projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 57fa688) | patch
[AMDGPU] Relax verification of soffset in scalar stores
authorStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Tue, 28 Jun 2022 22:06:41 +0000 (15:06 -0700)
committerStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Tue, 28 Jun 2022 23:10:08 +0000 (16:10 -0700)
commit21895c6b5060d71aa4bbe619cfc3baeb1df1894b
tree52dfaf645ed1fb80182d06eee090c21c6070c1fftree | snapshot
parent57fa68897bb76e1fe5442784bca4e0629033c384commit | diff
[AMDGPU] Relax verification of soffset in scalar stores

It must use m0 only on GFX8. Later chips can use ang SGPR.

Differential Revision: https://reviews.llvm.org/D128765
llvm/lib/Target/AMDGPU/SIInstrInfo.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/verify-scalar-store.mir [new file with mode: 0644] blob
Domain: System / Toolchain;