projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 6d05bc2) | patch
[AMDGPU] need to insert wait between the scalar load and vector store to the same...
authoralex-t <alexander.timofeev@amd.com>
Sat, 4 Jan 2020 15:23:14 +0000 (18:23 +0300)
committeralex-t <alexander.timofeev@amd.com>
Sat, 4 Jan 2020 15:23:14 +0000 (18:23 +0300)
commitca8b20ca3ba10288b61a083c4ce57fb011124935
tree60baa7eb6c2d7dd593da13c3b4749e3806bb9b29tree | snapshot
parent6d05bc2e3a9b54fde53aa5cbd83cc7c1d432cac1commit | diff
[AMDGPU] need to insert wait between the scalar load and vector store to the same address to avoid WAR conflict.

Reviewers: rampitec, vpykhtin, nhaehnle

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D71934
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/smrd_vmem_war.ll [new file with mode: 0644] blob
Domain: System / Toolchain;