3 files changed, 38 insertions, 16 deletions

diff --git a/clang/lib/Basic/OpenMPKinds.cpp b/clang/lib/Basic/OpenMPKinds.cpp
index 65ac797ab4b..519794c7c4f 100644
--- a/clang/lib/Basic/OpenMPKinds.cpp
+++ b/clang/lib/Basic/OpenMPKinds.cpp
@@ -902,6 +902,7 @@ void clang::getOpenMPCaptureRegions(
     CaptureRegions.push_back(OMPD_target);
     break;
   case OMPD_teams_distribute_parallel_for:
+  case OMPD_teams_distribute_parallel_for_simd:
     CaptureRegions.push_back(OMPD_teams);
     CaptureRegions.push_back(OMPD_parallel);
     break;
@@ -935,7 +936,6 @@ void clang::getOpenMPCaptureRegions(
   case OMPD_atomic:
   case OMPD_target_data:
   case OMPD_distribute_simd:
-  case OMPD_teams_distribute_parallel_for_simd:
   case OMPD_target_teams_distribute:
   case OMPD_target_teams_distribute_parallel_for:
   case OMPD_target_teams_distribute_parallel_for_simd:
diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp
index 96f5a655956..72847fa2827 100644
--- a/clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -2100,18 +2100,6 @@ void CodeGenFunction::EmitOMPTeamsDistributeSimdDirective(
       });
 }
 
-void CodeGenFunction::EmitOMPTeamsDistributeParallelForSimdDirective(
-    const OMPTeamsDistributeParallelForSimdDirective &S) {
-  OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
-  CGM.getOpenMPRuntime().emitInlinedDirective(
-      *this, OMPD_teams_distribute_parallel_for_simd,
-      [&S](CodeGenFunction &CGF, PrePostActionTy &) {
-        OMPLoopScope PreInitScope(CGF, S);
-        CGF.EmitStmt(
-            cast<CapturedStmt>(S.getAssociatedStmt())->getCapturedStmt());
-      });
-}
-
 void CodeGenFunction::EmitOMPTargetTeamsDistributeDirective(
     const OMPTargetTeamsDistributeDirective &S) {
   OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
@@ -3953,6 +3941,28 @@ void CodeGenFunction::EmitOMPTeamsDistributeParallelForDirective(
                                    [](CodeGenFunction &) { return nullptr; });
 }
 
+void CodeGenFunction::EmitOMPTeamsDistributeParallelForSimdDirective(
+    const OMPTeamsDistributeParallelForSimdDirective &S) {
+  auto &&CodeGenDistribute = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
+    CGF.EmitOMPDistributeLoop(S, emitInnerParallelForWhenCombined,
+                              S.getDistInc());
+  };
+
+  // Emit teams region as a standalone region.
+  auto &&CodeGen = [&S, &CodeGenDistribute](CodeGenFunction &CGF,
+                                            PrePostActionTy &) {
+    OMPPrivateScope PrivateScope(CGF);
+    CGF.EmitOMPReductionClauseInit(S, PrivateScope);
+    (void)PrivateScope.Privatize();
+    CGF.CGM.getOpenMPRuntime().emitInlinedDirective(
+        CGF, OMPD_distribute, CodeGenDistribute, /*HasCancel=*/false);
+    CGF.EmitOMPReductionClauseFinal(S, /*ReductionKind=*/OMPD_teams);
+  };
+  emitCommonOMPTeamsDirective(*this, S, OMPD_distribute_parallel_for, CodeGen);
+  emitPostUpdateForReductionClause(*this, S,
+                                   [](CodeGenFunction &) { return nullptr; });
+}
+
 void CodeGenFunction::EmitOMPCancellationPointDirective(
     const OMPCancellationPointDirective &S) {
   CGM.getOpenMPRuntime().emitCancellationPointCall(*this, S.getLocStart(),
diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 4c0fa7e6172..28e40d32e09 100644
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -2201,7 +2201,6 @@ void Sema::ActOnOpenMPRegionStart(OpenMPDirectiveKind DKind, Scope *CurScope) {
   case OMPD_distribute_simd:
   case OMPD_distribute_parallel_for:
   case OMPD_teams_distribute_simd:
-  case OMPD_teams_distribute_parallel_for_simd:
   case OMPD_target_teams_distribute:
   case OMPD_target_teams_distribute_parallel_for:
   case OMPD_target_teams_distribute_parallel_for_simd:
@@ -2220,7 +2219,8 @@ void Sema::ActOnOpenMPRegionStart(OpenMPDirectiveKind DKind, Scope *CurScope) {
                              Params);
     break;
   }
-  case OMPD_teams_distribute_parallel_for: {
+  case OMPD_teams_distribute_parallel_for: 
+  case OMPD_teams_distribute_parallel_for_simd: {
     QualType KmpInt32Ty = Context.getIntTypeForBitwidth(32, 1);
     QualType KmpInt32PtrTy =
         Context.getPointerType(KmpInt32Ty).withConst().withRestrict();
@@ -7155,12 +7155,24 @@ StmtResult Sema::ActOnOpenMPTeamsDistributeParallelForSimdDirective(
   // longjmp() and throw() must not violate the entry/exit criteria.
   CS->getCapturedDecl()->setNothrow();
 
+  for (int ThisCaptureLevel =
+           getOpenMPCaptureLevels(OMPD_teams_distribute_parallel_for_simd);
+       ThisCaptureLevel > 1; --ThisCaptureLevel) {
+    CS = cast<CapturedStmt>(CS->getCapturedStmt());
+    // 1.2.2 OpenMP Language Terminology
+    // Structured block - An executable statement with a single entry at the
+    // top and a single exit at the bottom.
+    // The point of exit cannot be a branch out of the structured block.
+    // longjmp() and throw() must not violate the entry/exit criteria.
+    CS->getCapturedDecl()->setNothrow();
+  }
+
   OMPLoopDirective::HelperExprs B;
   // In presence of clause 'collapse' with number of loops, it will
   // define the nested loops number.
   auto NestedLoopCount = CheckOpenMPLoop(
       OMPD_teams_distribute_parallel_for_simd, getCollapseNumberExpr(Clauses),
-      nullptr /*ordered not a clause on distribute*/, AStmt, *this, *DSAStack,
+      nullptr /*ordered not a clause on distribute*/, CS, *this, *DSAStack,
       VarsWithImplicitDSA, B);
 
   if (NestedLoopCount == 0)