[PATCH] D109228: [AMDGPU][GlobalISel] Legalize G_MUL for non-standard types

[Mateja Marjanovic via Phabricator via llvm-commits]

matejam created this revision.
matejam added reviewers: foad, arsenm, mbrkusanin, Petar.Avramovic.
matejam added a project: LLVM.
Herald added subscribers: kerbowa, hiraditya, t-tye, tpr, dstuttard, rovka, yaxunl, nhaehnle, jvesely, kzhuravl.
matejam requested review of this revision.
Herald added a subscriber: wdng.

Legalizing G_MUL for non-standard types (like i33) generated an error.
Putting widenScalarToNextPow2() before clampScalar() in AMGPULegalizerInfo.cpp solves the problem.


https://reviews.llvm.org/D109228

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

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D109228.370552.patch
Type: text/x-patch
Size: 23366 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210903/e4dfd8ff/attachment-0001.bin>