[PATCH] D128346: [AMDGPU] Report minimum scratch size in code object v5 and later by default
Abinav Puthan Purayil via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Sep 26 04:16:56 PDT 2022
abinavpp updated this revision to Diff 462861.
abinavpp retitled this revision from "[AMDGPU] Disable the private segment size fallback to 16k" to "[AMDGPU] Report minimum scratch size in code object v5 and later by default".
abinavpp edited the summary of this revision.
abinavpp added a comment.
- Get the new scratch reporting specific to v5+ as per internal discussion
- Not removing the -amdgpu-assume-* options now; Might need this when we run into problems
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D128346/new/
https://reviews.llvm.org/D128346
Files:
llvm/docs/AMDGPUUsage.rst
llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll
llvm/test/CodeGen/AMDGPU/non-entry-alloca.ll
llvm/test/CodeGen/AMDGPU/recursion.ll
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D128346.462861.patch
Type: text/x-patch
Size: 8342 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220926/81b1ab02/attachment-0001.bin>
More information about the llvm-commits
mailing list