projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 392d55c) | patch
[AMDGPU] Try to avoid inserting duplicate s_inst_prefetch
authorCarl Ritson <carl.ritson@amd.com>
Thu, 14 Apr 2022 07:06:17 +0000 (16:06 +0900)
committerCarl Ritson <carl.ritson@amd.com>
Thu, 14 Apr 2022 07:06:24 +0000 (16:06 +0900)
commit35ea326047ef1220f26dc69593db9842a7dfeec1
tree5325aa6774accec2ed36e976a65e737338b544c7tree | snapshot
parent392d55c1e2d777e9843864e1022d476599334dc9commit | diff
[AMDGPU] Try to avoid inserting duplicate s_inst_prefetch

Check for existing s_inst_prefetch instructions when
configuring prefetches during loop alignment.

Reviewed By: rampitec, foad

Differential Revision: https://reviews.llvm.org/D123569
llvm/lib/Target/AMDGPU/SIISelLowering.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll diff | blob | history
Domain: System / Toolchain;