[DirectX] Set Shader Flag DisableOptimizations

clang/lib/CodeGen/CGHLSLRuntime.cpp

@@ -54,10 +54,6 @@ void addDxilValVersion(StringRef ValVersionStr, llvm::Module &M) {
   auto *DXILValMD = M.getOrInsertNamedMetadata(DXILValKey);
   DXILValMD->addOperand(Val);
 }
-void addDisableOptimizations(llvm::Module &M) {
-  StringRef Key = "dx.disable_optimizations";
-  M.addModuleFlag(llvm::Module::ModFlagBehavior::Override, Key, 1);
-}
 // cbuffer will be translated into global variable in special address space.
 // If translate into C,
 // cbuffer A {
@@ -171,8 +167,6 @@ void CGHLSLRuntime::finishCodeGen() {
     addDxilValVersion(TargetOpts.DxilValidatorVersion, M);
 
   generateGlobalCtorDtorCalls();
-  if (CGM.getCodeGenOpts().OptimizationLevel == 0)
-    addDisableOptimizations(M);
 
   const DataLayout &DL = M.getDataLayout();
 

llvm/lib/Target/DirectX/DXILShaderFlags.cpp

@@ -17,6 +17,8 @@
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/Analysis/DXILResource.h"
+#include "llvm/IR/Attributes.h"
+#include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
@@ -96,7 +98,8 @@ void ModuleShaderFlags::updateFunctionFlags(ComputedShaderFlags &CSF,
 }
 
 /// Construct ModuleShaderFlags for module Module M
-void ModuleShaderFlags::initialize(Module &M, DXILResourceTypeMap &DRTM) {
+void ModuleShaderFlags::initialize(Module &M, DXILResourceTypeMap &DRTM,
+                                   const ModuleMetadataInfo &MMDI) {
   CallGraph CG(M);
 
   // Compute Shader Flags Mask for all functions using post-order visit of SCC
@@ -142,6 +145,20 @@ void ModuleShaderFlags::initialize(Module &M, DXILResourceTypeMap &DRTM) {
       // Merge SCCSF with that of F
       FunctionFlags[F].merge(SCCSF);
   }
+
+  // Set DisableOptimizations flag based on the presence of OptimizeNone
+  // attribute of entry functions.
+  if (MMDI.EntryPropertyVec.size() > 0) {
+    CombinedSFMask.DisableOptimizations =
+        MMDI.EntryPropertyVec[0].Entry->hasFnAttribute(
+            llvm::Attribute::OptimizeNone);
+    // Ensure all entry functions have the same optimization attribute
+    for (auto EF : MMDI.EntryPropertyVec)
+      if (CombinedSFMask.DisableOptimizations !=
+          EF.Entry->hasFnAttribute(llvm::Attribute::OptimizeNone))
+        EF.Entry->getContext().diagnose(DiagnosticInfoUnsupported(
+            *(EF.Entry), "Inconsistent optnone attribute "));
+  }
 }
 
 void ComputedShaderFlags::print(raw_ostream &OS) const {
@@ -180,9 +197,10 @@ AnalysisKey ShaderFlagsAnalysis::Key;
 ModuleShaderFlags ShaderFlagsAnalysis::run(Module &M,
                                            ModuleAnalysisManager &AM) {
   DXILResourceTypeMap &DRTM = AM.getResult<DXILResourceTypeAnalysis>(M);
+  const ModuleMetadataInfo MMDI = AM.getResult<DXILMetadataAnalysis>(M);
 
   ModuleShaderFlags MSFI;
-  MSFI.initialize(M, DRTM);
+  MSFI.initialize(M, DRTM, MMDI);
 
   return MSFI;
 }
@@ -212,20 +230,24 @@ PreservedAnalyses ShaderFlagsAnalysisPrinter::run(Module &M,
 bool ShaderFlagsAnalysisWrapper::runOnModule(Module &M) {
   DXILResourceTypeMap &DRTM =
       getAnalysis<DXILResourceTypeWrapperPass>().getResourceTypeMap();
+  const ModuleMetadataInfo MMDI =
+      getAnalysis<DXILMetadataAnalysisWrapperPass>().getModuleMetadata();
 
-  MSFI.initialize(M, DRTM);
+  MSFI.initialize(M, DRTM, MMDI);
   return false;
 }
 
 void ShaderFlagsAnalysisWrapper::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.setPreservesAll();
   AU.addRequiredTransitive<DXILResourceTypeWrapperPass>();
+  AU.addRequired<DXILMetadataAnalysisWrapperPass>();
 }
 
 char ShaderFlagsAnalysisWrapper::ID = 0;
 
 INITIALIZE_PASS_BEGIN(ShaderFlagsAnalysisWrapper, "dx-shader-flag-analysis",
                       "DXIL Shader Flag Analysis", true, true)
 INITIALIZE_PASS_DEPENDENCY(DXILResourceTypeWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(DXILMetadataAnalysisWrapperPass)
 INITIALIZE_PASS_END(ShaderFlagsAnalysisWrapper, "dx-shader-flag-analysis",
                     "DXIL Shader Flag Analysis", true, true)

llvm/lib/Target/DirectX/DXILShaderFlags.h

@@ -14,6 +14,7 @@
 #ifndef LLVM_TARGET_DIRECTX_DXILSHADERFLAGS_H
 #define LLVM_TARGET_DIRECTX_DXILSHADERFLAGS_H
 
+#include "llvm/Analysis/DXILMetadataAnalysis.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
@@ -83,7 +84,8 @@ struct ComputedShaderFlags {
 };
 
 struct ModuleShaderFlags {
-  void initialize(Module &, DXILResourceTypeMap &DRTM);
+  void initialize(Module &, DXILResourceTypeMap &DRTM,
+                  const ModuleMetadataInfo &MMDI);
   const ComputedShaderFlags &getFunctionFlags(const Function *) const;
   const ComputedShaderFlags &getCombinedFlags() const { return CombinedSFMask; }
 

llvm/test/CodeGen/DirectX/ShaderFlags/disable-opt-cs.ll

@@ -0,0 +1,43 @@
+; RUN: opt -S --passes="print-dx-shader-flags" 2>&1 %s | FileCheck %s
+
+
+; CHECK: ; Combined Shader Flags for Module
+; CHECK-NEXT: ; Shader Flags Value: 0x00000001
+
+; CHECK: ; Note: extra DXIL module flags:
+; CHECK-NEXT: ;       D3D11_1_SB_GLOBAL_FLAG_SKIP_OPTIMIZATION
+
+; CHECK: ; Shader Flags for Module Functions
+; CHECK: ; Function main : 0x00000000
+; The test source in this file generated from the following command:
+; clang -cc1 -triple dxil-pc-shadermodel6.0-compute -x hlsl -emit-llvm -O0 -o - <<EOF
+; [numthreads(1,1,1)]
+; [shader("compute")]
+; void main() {}
+; EOF
+
+; ModuleID = '-'
+source_filename = "-"
+target datalayout = "e-m:e-p:32:32-i1:32-i8:8-i16:16-i32:32-i64:64-f16:16-f32:32-f64:64-n8:16:32:64"
+target triple = "dxilv1.0-pc-shadermodel6.0-compute"
+
+; Function Attrs: convergent noinline norecurse optnone
+define void @main() #0 {
+entry:
+  ret void
+}
+
+; Function Attrs: alwaysinline convergent mustprogress norecurse nounwind
+define noundef i32 @_Z3foov() #1 {
+entry:
+  ret i32 0
+}
+
+attributes #0 = { convergent noinline norecurse optnone "approx-func-fp-math"="true" "hlsl.numthreads"="1,1,1" "hlsl.shader"="compute" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+attributes #1 = { alwaysinline convergent mustprogress norecurse nounwind "approx-func-fp-math"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+
+!llvm.module.flags = !{!0}
+!dx.valver = !{!1}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 1, i32 8}

llvm/test/CodeGen/DirectX/ShaderFlags/disable-opt-lib.ll

@@ -0,0 +1,53 @@
+; RUN: opt -S --passes="print-dx-shader-flags" 2>&1 %s | FileCheck %s
+
+
+; CHECK: ; Combined Shader Flags for Module
+; CHECK-NEXT: ; Shader Flags Value: 0x00000001
+
+; CHECK: ; Note: extra DXIL module flags:
+; CHECK-NEXT: ;       D3D11_1_SB_GLOBAL_FLAG_SKIP_OPTIMIZATION
+
+; CHECK: ; Shader Flags for Module Functions
+; CHECK: ; Function main : 0x00000000
+; The test source in this file generated from the following command:
+; clang -cc1 -triple dxil-pc-shadermodel6.3-library -x hlsl -emit-llvm -O0 -o - <<EOF
+
+; [numthreads(1,1,1)]
+; [shader("compute")]
+; void main() {}
+
+; int foo() {return 0;}
+; EOF
+
+; ModuleID = '-'
+source_filename = "-"
+target datalayout = "e-m:e-p:32:32-i1:32-i8:8-i16:16-i32:32-i64:64-f16:16-f32:32-f64:64-n8:16:32:64"
+target triple = "dxilv1.3-pc-shadermodel6.3-library"
+
+; Function Attrs: convergent mustprogress noinline norecurse nounwind optnone
+define internal void @_Z4mainv() #0 {
+entry:
+  ret void
+}
+
+; Function Attrs: convergent noinline norecurse optnone
+define void @main() #1 {
+entry:
+  call void @_Z4mainv()
+  ret void
+}
+
+; Function Attrs: convergent mustprogress noinline norecurse nounwind optnone
+define noundef i32 @_Z3foov() #0 {
+entry:
+  ret i32 0
+}
+
+attributes #0 = { convergent mustprogress noinline norecurse nounwind optnone "approx-func-fp-math"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+attributes #1 = { convergent noinline norecurse optnone "approx-func-fp-math"="true" "hlsl.numthreads"="1,1,1" "hlsl.shader"="compute" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+
+!llvm.module.flags = !{!0}
+!dx.valver = !{!1}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 1, i32 8}

llvm/test/CodeGen/DirectX/ShaderFlags/lib-entry-attr-error.ll

@@ -0,0 +1,30 @@
+; RUN: not opt -S --passes="print-dx-shader-flags" 2>&1 %s | FileCheck %s
+
+target triple = "dxilv1.3-pc-shadermodel6.3-library"
+
+; All entry functions of a library shader need to either have optnone
+; or not have the attribute
+; CHECK: error:
+; CHECK-SAME: in function entry_two
+; CHECK-SAME:  Inconsistent optnone attribute
+; Function Attrs: convergent noinline norecurse optnone
+define void @entry_one() #0 {
+entry:
+  ret void
+}
+
+; Function Attrs: convergent noinline norecurse
+define void @entry_two() #1 {
+entry:
+  ret void
+}
+
+attributes #0 = { convergent noinline norecurse optnone "approx-func-fp-math"="true" "hlsl.numthreads"="1,1,1" "hlsl.shader"="compute" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+attributes #1 = { convergent noinline norecurse "approx-func-fp-math"="true" "hlsl.numthreads"="1,1,1" "hlsl.shader"="compute" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+
+!llvm.module.flags = !{!0, !1}
+!dx.valver = !{!2}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 4, !"dx.disable_optimizations", i32 1}
+!2 = !{i32 1, i32 8}

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

@@ -23,8 +23,8 @@
 ; CHECK-NEXT:     Scalarize vector operations
 ; CHECK-NEXT:   DXIL Resource Binding Analysis
 ; CHECK-NEXT:   DXIL resource Information
-; CHECK-NEXT:   DXIL Shader Flag Analysis
 ; CHECK-NEXT:   DXIL Module Metadata analysis
+; CHECK-NEXT:   DXIL Shader Flag Analysis
 ; CHECK-NEXT:   DXIL Translate Metadata
 ; CHECK-NEXT:   DXIL Op Lowering
 ; CHECK-NEXT:   DXIL Prepare Module