm.fma.f16.ll
  test/CodeGen/AMDGPU/lshr.v2i16.ll
  test/CodeGen/AMDGPU/min.ll
  test/CodeGen/AMDGPU/reduction.ll
  test/CodeGen/AMDGPU/sdwa-peephole.ll
  test/CodeGen/AMDGPU/select-vectors.ll
  test/CodeGen/AMDGPU/shl.v2i16.ll
  test/CodeGen/AMDGPU/sign_extend.ll
  test/CodeGen/AMDGPU/sminmax.v2i16.ll
  test/CodeGen/AMDGPU/sub.v2i16.ll
  test/Transforms/SLPVectorizer/AMDGPU/packed-math.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D47078.147547.patch
Type: text/x-patch
Size: 136880 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180518/24071d27/attachment-0001.bin>