[PATCH] D124246: [AMDGPU] Adjust wave priority based on VMEM instructions to avoid duty-cycling.
Jay Foad via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Apr 22 04:57:49 PDT 2022
foad added inline comments.
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSetWavePriority.cpp:31
+static cl::opt<bool>
+ DisableSetWavePriority("amdgpu-disable-set-wave-priority",
+ cl::desc("Disable adjusting wave priority"),
----------------
It's a bit more normal to put "Enable" options in AMDGPUTargetMachine, where you can use isPassEnabled.
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSetWavePriority.cpp:122
+bool AMDGPUSetWavePriority::runOnMachineFunction(MachineFunction &MF) {
+ const unsigned HighPriority = 3;
+ const unsigned LowPriority = 0;
----------------
Should bail out early if skipFunction(MF.getFunction()), to help with bisecting optimization problems.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D124246/new/
https://reviews.llvm.org/D124246
More information about the llvm-commits
mailing list