[AMDGPU] Move perfhint analysis

[rampitec]

Summary

This is SCC pass, moving it to the end of SCC PM saves one
Function PM. This needs the analysis to take into account
memory access width since it is now places after the
load/store optimizer (D105651).

[rampitec]

Rebased.

[foad]

This looks fine once D105651 is accepted.

[rampitec]

Rebased.

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

 void AMDGPUPassConfig::addCodeGenPrepare() {
   if (TM->getTargetTriple().getArch() == Triple::amdgcn)
     addPass(createAMDGPUAnnotateKernelFeaturesPass());
 
   if (TM->getTargetTriple().getArch() == Triple::amdgcn &&
       EnableLowerKernelArguments)
     addPass(createAMDGPULowerKernelArgumentsPass());
 
-  if (TM->getOptLevel() > CodeGenOpt::Less)
-    addPass(&AMDGPUPerfHintAnalysisID);
-
   TargetPassConfig::addCodeGenPrepare();
 
   if (isPassEnabled(EnableLoadStoreVectorizer))
     addPass(createLoadStoreVectorizerPass());
 
   // LowerSwitch pass may introduce unreachable blocks that can
   // cause unexpected behavior for subsequent passes. Placing it
   // here seems better that these blocks would get cleaned up by
if (!LateCFGStructurize) {
     addPass(createStructurizeCFGPass(false)); // true -> SkipUniformRegions
   }
   addPass(createAMDGPUAnnotateUniformValues());
   if (!LateCFGStructurize) {
     addPass(createSIAnnotateControlFlowPass());
   }
   addPass(createLCSSAPass());
 
+  if (TM->getOptLevel() > CodeGenOpt::Less)
+    addPass(&AMDGPUPerfHintAnalysisID);
+
   return false;
 }
 
 void GCNPassConfig::addMachineSSAOptimization() {
   TargetPassConfig::addMachineSSAOptimization();
 
   // We want to fold operands after PeepholeOptimizer has run (or as part of
   // it), because it will eliminate extra copies making it easier to fold the

llvm/test/CodeGen/AMDGPU/llc-pipeline.ll

 ; GCN-O2-NEXT:      Scalarize Masked Memory Intrinsics
 ; GCN-O2-NEXT:      Expand reduction intrinsics
 ; GCN-O2-NEXT:      Early CSE
 ; GCN-O2-NEXT:    CallGraph Construction
 ; GCN-O2-NEXT:    Call Graph SCC Pass Manager
 ; GCN-O2-NEXT:      AMDGPU Annotate Kernel Features
 ; GCN-O2-NEXT:      FunctionPass Manager
 ; GCN-O2-NEXT:        AMDGPU Lower Kernel Arguments
-; GCN-O2-NEXT:      Analysis if a function is memory bound
-; GCN-O2-NEXT:      FunctionPass Manager
 ; GCN-O2-NEXT:        Dominator Tree Construction
 ; GCN-O2-NEXT:        Natural Loop Information
 ; GCN-O2-NEXT:        CodeGen Prepare
 ; GCN-O2-NEXT:        Dominator Tree Construction
 ; GCN-O2-NEXT:        Basic Alias Analysis (stateless AA impl)
 ; GCN-O2-NEXT:        Function Alias Analysis Results
 ; GCN-O2-NEXT:        Natural Loop Information
 ; GCN-O2-NEXT:        Scalar Evolution Analysis

 ; GCN-O2-NEXT:        Legacy Divergence Analysis
 ; GCN-O2-NEXT:        Basic Alias Analysis (stateless AA impl)
 ; GCN-O2-NEXT:        Function Alias Analysis Results
 ; GCN-O2-NEXT:        Memory SSA
 ; GCN-O2-NEXT:        AMDGPU Annotate Uniform Values
 ; GCN-O2-NEXT:        SI annotate control flow
 ; GCN-O2-NEXT:        LCSSA Verifier
 ; GCN-O2-NEXT:        Loop-Closed SSA Form Pass
+; GCN-O2-NEXT:      Analysis if a function is memory bound
 ; GCN-O2-NEXT:      DummyCGSCCPass
 ; GCN-O2-NEXT:      FunctionPass Manager
 ; GCN-O2-NEXT:        Safe Stack instrumentation pass
 ; GCN-O2-NEXT:        Insert stack protectors
 ; GCN-O2-NEXT:        Dominator Tree Construction
 ; GCN-O2-NEXT:        Post-Dominator Tree Construction
 ; GCN-O2-NEXT:        Natural Loop Information
 ; GCN-O2-NEXT:        Legacy Divergence Analysis

 ; GCN-O3-NEXT:      Lazy Block Frequency Analysis
 ; GCN-O3-NEXT:      Optimization Remark Emitter
 ; GCN-O3-NEXT:      Global Value Numbering
 ; GCN-O3-NEXT:    CallGraph Construction
 ; GCN-O3-NEXT:    Call Graph SCC Pass Manager
 ; GCN-O3-NEXT:      AMDGPU Annotate Kernel Features
 ; GCN-O3-NEXT:      FunctionPass Manager
 ; GCN-O3-NEXT:        AMDGPU Lower Kernel Arguments
-; GCN-O3-NEXT:      Analysis if a function is memory bound
-; GCN-O3-NEXT:      FunctionPass Manager
 ; GCN-O3-NEXT:        Dominator Tree Construction
 ; GCN-O3-NEXT:        Natural Loop Information
 ; GCN-O3-NEXT:        CodeGen Prepare
 ; GCN-O3-NEXT:        Dominator Tree Construction
 ; GCN-O3-NEXT:        Basic Alias Analysis (stateless AA impl)
 ; GCN-O3-NEXT:        Function Alias Analysis Results
 ; GCN-O3-NEXT:        Natural Loop Information
 ; GCN-O3-NEXT:        Scalar Evolution Analysis

 ; GCN-O3-NEXT:        Legacy Divergence Analysis
 ; GCN-O3-NEXT:        Basic Alias Analysis (stateless AA impl)
 ; GCN-O3-NEXT:        Function Alias Analysis Results
 ; GCN-O3-NEXT:        Memory SSA
 ; GCN-O3-NEXT:        AMDGPU Annotate Uniform Values
 ; GCN-O3-NEXT:        SI annotate control flow
 ; GCN-O3-NEXT:        LCSSA Verifier
 ; GCN-O3-NEXT:        Loop-Closed SSA Form Pass
+; GCN-O3-NEXT:      Analysis if a function is memory bound
 ; GCN-O3-NEXT:      DummyCGSCCPass
 ; GCN-O3-NEXT:      FunctionPass Manager
 ; GCN-O3-NEXT:        Safe Stack instrumentation pass
 ; GCN-O3-NEXT:        Insert stack protectors
 ; GCN-O3-NEXT:        Dominator Tree Construction
 ; GCN-O3-NEXT:        Post-Dominator Tree Construction
 ; GCN-O3-NEXT:        Natural Loop Information
 ; GCN-O3-NEXT:        Legacy Divergence Analysis