[OpenMP] codegen support for masked combined construct masked taskloop simd (#121916)

Added codegen support for combined masked constructs `masked taskloop
simd`.
Added implementation for `EmitOMPMaskedTaskLoopSimdDirective`.

Co-authored-by: Chandra Ghale <[email protected]>

Author: chandraghale

clang/lib/CodeGen/CGStmt.cpp

@@ -339,7 +339,8 @@ void CodeGenFunction::EmitStmt(const Stmt *S, ArrayRef<const Attr *> Attrs) {
         cast<OMPMasterTaskLoopSimdDirective>(*S));
     break;
   case Stmt::OMPMaskedTaskLoopSimdDirectiveClass:
-    llvm_unreachable("masked taskloop simd directive not supported yet.");
+    EmitOMPMaskedTaskLoopSimdDirective(
+        cast<OMPMaskedTaskLoopSimdDirective>(*S));
     break;
   case Stmt::OMPParallelMasterTaskLoopDirectiveClass:
     EmitOMPParallelMasterTaskLoopDirective(

clang/lib/CodeGen/CGStmtOpenMP.cpp

@@ -7994,6 +7994,18 @@ void CodeGenFunction::EmitOMPMasterTaskLoopSimdDirective(
   CGM.getOpenMPRuntime().emitMasterRegion(*this, CodeGen, S.getBeginLoc());
 }
 
+void CodeGenFunction::EmitOMPMaskedTaskLoopSimdDirective(
+    const OMPMaskedTaskLoopSimdDirective &S) {
+  auto &&CodeGen = [this, &S](CodeGenFunction &CGF, PrePostActionTy &Action) {
+    Action.Enter(CGF);
+    EmitOMPTaskLoopBasedDirective(S);
+  };
+  auto LPCRegion =
+      CGOpenMPRuntime::LastprivateConditionalRAII::disable(*this, S);
+  OMPLexicalScope Scope(*this, S);
+  CGM.getOpenMPRuntime().emitMaskedRegion(*this, CodeGen, S.getBeginLoc());
+}
+
 void CodeGenFunction::EmitOMPParallelMasterTaskLoopDirective(
     const OMPParallelMasterTaskLoopDirective &S) {
   auto &&CodeGen = [this, &S](CodeGenFunction &CGF, PrePostActionTy &Action) {

clang/lib/CodeGen/CodeGenFunction.h

@@ -3872,6 +3872,8 @@ class CodeGenFunction : public CodeGenTypeCache {
   void EmitOMPMasterTaskLoopDirective(const OMPMasterTaskLoopDirective &S);
   void
   EmitOMPMasterTaskLoopSimdDirective(const OMPMasterTaskLoopSimdDirective &S);
+  void
+  EmitOMPMaskedTaskLoopSimdDirective(const OMPMaskedTaskLoopSimdDirective &S);
   void EmitOMPParallelMasterTaskLoopDirective(
       const OMPParallelMasterTaskLoopDirective &S);
   void EmitOMPParallelMaskedTaskLoopDirective(

clang/test/OpenMP/masked_taskloop_simd_codegen.c

@@ -0,0 +1,49 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --include-generated-funcs --prefix-filecheck-ir-name _ --version 5
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fopenmp -fopenmp-version=52 -x c -emit-llvm %s -o - | FileCheck %s
+// expected-no-diagnostics
+#define N 100
+void masked_taskloop_simd(){
+	#pragma omp masked taskloop simd
+	for( int i = 0; i < N; i++)
+	;
+
+}
+
+int main()
+{
+ masked_taskloop_simd();
+}
+// CHECK-LABEL: define dso_local void @masked_taskloop_simd(
+// CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 1
+// CHECK-NEXT:    [[TMP:%.*]] = alloca i32, align 4
+// CHECK-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
+// CHECK-NEXT:    [[TMP1:%.*]] = call i32 @__kmpc_masked(ptr @[[GLOB1]], i32 [[TMP0]], i32 0)
+// CHECK-NEXT:    [[TMP2:%.*]] = icmp ne i32 [[TMP1]], 0
+// CHECK-NEXT:    br i1 [[TMP2]], label %[[OMP_IF_THEN:.*]], label %[[OMP_IF_END:.*]]
+// CHECK:       [[OMP_IF_THEN]]:
+// CHECK-NEXT:    call void @__kmpc_taskgroup(ptr @[[GLOB1]], i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP3:%.*]] = call ptr @__kmpc_omp_task_alloc(ptr @[[GLOB1]], i32 [[TMP0]], i32 1, i64 80, i64 0, ptr @.omp_task_entry.)
+// CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], ptr [[TMP3]], i32 0, i32 0
+// CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T:%.*]], ptr [[TMP4]], i32 0, i32 5
+// CHECK-NEXT:    store i64 0, ptr [[TMP5]], align 8
+// CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T]], ptr [[TMP4]], i32 0, i32 6
+// CHECK-NEXT:    store i64 99, ptr [[TMP6]], align 8
+// CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T]], ptr [[TMP4]], i32 0, i32 7
+// CHECK-NEXT:    store i64 1, ptr [[TMP7]], align 8
+// CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T]], ptr [[TMP4]], i32 0, i32 9
+// CHECK-NEXT:    call void @llvm.memset.p0.i64(ptr align 8 [[TMP8]], i8 0, i64 8, i1 false)
+// CHECK-NEXT:    [[TMP9:%.*]] = load i64, ptr [[TMP7]], align 8
+// CHECK-NEXT:    call void @__kmpc_taskloop(ptr @[[GLOB1]], i32 [[TMP0]], ptr [[TMP3]], i32 1, ptr [[TMP5]], ptr [[TMP6]], i64 [[TMP9]], i32 1, i32 0, i64 0, ptr null)
+// CHECK-NEXT:    call void @__kmpc_end_taskgroup(ptr @[[GLOB1]], i32 [[TMP0]])
+// CHECK-NEXT:    call void @__kmpc_end_masked(ptr @[[GLOB1]], i32 [[TMP0]])
+// CHECK-NEXT:    br label %[[OMP_IF_END]]
+// CHECK:       [[OMP_IF_END]]:
+// CHECK-NEXT:    ret void
+//
+// CHECK-LABEL: define dso_local i32 @main(
+// CHECK-SAME: ) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    call void @masked_taskloop_simd()
+// CHECK-NEXT:    ret i32 0