aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/R600/R600MachineScheduler.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'lib/Target/R600/R600MachineScheduler.cpp')
-rw-r--r--lib/Target/R600/R600MachineScheduler.cpp33
1 files changed, 18 insertions, 15 deletions
diff --git a/lib/Target/R600/R600MachineScheduler.cpp b/lib/Target/R600/R600MachineScheduler.cpp
index 7ea654c..d782713 100644
--- a/lib/Target/R600/R600MachineScheduler.cpp
+++ b/lib/Target/R600/R600MachineScheduler.cpp
@@ -14,7 +14,6 @@
#include "R600MachineScheduler.h"
#include "AMDGPUSubtarget.h"
-#include "llvm/CodeGen/LiveIntervalAnalysis.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/Pass.h"
#include "llvm/PassManager.h"
@@ -76,21 +75,25 @@ SUnit* R600SchedStrategy::pickNode(bool &IsTopNode) {
float ALUFetchRationEstimate =
(AluInstCount + AvailablesAluCount() + Pending[IDAlu].size()) /
(FetchInstCount + Available[IDFetch].size());
- unsigned NeededWF = 62.5f / ALUFetchRationEstimate;
- DEBUG( dbgs() << NeededWF << " approx. Wavefronts Required\n" );
- // We assume the local GPR requirements to be "dominated" by the requirement
- // of the TEX clause (which consumes 128 bits regs) ; ALU inst before and
- // after TEX are indeed likely to consume or generate values from/for the
- // TEX clause.
- // Available[IDFetch].size() * 2 : GPRs required in the Fetch clause
- // We assume that fetch instructions are either TnXYZW = TEX TnXYZW (need
- // one GPR) or TmXYZW = TnXYZW (need 2 GPR).
- // (TODO : use RegisterPressure)
- // If we are going too use too many GPR, we flush Fetch instruction to lower
- // register pressure on 128 bits regs.
- unsigned NearRegisterRequirement = 2 * Available[IDFetch].size();
- if (NeededWF > getWFCountLimitedByGPR(NearRegisterRequirement))
+ if (ALUFetchRationEstimate == 0) {
AllowSwitchFromAlu = true;
+ } else {
+ unsigned NeededWF = 62.5f / ALUFetchRationEstimate;
+ DEBUG( dbgs() << NeededWF << " approx. Wavefronts Required\n" );
+ // We assume the local GPR requirements to be "dominated" by the requirement
+ // of the TEX clause (which consumes 128 bits regs) ; ALU inst before and
+ // after TEX are indeed likely to consume or generate values from/for the
+ // TEX clause.
+ // Available[IDFetch].size() * 2 : GPRs required in the Fetch clause
+ // We assume that fetch instructions are either TnXYZW = TEX TnXYZW (need
+ // one GPR) or TmXYZW = TnXYZW (need 2 GPR).
+ // (TODO : use RegisterPressure)
+ // If we are going too use too many GPR, we flush Fetch instruction to lower
+ // register pressure on 128 bits regs.
+ unsigned NearRegisterRequirement = 2 * Available[IDFetch].size();
+ if (NeededWF > getWFCountLimitedByGPR(NearRegisterRequirement))
+ AllowSwitchFromAlu = true;
+ }
}
if (!SU && ((AllowSwitchToAlu && CurInstKind != IDAlu) ||