[PATCH] D46828: AMDGPU: Custom lower v4i16/v4f16 vector operations

[Matt Arsenault via Phabricator via llvm-commits]

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

Avoids stack access.

      

Also handle extract hi elt pattern from truncate + shift
to avoid a couple test regressions.


https://reviews.llvm.org/D46828

Files:
  lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  lib/Target/AMDGPU/AMDGPUISelLowering.h
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIISelLowering.h
  test/CodeGen/AMDGPU/extload-align.ll
  test/CodeGen/AMDGPU/extract_vector_elt-f16.ll
  test/CodeGen/AMDGPU/extract_vector_elt-i16.ll
  test/CodeGen/AMDGPU/insert_vector_elt.ll
  test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
  test/CodeGen/AMDGPU/min.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D46828.146579.patch
Type: text/x-patch
Size: 32651 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180514/acceb1bb/attachment.bin>