R600: Use a refined heuristic to choose when switching clause

This is using a hint from AMD APP OpenCL Programming Guide with
empirically tweaked parameters.
I used Unigine Heaven 3.0 to determine best parameters on my system
(i7 2600/Radeon 6950/Kernel 3.9.4) the benchmark :
it went from 38.8 average fps to 39.6, which is ~3% gain.
(Lightmark 2008.2 gain is much more marginal: from 537 to 539)

There is no lit test provided as the parameter were determined
empirically and it it would be nearly impossiblet to find a test
program that check for optimal behavior.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183593 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 4 insertions, 1 deletions

diff --git a/lib/Target/R600/R600MachineScheduler.h b/lib/Target/R600/R600MachineScheduler.h
index c5024d2492..aae8b3f4eb 100644
--- a/lib/Target/R600/R600MachineScheduler.h
+++ b/lib/Target/R600/R600MachineScheduler.h
@@ -60,6 +60,9 @@ class R600SchedStrategy : public MachineSchedStrategy {
   int CurEmitted;
   InstKind NextInstKind;
 
+  unsigned AluInstCount;
+  unsigned FetchInstCount;
+
   int InstKindLimit[IDLast];
 
   int OccupedSlotsMask;
@@ -85,7 +88,7 @@ private:
   bool regBelongsToClass(unsigned Reg, const TargetRegisterClass *RC) const;
   AluKind getAluKind(SUnit *SU) const;
   void LoadAlu();
-  bool isAvailablesAluEmpty() const;
+  unsigned AvailablesAluCount() const;
   SUnit *AttemptFillSlot (unsigned Slot);
   void PrepareNextSlot();
   SUnit *PopInst(std::vector<SUnit*> &Q);