[llvm] r300083 - MachineScheduler: Skip acyclic latency heuristic for in-order cores

[Matthias Braun via llvm-commits]

Author: matze
Date: Wed Apr 12 13:09:05 2017
New Revision: 300083

URL: http://llvm.org/viewvc/llvm-project?rev=300083&view=rev
Log:
MachineScheduler: Skip acyclic latency heuristic for in-order cores

The current heuristic is triggered on `InFlightCount > BufferLimit`
which isn't really helpful on in-order cores where BufferLimit is zero.

Note that we already get latency hiding effects for in order cores
by instructions staying in the pending queue on stalls; The additional
latency scheduling heuristics only have minimal effects after that while
occasionally increasing register pressure too much resulting in extra
spills.

My motivation here is additional spills/reloads ending up in a loop in
464.h264ref / BlockMotionSearch function resulting in a 4% overal
regression on an in order core. rdar://30264380

Modified:
    llvm/trunk/lib/CodeGen/MachineScheduler.cpp

Modified: llvm/trunk/lib/CodeGen/MachineScheduler.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/MachineScheduler.cpp?rev=300083&r1=300082&r2=300083&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/MachineScheduler.cpp (original)
+++ llvm/trunk/lib/CodeGen/MachineScheduler.cpp Wed Apr 12 13:09:05 2017
@@ -2729,7 +2729,7 @@ void GenericScheduler::registerRoots() {
     errs() << "Critical Path(GS-RR ): " << Rem.CriticalPath << " \n";
   }
 
-  if (EnableCyclicPath) {
+  if (EnableCyclicPath && SchedModel->getMicroOpBufferSize() > 0) {
     Rem.CyclicCritPath = DAG->computeCyclicCriticalPath();
     checkAcyclicLatency();
   }