Merge branch 'users/meinersbur/flang_runtime_move-files' into users/meinersbur/flang_runtime

Author: Meinersbur

.github/workflows/libc-fullbuild-tests.yml

@@ -44,7 +44,7 @@ jobs:
     - name: Prepare dependencies (Ubuntu)
       run: |
         sudo apt-get update
-        sudo apt-get install -y libmpfr-dev libgmp-dev libmpc-dev ninja-build linux-headers-generic linux-libc-dev
+        sudo apt-get install -y libmpfr-dev libgmp-dev libmpc-dev ninja-build linux-libc-dev
         sudo ln -sf /usr/include/$(uname -p)-linux-gnu/asm /usr/include/asm
 
     - name: Set reusable strings

clang/include/clang/Basic/Attr.td

@@ -4651,6 +4651,13 @@ def HLSLNumThreads: InheritableAttr {
   let Documentation = [NumThreadsDocs];
 }
 
+def HLSLSV_GroupThreadID: HLSLAnnotationAttr {
+  let Spellings = [HLSLAnnotation<"SV_GroupThreadID">];
+  let Subjects = SubjectList<[ParmVar, Field]>;
+  let LangOpts = [HLSL];
+  let Documentation = [HLSLSV_GroupThreadIDDocs];
+}
+
 def HLSLSV_GroupID: HLSLAnnotationAttr {
   let Spellings = [HLSLAnnotation<"SV_GroupID">];
   let Subjects = SubjectList<[ParmVar, Field]>;

clang/include/clang/Basic/AttrDocs.td

@@ -7941,6 +7941,17 @@ randomized.
   }];
 }
 
+def HLSLSV_GroupThreadIDDocs : Documentation {
+  let Category = DocCatFunction;
+  let Content = [{
+The ``SV_GroupThreadID`` semantic, when applied to an input parameter, specifies which
+individual thread within a thread group is executing in. This attribute is
+only supported in compute shaders.
+
+The full documentation is available here: https://docs.microsoft.com/en-us/windows/win32/direct3dhlsl/sv-groupthreadid
+  }];
+}
+
 def HLSLSV_GroupIDDocs : Documentation {
   let Category = DocCatFunction;
   let Content = [{

clang/include/clang/Sema/SemaHLSL.h

@@ -119,6 +119,7 @@ class SemaHLSL : public SemaBase {
   void handleNumThreadsAttr(Decl *D, const ParsedAttr &AL);
   void handleWaveSizeAttr(Decl *D, const ParsedAttr &AL);
   void handleSV_DispatchThreadIDAttr(Decl *D, const ParsedAttr &AL);
+  void handleSV_GroupThreadIDAttr(Decl *D, const ParsedAttr &AL);
   void handleSV_GroupIDAttr(Decl *D, const ParsedAttr &AL);
   void handlePackOffsetAttr(Decl *D, const ParsedAttr &AL);
   void handleShaderAttr(Decl *D, const ParsedAttr &AL);

clang/lib/CodeGen/CGHLSLRuntime.cpp

@@ -389,6 +389,11 @@ llvm::Value *CGHLSLRuntime::emitInputSemantic(IRBuilder<> &B,
         CGM.getIntrinsic(getThreadIdIntrinsic());
     return buildVectorInput(B, ThreadIDIntrinsic, Ty);
   }
+  if (D.hasAttr<HLSLSV_GroupThreadIDAttr>()) {
+    llvm::Function *GroupThreadIDIntrinsic =
+        CGM.getIntrinsic(getGroupThreadIdIntrinsic());
+    return buildVectorInput(B, GroupThreadIDIntrinsic, Ty);
+  }
   if (D.hasAttr<HLSLSV_GroupIDAttr>()) {
     llvm::Function *GroupIDIntrinsic = CGM.getIntrinsic(Intrinsic::dx_group_id);
     return buildVectorInput(B, GroupIDIntrinsic, Ty);

clang/lib/CodeGen/CGHLSLRuntime.h

@@ -86,6 +86,7 @@ class CGHLSLRuntime {
   GENERATE_HLSL_INTRINSIC_FUNCTION(Step, step)
   GENERATE_HLSL_INTRINSIC_FUNCTION(Radians, radians)
   GENERATE_HLSL_INTRINSIC_FUNCTION(ThreadId, thread_id)
+  GENERATE_HLSL_INTRINSIC_FUNCTION(GroupThreadId, thread_id_in_group)
   GENERATE_HLSL_INTRINSIC_FUNCTION(FDot, fdot)
   GENERATE_HLSL_INTRINSIC_FUNCTION(SDot, sdot)
   GENERATE_HLSL_INTRINSIC_FUNCTION(UDot, udot)

clang/lib/Parse/ParseHLSL.cpp

@@ -280,6 +280,7 @@ void Parser::ParseHLSLAnnotations(ParsedAttributes &Attrs,
   case ParsedAttr::UnknownAttribute:
     Diag(Loc, diag::err_unknown_hlsl_semantic) << II;
     return;
+  case ParsedAttr::AT_HLSLSV_GroupThreadID:
   case ParsedAttr::AT_HLSLSV_GroupID:
   case ParsedAttr::AT_HLSLSV_GroupIndex:
   case ParsedAttr::AT_HLSLSV_DispatchThreadID:

clang/lib/Sema/SemaDeclAttr.cpp

@@ -7114,6 +7114,9 @@ ProcessDeclAttribute(Sema &S, Scope *scope, Decl *D, const ParsedAttr &AL,
   case ParsedAttr::AT_HLSLWaveSize:
     S.HLSL().handleWaveSizeAttr(D, AL);
     break;
+  case ParsedAttr::AT_HLSLSV_GroupThreadID:
+    S.HLSL().handleSV_GroupThreadIDAttr(D, AL);
+    break;
   case ParsedAttr::AT_HLSLSV_GroupID:
     S.HLSL().handleSV_GroupIDAttr(D, AL);
     break;

clang/lib/Sema/SemaHLSL.cpp

@@ -434,6 +434,7 @@ void SemaHLSL::CheckSemanticAnnotation(
   switch (AnnotationAttr->getKind()) {
   case attr::HLSLSV_DispatchThreadID:
   case attr::HLSLSV_GroupIndex:
+  case attr::HLSLSV_GroupThreadID:
   case attr::HLSLSV_GroupID:
     if (ST == llvm::Triple::Compute)
       return;
@@ -787,6 +788,15 @@ void SemaHLSL::handleSV_DispatchThreadIDAttr(Decl *D, const ParsedAttr &AL) {
                  HLSLSV_DispatchThreadIDAttr(getASTContext(), AL));
 }
 
+void SemaHLSL::handleSV_GroupThreadIDAttr(Decl *D, const ParsedAttr &AL) {
+  auto *VD = cast<ValueDecl>(D);
+  if (!diagnoseInputIDType(VD->getType(), AL))
+    return;
+
+  D->addAttr(::new (getASTContext())
+                 HLSLSV_GroupThreadIDAttr(getASTContext(), AL));
+}
+
 void SemaHLSL::handleSV_GroupIDAttr(Decl *D, const ParsedAttr &AL) {
   auto *VD = cast<ValueDecl>(D);
   if (!diagnoseInputIDType(VD->getType(), AL))

clang/test/CodeGenHLSL/semantics/SV_GroupThreadID.hlsl

@@ -0,0 +1,36 @@
+// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.3-library -x hlsl -emit-llvm -finclude-default-header -disable-llvm-passes -o - %s | FileCheck %s --check-prefixes=CHECK,CHECK-DXIL -DTARGET=dx
+// RUN: %clang_cc1 -triple spirv-linux-vulkan-library -x hlsl -emit-llvm -finclude-default-header -disable-llvm-passes -o - %s | FileCheck %s --check-prefixes=CHECK,CHECK-SPIRV -DTARGET=spv
+
+// Make sure SV_GroupThreadID translated into dx.thread.id.in.group for directx target and spv.thread.id.in.group for spirv target.
+
+// CHECK:       define void @foo()
+// CHECK:       %[[#ID:]] = call i32 @llvm.[[TARGET]].thread.id.in.group(i32 0)
+// CHECK-DXIL:       call void @{{.*}}foo{{.*}}(i32 %[[#ID]])
+// CHECK-SPIRV:      call spir_func void @{{.*}}foo{{.*}}(i32 %[[#ID]])
+[shader("compute")]
+[numthreads(8,8,1)]
+void foo(uint Idx : SV_GroupThreadID) {}
+
+// CHECK:       define void @bar()
+// CHECK:       %[[#ID_X:]] = call i32 @llvm.[[TARGET]].thread.id.in.group(i32 0)
+// CHECK:       %[[#ID_X_:]] = insertelement <2 x i32> poison, i32 %[[#ID_X]], i64 0
+// CHECK:       %[[#ID_Y:]] = call i32 @llvm.[[TARGET]].thread.id.in.group(i32 1)
+// CHECK:       %[[#ID_XY:]] = insertelement <2 x i32> %[[#ID_X_]], i32 %[[#ID_Y]], i64 1
+// CHECK-DXIL:  call void @{{.*}}bar{{.*}}(<2 x i32> %[[#ID_XY]])
+// CHECK-SPIRV:  call spir_func void @{{.*}}bar{{.*}}(<2 x i32> %[[#ID_XY]])
+[shader("compute")]
+[numthreads(8,8,1)]
+void bar(uint2 Idx : SV_GroupThreadID) {}
+
+// CHECK:  define void @test()
+// CHECK:  %[[#ID_X:]] = call i32 @llvm.[[TARGET]].thread.id.in.group(i32 0)
+// CHECK:  %[[#ID_X_:]] = insertelement <3 x i32> poison, i32 %[[#ID_X]], i64 0
+// CHECK:  %[[#ID_Y:]] = call i32 @llvm.[[TARGET]].thread.id.in.group(i32 1)
+// CHECK:  %[[#ID_XY:]] = insertelement <3 x i32> %[[#ID_X_]], i32 %[[#ID_Y]], i64 1
+// CHECK:  %[[#ID_Z:]] = call i32 @llvm.[[TARGET]].thread.id.in.group(i32 2)
+// CHECK:  %[[#ID_XYZ:]] = insertelement <3 x i32> %[[#ID_XY]], i32 %[[#ID_Z]], i64 2
+// CHECK-DXIL:   call void @{{.*}}test{{.*}}(<3 x i32> %[[#ID_XYZ]])
+// CHECK-SPIRV:  call spir_func void @{{.*}}test{{.*}}(<3 x i32> %[[#ID_XYZ]])
+[shader("compute")]
+[numthreads(8,8,1)]
+void test(uint3 Idx : SV_GroupThreadID) {}