AMDGPU: Disable the load and store cluster mutations for the schedulers

[tstellar]

Summary

These tend to increase register usage, and I'm not sure they provide
that much benefit now that the SILoadStoreOptimizer is run before
scheduling.

shader-db results:

SGPRS: 2395408 -> 2245808 (-6.25 %)
VGPRS: 1385652 -> 1377068 (-0.62 %)
Spilled SGPRs: 13732 -> 12147 (-11.54 %)
Spilled VGPRs: 67 -> 104 (55.22 %)
Private memory VGPRs: 5872 -> 5872 (0.00 %)
Scratch size: 6848 -> 6864 (0.23 %) dwords per thread
Code Size: 57847052 -> 58209484 (0.63 %) bytes
LDS: 132 -> 132 (0.00 %) blocks
Max Waves: 470488 -> 472363 (0.40 %)
Wait states: 0 -> 0 (0.00 %)

[rampitec]

That is known clustering increases register pressure. However in our experiments it gives performance benefits by better cache utilization. Clustering might need a tuning, but not disabled.

You can add an option to disable them though.

[tstellar]

Ok, thanks for the info. I will drop this patch.

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

 static ScheduleDAGInstrs *createSIMachineScheduler(MachineSchedContext *C) {
   return new SIScheduleDAGMI(C);
 }
 
 static ScheduleDAGInstrs *
 createGCNMaxOccupancyMachineScheduler(MachineSchedContext *C) {
   ScheduleDAGMILive *DAG =
     new GCNScheduleDAGMILive(C, make_unique<GCNMaxOccupancySchedStrategy>(C));
-  DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
-  DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
   DAG->addMutation(createAMDGPUMacroFusionDAGMutation());
   return DAG;
 }
 
 static ScheduleDAGInstrs *
 createIterativeGCNMaxOccupancyMachineScheduler(MachineSchedContext *C) {
   auto DAG = new GCNIterativeScheduler(C,
     GCNIterativeScheduler::SCHEDULE_LEGACYMAXOCCUPANCY);
-  DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
-  DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
   return DAG;
 }
 
 static ScheduleDAGInstrs *createMinRegScheduler(MachineSchedContext *C) {
   return new GCNIterativeScheduler(C,
     GCNIterativeScheduler::SCHEDULE_MINREGFORCED);
 }
 
 static ScheduleDAGInstrs *
 createIterativeILPMachineScheduler(MachineSchedContext *C) {
   auto DAG = new GCNIterativeScheduler(C,
     GCNIterativeScheduler::SCHEDULE_ILP);
-  DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
-  DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
   DAG->addMutation(createAMDGPUMacroFusionDAGMutation());
   return DAG;
 }
 
 static MachineSchedRegistry
 R600SchedRegistry("r600", "Run R600's custom scheduler",
                    createR600MachineScheduler);
 
public:
 
   AMDGPUTargetMachine &getAMDGPUTargetMachine() const {
     return getTM<AMDGPUTargetMachine>();
   }
 
   ScheduleDAGInstrs *
   createMachineScheduler(MachineSchedContext *C) const override {
     ScheduleDAGMILive *DAG = createGenericSchedLive(C);
-    DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
-    DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
     return DAG;
   }
 
   void addEarlyCSEOrGVNPass();
   void addStraightLineScalarOptimizationPasses();
   void addIRPasses() override;
   void addCodeGenPrepare() override;
   bool addPreISel() override;