AMDGPU: Move AMDGPUAttributor run earlier

[arsenm]

Summary

Move it up with other module passes. It's a higher level optimization
that should probably be done before hacking up the IR for codegen. It
should really be done earlier than this. We could possibly move this
with other IPO passes, but we'd have to stop inferring the lack of
lds.kernel.id calls and have the LDS module pass mark functions which
don't need the ID.

The one test change is because that pass is relying on the backend run
of SROA (which we ideally wouldn't have).

[Pierre-vh]

llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll

46–48

nit: Do you know why there's more registers being used?
We go up to s31 for the call at the end so I guess the SGPR usage is the same overall, I'm just wondering.

[arsenm]

llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll

46–48

This is what the change description referenced. Since InferAddressSpaces/SROA no longer eliminate the cast and alloca, it doesn't figure out it can turn off all the inputs

[arsenm]

d7d4aa539c0d2f80c080a3b1e0fa45a78d5e9bfc

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

void AMDGPUPassConfig::addIRPasses() {
   // Replace OpenCL enqueued block function pointers with global variables.
   addPass(createAMDGPUOpenCLEnqueuedBlockLoweringPass());
 
   // Runs before PromoteAlloca so the latter can account for function uses
   if (EnableLowerModuleLDS) {
     addPass(createAMDGPULowerModuleLDSPass());
   }
 
+  // AMDGPUAttributor infers lack of llvm.amdgcn.lds.kernel.id calls, so run
+  // after their introduction
+  if (TM.getOptLevel() > CodeGenOpt::None)
+    addPass(createAMDGPUAttributorPass());
+
   if (TM.getOptLevel() > CodeGenOpt::None)
     addPass(createInferAddressSpacesPass());
 
   addPass(createAtomicExpandPass());
 
   if (TM.getOptLevel() > CodeGenOpt::None) {
     addPass(createAMDGPUPromoteAlloca());
 
if (isPassEnabled(EnableScalarIRPasses))
     addEarlyCSEOrGVNPass();
 }
 
 void AMDGPUPassConfig::addCodeGenPrepare() {
   if (TM->getTargetTriple().getArch() == Triple::amdgcn) {
     if (RemoveIncompatibleFunctions)
       addPass(createAMDGPURemoveIncompatibleFunctionsPass(TM));
 
-    if (TM->getOptLevel() > CodeGenOpt::None)
-      addPass(createAMDGPUAttributorPass());
-
     // FIXME: This pass adds 2 hacky attributes that can be replaced with an
     // analysis, and should be removed.
     addPass(createAMDGPUAnnotateKernelFeaturesPass());
   }
 
   if (TM->getTargetTriple().getArch() == Triple::amdgcn &&
       EnableLowerKernelArguments)
     addPass(createAMDGPULowerKernelArgumentsPass());

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

 ; GCN-O1-NEXT:    AMDGPU Printf lowering
 ; GCN-O1-NEXT:      FunctionPass Manager
 ; GCN-O1-NEXT:        Dominator Tree Construction
 ; GCN-O1-NEXT:    Lower ctors and dtors for AMDGPU
 ; GCN-O1-NEXT:    FunctionPass Manager
 ; GCN-O1-NEXT:      Early propagate attributes from kernels to functions
 ; GCN-O1-NEXT:    Lower OpenCL enqueued blocks
 ; GCN-O1-NEXT:    Lower uses of LDS variables from non-kernel functions
+; GCN-O1-NEXT:    AMDGPU Attributor
+; GCN-O1-NEXT:      FunctionPass Manager
+; GCN-O1-NEXT:        Cycle Info Analysis
 ; GCN-O1-NEXT:    FunctionPass Manager
 ; GCN-O1-NEXT:      Infer address spaces
 ; GCN-O1-NEXT:      Expand Atomic instructions
 ; GCN-O1-NEXT:      AMDGPU Promote Alloca
 ; GCN-O1-NEXT:      Dominator Tree Construction
 ; GCN-O1-NEXT:      SROA
 ; GCN-O1-NEXT:      Cycle Info Analysis
 ; GCN-O1-NEXT:      Uniformity Analysis

 ; GCN-O1-NEXT:      Replace intrinsics with calls to vector library
 ; GCN-O1-NEXT:      Partially inline calls to library functions
 ; GCN-O1-NEXT:      Expand vector predication intrinsics
 ; GCN-O1-NEXT:      Scalarize Masked Memory Intrinsics
 ; GCN-O1-NEXT:      Expand reduction intrinsics
 ; GCN-O1-NEXT:      Natural Loop Information
 ; GCN-O1-NEXT:      TLS Variable Hoist
 ; GCN-O1-NEXT:    AMDGPU Remove Incompatible Functions
-; GCN-O1-NEXT:    AMDGPU Attributor
-; GCN-O1-NEXT:      FunctionPass Manager
-; GCN-O1-NEXT:        Cycle Info Analysis
 ; GCN-O1-NEXT:    CallGraph Construction
 ; GCN-O1-NEXT:    Call Graph SCC Pass Manager
 ; GCN-O1-NEXT:      AMDGPU Annotate Kernel Features
 ; GCN-O1-NEXT:      FunctionPass Manager
 ; GCN-O1-NEXT:        AMDGPU Lower Kernel Arguments
 ; GCN-O1-NEXT:        Dominator Tree Construction
 ; GCN-O1-NEXT:        Natural Loop Information
 ; GCN-O1-NEXT:        CodeGen Prepare

 ; GCN-O1-OPTS-NEXT:    AMDGPU Printf lowering
 ; GCN-O1-OPTS-NEXT:      FunctionPass Manager
 ; GCN-O1-OPTS-NEXT:        Dominator Tree Construction
 ; GCN-O1-OPTS-NEXT:    Lower ctors and dtors for AMDGPU
 ; GCN-O1-OPTS-NEXT:    FunctionPass Manager
 ; GCN-O1-OPTS-NEXT:      Early propagate attributes from kernels to functions
 ; GCN-O1-OPTS-NEXT:    Lower OpenCL enqueued blocks
 ; GCN-O1-OPTS-NEXT:    Lower uses of LDS variables from non-kernel functions
+; GCN-O1-OPTS-NEXT:    AMDGPU Attributor
+; GCN-O1-OPTS-NEXT:      FunctionPass Manager
+; GCN-O1-OPTS-NEXT:        Cycle Info Analysis
 ; GCN-O1-OPTS-NEXT:    FunctionPass Manager
 ; GCN-O1-OPTS-NEXT:      Infer address spaces
 ; GCN-O1-OPTS-NEXT:      Expand Atomic instructions
 ; GCN-O1-OPTS-NEXT:      AMDGPU Promote Alloca
 ; GCN-O1-OPTS-NEXT:      Dominator Tree Construction
 ; GCN-O1-OPTS-NEXT:      SROA
 ; GCN-O1-OPTS-NEXT:      Natural Loop Information
 ; GCN-O1-OPTS-NEXT:      Scalar Evolution Analysis

 ; GCN-O1-OPTS-NEXT:      Partially inline calls to library functions
 ; GCN-O1-OPTS-NEXT:      Expand vector predication intrinsics
 ; GCN-O1-OPTS-NEXT:      Scalarize Masked Memory Intrinsics
 ; GCN-O1-OPTS-NEXT:      Expand reduction intrinsics
 ; GCN-O1-OPTS-NEXT:      Natural Loop Information
 ; GCN-O1-OPTS-NEXT:      TLS Variable Hoist
 ; GCN-O1-OPTS-NEXT:      Early CSE
 ; GCN-O1-OPTS-NEXT:    AMDGPU Remove Incompatible Functions
-; GCN-O1-OPTS-NEXT:    AMDGPU Attributor
-; GCN-O1-OPTS-NEXT:      FunctionPass Manager
-; GCN-O1-OPTS-NEXT:        Cycle Info Analysis
 ; GCN-O1-OPTS-NEXT:    CallGraph Construction
 ; GCN-O1-OPTS-NEXT:    Call Graph SCC Pass Manager
 ; GCN-O1-OPTS-NEXT:      AMDGPU Annotate Kernel Features
 ; GCN-O1-OPTS-NEXT:      FunctionPass Manager
 ; GCN-O1-OPTS-NEXT:        AMDGPU Lower Kernel Arguments
 ; GCN-O1-OPTS-NEXT:        Dominator Tree Construction
 ; GCN-O1-OPTS-NEXT:        Natural Loop Information
 ; GCN-O1-OPTS-NEXT:        CodeGen Prepare

 ; GCN-O2-NEXT:    AMDGPU Printf lowering
 ; GCN-O2-NEXT:      FunctionPass Manager
 ; GCN-O2-NEXT:        Dominator Tree Construction
 ; GCN-O2-NEXT:    Lower ctors and dtors for AMDGPU
 ; GCN-O2-NEXT:    FunctionPass Manager
 ; GCN-O2-NEXT:      Early propagate attributes from kernels to functions
 ; GCN-O2-NEXT:    Lower OpenCL enqueued blocks
 ; GCN-O2-NEXT:    Lower uses of LDS variables from non-kernel functions
+; GCN-O2-NEXT:    AMDGPU Attributor
+; GCN-O2-NEXT:      FunctionPass Manager
+; GCN-O2-NEXT:        Cycle Info Analysis
 ; GCN-O2-NEXT:    FunctionPass Manager
 ; GCN-O2-NEXT:      Infer address spaces
 ; GCN-O2-NEXT:      Expand Atomic instructions
 ; GCN-O2-NEXT:      AMDGPU Promote Alloca
 ; GCN-O2-NEXT:      Dominator Tree Construction
 ; GCN-O2-NEXT:      SROA
 ; GCN-O2-NEXT:      Natural Loop Information
 ; GCN-O2-NEXT:      Scalar Evolution Analysis

 ; GCN-O2-NEXT:      Partially inline calls to library functions
 ; GCN-O2-NEXT:      Expand vector predication intrinsics
 ; GCN-O2-NEXT:      Scalarize Masked Memory Intrinsics
 ; GCN-O2-NEXT:      Expand reduction intrinsics
 ; GCN-O2-NEXT:      Natural Loop Information
 ; GCN-O2-NEXT:      TLS Variable Hoist
 ; GCN-O2-NEXT:      Early CSE
 ; GCN-O2-NEXT:    AMDGPU Remove Incompatible Functions
-; GCN-O2-NEXT:    AMDGPU Attributor
-; GCN-O2-NEXT:      FunctionPass Manager
-; GCN-O2-NEXT:        Cycle Info Analysis
 ; 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:        Dominator Tree Construction
 ; GCN-O2-NEXT:        Natural Loop Information
 ; GCN-O2-NEXT:        CodeGen Prepare

 ; GCN-O3-NEXT:    AMDGPU Printf lowering
 ; GCN-O3-NEXT:      FunctionPass Manager
 ; GCN-O3-NEXT:        Dominator Tree Construction
 ; GCN-O3-NEXT:    Lower ctors and dtors for AMDGPU
 ; GCN-O3-NEXT:    FunctionPass Manager
 ; GCN-O3-NEXT:      Early propagate attributes from kernels to functions
 ; GCN-O3-NEXT:    Lower OpenCL enqueued blocks
 ; GCN-O3-NEXT:    Lower uses of LDS variables from non-kernel functions
+; GCN-O3-NEXT:    AMDGPU Attributor
+; GCN-O3-NEXT:      FunctionPass Manager
+; GCN-O3-NEXT:        Cycle Info Analysis
 ; GCN-O3-NEXT:    FunctionPass Manager
 ; GCN-O3-NEXT:      Infer address spaces
 ; GCN-O3-NEXT:      Expand Atomic instructions
 ; GCN-O3-NEXT:      AMDGPU Promote Alloca
 ; GCN-O3-NEXT:      Dominator Tree Construction
 ; GCN-O3-NEXT:      SROA
 ; GCN-O3-NEXT:      Natural Loop Information
 ; GCN-O3-NEXT:      Scalar Evolution Analysis

 ; GCN-O3-NEXT:      Basic Alias Analysis (stateless AA impl)
 ; GCN-O3-NEXT:      Function Alias Analysis Results
 ; GCN-O3-NEXT:      Memory Dependence Analysis
 ; GCN-O3-NEXT:      Lazy Branch Probability Analysis
 ; GCN-O3-NEXT:      Lazy Block Frequency Analysis
 ; GCN-O3-NEXT:      Optimization Remark Emitter
 ; GCN-O3-NEXT:      Global Value Numbering
 ; GCN-O3-NEXT:    AMDGPU Remove Incompatible Functions
-; GCN-O3-NEXT:    AMDGPU Attributor
-; GCN-O3-NEXT:      FunctionPass Manager
-; GCN-O3-NEXT:        Cycle Info Analysis
 ; 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:        Dominator Tree Construction
 ; GCN-O3-NEXT:        Natural Loop Information
 ; GCN-O3-NEXT:        CodeGen Prepare

llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll

 ; ATTRIBUTOR_GCN-NEXT:    store ptr @indirect, ptr [[FPTR_CAST]], align 8
 ; ATTRIBUTOR_GCN-NEXT:    [[FP:%.*]] = load ptr, ptr [[FPTR_CAST]], align 8
 ; ATTRIBUTOR_GCN-NEXT:    call void [[FP]]()
 ; ATTRIBUTOR_GCN-NEXT:    ret void
 ;
 ; GFX9-LABEL: test_simple_indirect_call:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x4
-; GFX9-NEXT:    s_add_u32 flat_scratch_lo, s6, s9
-; GFX9-NEXT:    s_addc_u32 flat_scratch_hi, s7, 0
-; GFX9-NEXT:    s_add_u32 s0, s0, s9
+; GFX9-NEXT:    s_add_u32 flat_scratch_lo, s12, s17
+; GFX9-NEXT:    s_addc_u32 flat_scratch_hi, s13, 0
+; GFX9-NEXT:    s_add_u32 s0, s0, s17
 ; GFX9-NEXT:    s_addc_u32 s1, s1, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    s_lshr_b32 s4, s4, 16
 ; GFX9-NEXT:    s_mul_i32 s4, s4, s5
 ; GFX9-NEXT:    v_mul_lo_u32 v0, s4, v0
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
 ; GFX9-NEXT:    s_add_u32 s6, s6, indirect@rel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s7, s7, indirect@rel32@hi+12