[PATCH] D54606: [AMDGPU] Convert insert_vector_elt into set of selects

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
rampitec added a reviewer: arsenm.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.

This allows to avoid scratch use or indirect VGPR addressing for small vectors.


https://reviews.llvm.org/D54606

Files:
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIISelLowering.h
  test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll
  test/CodeGen/AMDGPU/indirect-addressing-si.ll
  test/CodeGen/AMDGPU/insert_vector_dynelt.ll
  test/CodeGen/AMDGPU/insert_vector_elt.ll
  test/CodeGen/AMDGPU/movreld-bug.ll
  test/CodeGen/AMDGPU/promote-alloca-vector-to-vector.ll
  test/CodeGen/AMDGPU/vector-extract-insert.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D54606.174295.patch
Type: text/x-patch
Size: 46768 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20181115/1548d13f/attachment.bin>