projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 42ad9bf) | patch
[AMDGPU][InsertWaits] No wait for WAW for global/scratch_load
authorRuiling Song <ruiling.song@amd.com>
Mon, 21 Nov 2022 07:33:18 +0000 (15:33 +0800)
committerRuiling Song <ruiling.song@amd.com>
Wed, 23 Nov 2022 01:57:50 +0000 (09:57 +0800)
commit0eaf6759aee92fa27efb78a97405195869c67bb0
tree78d66e6c0157e86366135a6dd93c2d9eb5b890c2tree | snapshot
parent42ad9bf95fd5cb30e2ab3e017b6718ac6efea1becommit | diff
[AMDGPU][InsertWaits] No wait for WAW for global/scratch_load

global/scratch_load will return in order they are issued. No
need to insert a s_waitcnt for WAW hazard.

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D138476
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/GlobalISel/implicit-kernarg-backend-usage-global-isel.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/extract-subvector-16bit.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/implicit-kernarg-backend-usage.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/vector_shuffle.packed.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/waitcnt-vmem-waw.mir diff | blob | history
Domain: System / Toolchain;