[libclc] [AMDGPU][MachineScheduler] Alternative way to control excess RP. (PR #68004)
via cfe-commits
cfe-commits at lists.llvm.org
Tue Oct 24 05:38:14 PDT 2023
================
@@ -1117,16 +1118,23 @@ bool OccInitialScheduleStage::shouldRevertScheduling(unsigned WavesAfter) {
bool UnclusteredHighRPStage::shouldRevertScheduling(unsigned WavesAfter) {
// If RP is not reduced in the unclustered reschedule stage, revert to the
// old schedule.
- if ((WavesAfter <= PressureBefore.getOccupancy(ST) &&
- mayCauseSpilling(WavesAfter)) ||
- GCNSchedStage::shouldRevertScheduling(WavesAfter)) {
- LLVM_DEBUG(dbgs() << "Unclustered reschedule did not help.\n");
- return true;
- }
+ if (DAG.RegionsWithExcessRP[RegionIdx]) {
----------------
alex-t wrote:
The higher RP is necessary for the occupancy drop so it will be reverted.
https://github.com/llvm/llvm-project/pull/68004
More information about the cfe-commits
mailing list