[PATCH] D68338: [AMDGPU] Remove dubious logic in bidirectional list scheduler

Jay Foad via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Fri Feb 28 02:37:42 PST 2020


foad marked an inline comment as done.
foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp:252
-      Cand = BotCand;
-    } else if (TopCand.Reason == RegCritical && TopCand.RPDelta.CriticalMax.getUnitInc() <= 0) {
-      Cand = TopCand;
----------------
rampitec wrote:
> Do we check for RP limits anywhere now?
Yes, we call `GenericScheduler::tryCandidate` which does this:
```
  // Avoid exceeding the target's limit.
  if (DAG->isTrackingPressure() && tryPressure(TryCand.RPDelta.Excess,
                                               Cand.RPDelta.Excess,
                                               TryCand, Cand, RegExcess, TRI,
                                               DAG->MF))
    return;

  // Avoid increasing the max critical pressure in the scheduled region.
  if (DAG->isTrackingPressure() && tryPressure(TryCand.RPDelta.CriticalMax,
                                               Cand.RPDelta.CriticalMax,
                                               TryCand, Cand, RegCritical, TRI,
                                               DAG->MF))
    return;
```


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D68338/new/

https://reviews.llvm.org/D68338





More information about the llvm-commits mailing list