[PATCH] D73114: AMDGPU/GlobalISel: Improve legalization of wide stores

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: kerbowa, nhaehnle.
Herald added subscribers: Petar.Avramovic, hiraditya, t-tye, tpr, dstuttard, rovka, yaxunl, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.
arsenm added parent revisions: D73113: GlobalISel: Support widening unmerge results with pointer source, D73111: GlobalISel: Reimplement widenScalar for G_UNMERGE_VALUES results.

This fixes legalizations of global stores > 128-bits. It seems work is
needed on how this split actually occurs. For example, we get the
right code for s160, with an s128 and s32 load, but get 5 s32 loads
for <5 x s32>.


https://reviews.llvm.org/D73114

Files:
  llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-store-global.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D73114.239338.patch
Type: text/x-patch
Size: 504319 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200121/56a93218/attachment-0001.bin>