[PATCH] D141168: AMDGPU: Don't assert on printf of half

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: sameerds, AMDGPU, vikramRH.
Herald added subscribers: kosarev, foad, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
arsenm requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.

The comment says fields should be 4-byte aligned, so just pass through
after conversion to integer. The conformance test lacks any testing of
half.


https://reviews.llvm.org/D141168

Files:
  llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
  llvm/test/CodeGen/AMDGPU/opencl-printf.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D141168.487008.patch
Type: text/x-patch
Size: 14553 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230107/12f5791a/attachment.bin>