projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 5dfec67) | patch
[AMDGPU] Simplify scavenging in indirectCopyToAGPR
authorJay Foad <jay.foad@amd.com>
Wed, 17 May 2023 13:15:02 +0000 (14:15 +0100)
committerJay Foad <jay.foad@amd.com>
Mon, 22 May 2023 10:55:26 +0000 (11:55 +0100)
commit3c0d81d43fd75ca89fdf59c4887afe6908ffb35e
treef19900eab92d61c082cd96fa93619102d005bf3ctree | snapshot
parent5dfec676c3ab4fa2b7ea95d203f97faf7768b77fcommit | diff
[AMDGPU] Simplify scavenging in indirectCopyToAGPR

This just makes it clearer that we do not want the scavenger to spill
here. NFCI.

Differential Revision: https://reviews.llvm.org/D150774
llvm/lib/Target/AMDGPU/SIInstrInfo.cpp diff | blob | history
Domain: System / Toolchain;