[Clang][OpenMP] Emit dependent PreInits before directive.

The PreInits of a loop transformation (atm moment only tile) include the computation of the trip count. The trip count is needed by any loop-associated directives that consumes the transformation-generated loop. Hence, we must ensure that the PreInits of consumed loop transformations are emitted with the consuming directive.

This is done by addinging the inner loop transformation's PreInits to the outer loop-directive's PreInits. The outer loop-directive will consume the de-sugared AST such that the inner PreInits are not emitted twice. The PreInits of a loop transformation are still emitted directly if its generated loop(s) are not associated with another loop-associated directive.

Reviewed By: ABataev

Differential Revision: https://reviews.llvm.org/D102180

diff --git a/clang/include/clang/AST/StmtOpenMP.h b/clang/include/clang/AST/StmtOpenMP.h
index 4d14848..4d6774c 100644 (file)
--- a/clang/include/clang/AST/StmtOpenMP.h
+++ b/clang/include/clang/AST/StmtOpenMP.h
@@ -884,15 +884,43 @@ public:
 
   /// Calls the specified callback function for all the loops in \p CurStmt,
   /// from the outermost to the innermost.
+  static bool doForAllLoops(Stmt *CurStmt, bool TryImperfectlyNestedLoops,
+                            unsigned NumLoops,
+                            llvm::function_ref<bool(unsigned, Stmt *)> Callback,
+                            llvm::function_ref<void(OMPLoopBasedDirective *)>
+                                OnTransformationCallback);
+  static bool
+  doForAllLoops(const Stmt *CurStmt, bool TryImperfectlyNestedLoops,
+                unsigned NumLoops,
+                llvm::function_ref<bool(unsigned, const Stmt *)> Callback,
+                llvm::function_ref<void(const OMPLoopBasedDirective *)>
+                    OnTransformationCallback) {
+    auto &&NewCallback = [Callback](unsigned Cnt, Stmt *CurStmt) {
+      return Callback(Cnt, CurStmt);
+    };
+    auto &&NewTransformCb =
+        [OnTransformationCallback](OMPLoopBasedDirective *A) {
+          OnTransformationCallback(A);
+        };
+    return doForAllLoops(const_cast<Stmt *>(CurStmt), TryImperfectlyNestedLoops,
+                         NumLoops, NewCallback, NewTransformCb);
+  }
+
+  /// Calls the specified callback function for all the loops in \p CurStmt,
+  /// from the outermost to the innermost.
   static bool
   doForAllLoops(Stmt *CurStmt, bool TryImperfectlyNestedLoops,
                 unsigned NumLoops,
-                llvm::function_ref<bool(unsigned, Stmt *)> Callback);
+                llvm::function_ref<bool(unsigned, Stmt *)> Callback) {
+    auto &&TransformCb = [](OMPLoopBasedDirective *) {};
+    return doForAllLoops(CurStmt, TryImperfectlyNestedLoops, NumLoops, Callback,
+                         TransformCb);
+  }
   static bool
   doForAllLoops(const Stmt *CurStmt, bool TryImperfectlyNestedLoops,
                 unsigned NumLoops,
                 llvm::function_ref<bool(unsigned, const Stmt *)> Callback) {
-    auto &&NewCallback = [Callback](unsigned Cnt, Stmt *CurStmt) {
+    auto &&NewCallback = [Callback](unsigned Cnt, const Stmt *CurStmt) {
       return Callback(Cnt, CurStmt);
     };
     return doForAllLoops(const_cast<Stmt *>(CurStmt), TryImperfectlyNestedLoops,

diff --git a/clang/lib/AST/StmtOpenMP.cpp b/clang/lib/AST/StmtOpenMP.cpp
index a990594..dbb11e7 100644 (file)
--- a/clang/lib/AST/StmtOpenMP.cpp
+++ b/clang/lib/AST/StmtOpenMP.cpp
@@ -124,11 +124,15 @@ OMPLoopBasedDirective::tryToFindNextInnerLoop(Stmt *CurStmt,
 
 bool OMPLoopBasedDirective::doForAllLoops(
     Stmt *CurStmt, bool TryImperfectlyNestedLoops, unsigned NumLoops,
-    llvm::function_ref<bool(unsigned, Stmt *)> Callback) {
+    llvm::function_ref<bool(unsigned, Stmt *)> Callback,
+    llvm::function_ref<void(OMPLoopBasedDirective *)>
+        OnTransformationCallback) {
   CurStmt = CurStmt->IgnoreContainers();
   for (unsigned Cnt = 0; Cnt < NumLoops; ++Cnt) {
-    if (auto *Dir = dyn_cast<OMPTileDirective>(CurStmt))
+    while (auto *Dir = dyn_cast<OMPTileDirective>(CurStmt)) {
+      OnTransformationCallback(Dir);
       CurStmt = Dir->getTransformedStmt();
+    }
     if (auto *CanonLoop = dyn_cast<OMPCanonicalLoop>(CurStmt))
       CurStmt = CanonLoop->getLoopStmt();
     if (Callback(Cnt, CurStmt))

diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp
index 344fa90..a03cbff 100644 (file)
--- a/clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -1819,8 +1819,6 @@ static void emitBody(CodeGenFunction &CGF, const Stmt *S, const Stmt *NextLoop,
     return;
   }
   if (SimplifiedS == NextLoop) {
-    OMPTransformDirectiveScopeRAII PossiblyTransformDirectiveScope(CGF,
-                                                                   SimplifiedS);
     if (auto *Dir = dyn_cast<OMPTileDirective>(SimplifiedS))
       SimplifiedS = Dir->getTransformedStmt();
     if (const auto *CanonLoop = dyn_cast<OMPCanonicalLoop>(SimplifiedS))

diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 3fcb1a7..2fcc3fb 100644 (file)
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -8964,6 +8964,18 @@ checkOpenMPLoop(OpenMPDirectiveKind DKind, Expr *CollapseLoopCountExpr,
               }
             }
             return false;
+          },
+          [&SemaRef, &Captures](OMPLoopBasedDirective *Transform) {
+            Stmt *DependentPreInits =
+                cast<OMPTileDirective>(Transform)->getPreInits();
+            if (!DependentPreInits)
+              return;
+            for (Decl *C : cast<DeclStmt>(DependentPreInits)->getDeclGroup()) {
+              auto *D = cast<VarDecl>(C);
+              DeclRefExpr *Ref = buildDeclRefExpr(SemaRef, D, D->getType(),
+                                                  Transform->getBeginLoc());
+              Captures[Ref] = Ref;
+            }
           }))
     return 0;
 
@@ -12564,7 +12576,8 @@ StmtResult Sema::ActOnOpenMPTileDirective(ArrayRef<OMPClause *> Clauses,
   // Verify and diagnose loop nest.
   SmallVector<OMPLoopBasedDirective::HelperExprs, 4> LoopHelpers(NumLoops);
   Stmt *Body = nullptr;
-  SmallVector<Stmt *, 4> OriginalInits;
+  SmallVector<SmallVector<llvm::PointerUnion<Stmt *, Decl *>, 0>, 4>
+      OriginalInits(1);
   if (!OMPLoopBasedDirective::doForAllLoops(
           AStmt->IgnoreContainers(), /*TryImperfectlyNestedLoops=*/false,
           NumLoops,
@@ -12578,16 +12591,23 @@ StmtResult Sema::ActOnOpenMPTileDirective(ArrayRef<OMPClause *> Clauses,
               return true;
             assert(SingleNumLoops == 1 && "Expect single loop iteration space");
             if (auto *For = dyn_cast<ForStmt>(CurStmt)) {
-              OriginalInits.push_back(For->getInit());
+              OriginalInits.back().push_back(For->getInit());
               Body = For->getBody();
             } else {
               assert(isa<CXXForRangeStmt>(CurStmt) &&
                      "Expected canonical for or range-based for loops.");
               auto *CXXFor = cast<CXXForRangeStmt>(CurStmt);
-              OriginalInits.push_back(CXXFor->getBeginStmt());
+              OriginalInits.back().push_back(CXXFor->getBeginStmt());
               Body = CXXFor->getBody();
             }
+            OriginalInits.emplace_back();
             return false;
+          },
+          [&OriginalInits](OMPLoopBasedDirective *Transform) {
+            Stmt *DependentPreInits =
+                cast<OMPTileDirective>(Transform)->getPreInits();
+            for (Decl *C : cast<DeclStmt>(DependentPreInits)->getDeclGroup())
+              OriginalInits.back().push_back(C);
           }))
     return StmtError();
 
@@ -12596,7 +12616,6 @@ StmtResult Sema::ActOnOpenMPTileDirective(ArrayRef<OMPClause *> Clauses,
     return OMPTileDirective::Create(Context, StartLoc, EndLoc, Clauses,
                                     NumLoops, AStmt, nullptr, nullptr);
 
-  // Collection of generated variable declaration.
   SmallVector<Decl *, 4> PreInits;
 
   // Create iteration variables for the generated loops.
@@ -12606,8 +12625,7 @@ StmtResult Sema::ActOnOpenMPTileDirective(ArrayRef<OMPClause *> Clauses,
   TileIndVars.resize(NumLoops);
   for (unsigned I = 0; I < NumLoops; ++I) {
     OMPLoopBasedDirective::HelperExprs &LoopHelper = LoopHelpers[I];
-    if (auto *PI = cast_or_null<DeclStmt>(LoopHelper.PreInits))
-      PreInits.append(PI->decl_begin(), PI->decl_end());
+
     assert(LoopHelper.Counters.size() == 1 &&
            "Expect single-dimensional loop iteration space");
     auto *OrigCntVar = cast<DeclRefExpr>(LoopHelper.Counters.front());
@@ -12636,7 +12654,13 @@ StmtResult Sema::ActOnOpenMPTileDirective(ArrayRef<OMPClause *> Clauses,
       TileCntDecl->setDeclName(&PP.getIdentifierTable().get(TileCntName));
       TileIndVars[I] = TileCntDecl;
     }
-    if (auto *PI = dyn_cast_or_null<DeclStmt>(OriginalInits[I]))
+    for (auto &P : OriginalInits[I]) {
+      if (auto *D = P.dyn_cast<Decl *>())
+        PreInits.push_back(D);
+      else if (auto *PI = dyn_cast_or_null<DeclStmt>(P.dyn_cast<Stmt *>()))
+        PreInits.append(PI->decl_begin(), PI->decl_end());
+    }
+    if (auto *PI = cast_or_null<DeclStmt>(LoopHelper.PreInits))
       PreInits.append(PI->decl_begin(), PI->decl_end());
     // Gather declarations for the data members used as counters.
     for (Expr *CounterRef : LoopHelper.Counters) {

diff --git a/clang/test/OpenMP/tile_codegen.cpp b/clang/test/OpenMP/tile_codegen.cpp
index d4de1de..e6d956b 100644 (file)
--- a/clang/test/OpenMP/tile_codegen.cpp
+++ b/clang/test/OpenMP/tile_codegen.cpp
@@ -378,17 +378,19 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TMP:%.*]] = alloca i32, align 4
+// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
+// CHECK1-NEXT:    [[J:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTFLOOR_0_IV_I:%.*]] = alloca i32, align 4
-// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
-// CHECK1-NEXT:    [[J:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTFLOOR_1_IV_J:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTTILE_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTTILE_1_IV_J:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2:[0-9]+]])
+// CHECK1-NEXT:    store i32 7, i32* [[I]], align 4
+// CHECK1-NEXT:    store i32 7, i32* [[J]], align 4
 // CHECK1-NEXT:    store i32 0, i32* [[DOTOMP_LB]], align 4
 // CHECK1-NEXT:    store i32 0, i32* [[DOTOMP_UB]], align 4
 // CHECK1-NEXT:    store i32 1, i32* [[DOTOMP_STRIDE]], align 4
@@ -418,8 +420,6 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP6]], 5
 // CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 0, [[MUL]]
 // CHECK1-NEXT:    store i32 [[ADD]], i32* [[DOTFLOOR_0_IV_I]], align 4
-// CHECK1-NEXT:    store i32 7, i32* [[I]], align 4
-// CHECK1-NEXT:    store i32 7, i32* [[J]], align 4
 // CHECK1-NEXT:    store i32 0, i32* [[DOTFLOOR_1_IV_J]], align 4
 // CHECK1-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK1:       for.cond:
@@ -521,18 +521,20 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TMP:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[_TMP1:%.*]] = alloca i32, align 4
+// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
+// CHECK1-NEXT:    [[J:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[K:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTFLOOR_0_IV_I:%.*]] = alloca i32, align 4
-// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
-// CHECK1-NEXT:    [[J:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTFLOOR_1_IV_J:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTTILE_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTTILE_1_IV_J:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
+// CHECK1-NEXT:    store i32 7, i32* [[I]], align 4
+// CHECK1-NEXT:    store i32 7, i32* [[J]], align 4
 // CHECK1-NEXT:    store i32 0, i32* [[DOTOMP_LB]], align 4
 // CHECK1-NEXT:    store i32 3, i32* [[DOTOMP_UB]], align 4
 // CHECK1-NEXT:    store i32 1, i32* [[DOTOMP_STRIDE]], align 4
@@ -571,8 +573,6 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:    [[MUL5:%.*]] = mul nsw i32 [[SUB]], 5
 // CHECK1-NEXT:    [[ADD6:%.*]] = add nsw i32 0, [[MUL5]]
 // CHECK1-NEXT:    store i32 [[ADD6]], i32* [[DOTFLOOR_0_IV_I]], align 4
-// CHECK1-NEXT:    store i32 7, i32* [[I]], align 4
-// CHECK1-NEXT:    store i32 7, i32* [[J]], align 4
 // CHECK1-NEXT:    store i32 0, i32* [[DOTFLOOR_1_IV_J]], align 4
 // CHECK1-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK1:       for.cond:
@@ -675,6 +675,7 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:    [[TMP:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[_TMP1:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[_TMP2:%.*]] = alloca i32, align 4
+// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTCAPTURE_EXPR_3:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTCAPTURE_EXPR_5:%.*]] = alloca i64, align 8
@@ -688,8 +689,8 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:    [[DOTFLOOR_0_IV_I11:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTTILE_0_IV_I12:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[J13:%.*]] = alloca i32, align 4
-// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
+// CHECK1-NEXT:    store i32 7, i32* [[I]], align 4
 // CHECK1-NEXT:    [[TMP1:%.*]] = load i32, i32* [[TMP]], align 4
 // CHECK1-NEXT:    store i32 [[TMP1]], i32* [[DOTCAPTURE_EXPR_]], align 4
 // CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP]], align 4
@@ -851,7 +852,6 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:    [[ADD91:%.*]] = add nsw i64 7, [[MUL90]]
 // CHECK1-NEXT:    [[CONV92:%.*]] = trunc i64 [[ADD91]] to i32
 // CHECK1-NEXT:    store i32 [[CONV92]], i32* [[J13]], align 4
-// CHECK1-NEXT:    store i32 7, i32* [[I]], align 4
 // CHECK1-NEXT:    [[TMP39:%.*]] = load i32, i32* [[DOTTILE_0_IV_I12]], align 4
 // CHECK1-NEXT:    [[MUL93:%.*]] = mul nsw i32 [[TMP39]], 3
 // CHECK1-NEXT:    [[ADD94:%.*]] = add nsw i32 7, [[MUL93]]
@@ -891,15 +891,16 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
 // CHECK1-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TMP:%.*]] = alloca i32, align 4
+// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTFLOOR_0_IV_I:%.*]] = alloca i32, align 4
-// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTTILE_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
 // CHECK1-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
+// CHECK1-NEXT:    store i32 7, i32* [[I]], align 4
 // CHECK1-NEXT:    store i32 0, i32* [[DOTOMP_LB]], align 4
 // CHECK1-NEXT:    store i32 0, i32* [[DOTOMP_UB]], align 4
 // CHECK1-NEXT:    store i32 1, i32* [[DOTOMP_STRIDE]], align 4
@@ -931,7 +932,6 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP7]], 5
 // CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 0, [[MUL]]
 // CHECK1-NEXT:    store i32 [[ADD]], i32* [[DOTFLOOR_0_IV_I]], align 4
-// CHECK1-NEXT:    store i32 7, i32* [[I]], align 4
 // CHECK1-NEXT:    [[TMP8:%.*]] = load i32, i32* [[DOTFLOOR_0_IV_I]], align 4
 // CHECK1-NEXT:    store i32 [[TMP8]], i32* [[DOTTILE_0_IV_I]], align 4
 // CHECK1-NEXT:    br label [[FOR_COND:%.*]]
@@ -992,28 +992,28 @@ extern "C" void tfoo7() {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[START_ADDR:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[END_ADDR:%.*]] = alloca i32, align 4
+// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTCAPTURE_EXPR_2:%.*]] = alloca i32, align 4
-// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTFLOOR_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTTILE_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    store i32 [[START]], i32* [[START_ADDR]], align 4
 // CHECK1-NEXT:    store i32 [[END]], i32* [[END_ADDR]], align 4
 // CHECK1-NEXT:    [[TMP0:%.*]] = load i32, i32* [[START_ADDR]], align 4
-// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTCAPTURE_EXPR_]], align 4
-// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, i32* [[END_ADDR]], align 4
-// CHECK1-NEXT:    store i32 [[TMP1]], i32* [[DOTCAPTURE_EXPR_1]], align 4
-// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
-// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
-// CHECK1-NEXT:    [[SUB:%.*]] = sub i32 [[TMP2]], [[TMP3]]
+// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[I]], align 4
+// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, i32* [[START_ADDR]], align 4
+// CHECK1-NEXT:    store i32 [[TMP1]], i32* [[DOTCAPTURE_EXPR_]], align 4
+// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[END_ADDR]], align 4
+// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTCAPTURE_EXPR_1]], align 4
+// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
+// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
+// CHECK1-NEXT:    [[SUB:%.*]] = sub i32 [[TMP3]], [[TMP4]]
 // CHECK1-NEXT:    [[SUB3:%.*]] = sub i32 [[SUB]], 1
 // CHECK1-NEXT:    [[ADD:%.*]] = add i32 [[SUB3]], 3
 // CHECK1-NEXT:    [[DIV:%.*]] = udiv i32 [[ADD]], 3
 // CHECK1-NEXT:    [[SUB4:%.*]] = sub i32 [[DIV]], 1
 // CHECK1-NEXT:    store i32 [[SUB4]], i32* [[DOTCAPTURE_EXPR_2]], align 4
-// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, i32* [[START_ADDR]], align 4
-// CHECK1-NEXT:    store i32 [[TMP4]], i32* [[I]], align 4
 // CHECK1-NEXT:    store i32 0, i32* [[DOTFLOOR_0_IV_I]], align 4
 // CHECK1-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK1:       for.cond:
@@ -1372,17 +1372,19 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:  entry:
 // CHECK2-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[TMP:%.*]] = alloca i32, align 4
+// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
+// CHECK2-NEXT:    [[J:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTFLOOR_0_IV_I:%.*]] = alloca i32, align 4
-// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
-// CHECK2-NEXT:    [[J:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTFLOOR_1_IV_J:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTTILE_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTTILE_1_IV_J:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2:[0-9]+]])
+// CHECK2-NEXT:    store i32 7, i32* [[I]], align 4
+// CHECK2-NEXT:    store i32 7, i32* [[J]], align 4
 // CHECK2-NEXT:    store i32 0, i32* [[DOTOMP_LB]], align 4
 // CHECK2-NEXT:    store i32 0, i32* [[DOTOMP_UB]], align 4
 // CHECK2-NEXT:    store i32 1, i32* [[DOTOMP_STRIDE]], align 4
@@ -1412,8 +1414,6 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP6]], 5
 // CHECK2-NEXT:    [[ADD:%.*]] = add nsw i32 0, [[MUL]]
 // CHECK2-NEXT:    store i32 [[ADD]], i32* [[DOTFLOOR_0_IV_I]], align 4
-// CHECK2-NEXT:    store i32 7, i32* [[I]], align 4
-// CHECK2-NEXT:    store i32 7, i32* [[J]], align 4
 // CHECK2-NEXT:    store i32 0, i32* [[DOTFLOOR_1_IV_J]], align 4
 // CHECK2-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK2:       for.cond:
@@ -1515,18 +1515,20 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[TMP:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[_TMP1:%.*]] = alloca i32, align 4
+// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
+// CHECK2-NEXT:    [[J:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[K:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTFLOOR_0_IV_I:%.*]] = alloca i32, align 4
-// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
-// CHECK2-NEXT:    [[J:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTFLOOR_1_IV_J:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTTILE_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTTILE_1_IV_J:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
+// CHECK2-NEXT:    store i32 7, i32* [[I]], align 4
+// CHECK2-NEXT:    store i32 7, i32* [[J]], align 4
 // CHECK2-NEXT:    store i32 0, i32* [[DOTOMP_LB]], align 4
 // CHECK2-NEXT:    store i32 3, i32* [[DOTOMP_UB]], align 4
 // CHECK2-NEXT:    store i32 1, i32* [[DOTOMP_STRIDE]], align 4
@@ -1565,8 +1567,6 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:    [[MUL5:%.*]] = mul nsw i32 [[SUB]], 5
 // CHECK2-NEXT:    [[ADD6:%.*]] = add nsw i32 0, [[MUL5]]
 // CHECK2-NEXT:    store i32 [[ADD6]], i32* [[DOTFLOOR_0_IV_I]], align 4
-// CHECK2-NEXT:    store i32 7, i32* [[I]], align 4
-// CHECK2-NEXT:    store i32 7, i32* [[J]], align 4
 // CHECK2-NEXT:    store i32 0, i32* [[DOTFLOOR_1_IV_J]], align 4
 // CHECK2-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK2:       for.cond:
@@ -1669,6 +1669,7 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:    [[TMP:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[_TMP1:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[_TMP2:%.*]] = alloca i32, align 4
+// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTCAPTURE_EXPR_3:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTCAPTURE_EXPR_5:%.*]] = alloca i64, align 8
@@ -1682,8 +1683,8 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:    [[DOTFLOOR_0_IV_I11:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTTILE_0_IV_I12:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[J13:%.*]] = alloca i32, align 4
-// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
+// CHECK2-NEXT:    store i32 7, i32* [[I]], align 4
 // CHECK2-NEXT:    [[TMP1:%.*]] = load i32, i32* [[TMP]], align 4
 // CHECK2-NEXT:    store i32 [[TMP1]], i32* [[DOTCAPTURE_EXPR_]], align 4
 // CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP]], align 4
@@ -1845,7 +1846,6 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:    [[ADD91:%.*]] = add nsw i64 7, [[MUL90]]
 // CHECK2-NEXT:    [[CONV92:%.*]] = trunc i64 [[ADD91]] to i32
 // CHECK2-NEXT:    store i32 [[CONV92]], i32* [[J13]], align 4
-// CHECK2-NEXT:    store i32 7, i32* [[I]], align 4
 // CHECK2-NEXT:    [[TMP39:%.*]] = load i32, i32* [[DOTTILE_0_IV_I12]], align 4
 // CHECK2-NEXT:    [[MUL93:%.*]] = mul nsw i32 [[TMP39]], 3
 // CHECK2-NEXT:    [[ADD94:%.*]] = add nsw i32 7, [[MUL93]]
@@ -1885,15 +1885,16 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
 // CHECK2-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[TMP:%.*]] = alloca i32, align 4
+// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTFLOOR_0_IV_I:%.*]] = alloca i32, align 4
-// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTTILE_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
 // CHECK2-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
+// CHECK2-NEXT:    store i32 7, i32* [[I]], align 4
 // CHECK2-NEXT:    store i32 0, i32* [[DOTOMP_LB]], align 4
 // CHECK2-NEXT:    store i32 0, i32* [[DOTOMP_UB]], align 4
 // CHECK2-NEXT:    store i32 1, i32* [[DOTOMP_STRIDE]], align 4
@@ -1925,7 +1926,6 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP7]], 5
 // CHECK2-NEXT:    [[ADD:%.*]] = add nsw i32 0, [[MUL]]
 // CHECK2-NEXT:    store i32 [[ADD]], i32* [[DOTFLOOR_0_IV_I]], align 4
-// CHECK2-NEXT:    store i32 7, i32* [[I]], align 4
 // CHECK2-NEXT:    [[TMP8:%.*]] = load i32, i32* [[DOTFLOOR_0_IV_I]], align 4
 // CHECK2-NEXT:    store i32 [[TMP8]], i32* [[DOTTILE_0_IV_I]], align 4
 // CHECK2-NEXT:    br label [[FOR_COND:%.*]]
@@ -1986,28 +1986,28 @@ extern "C" void tfoo7() {
 // CHECK2-NEXT:  entry:
 // CHECK2-NEXT:    [[START_ADDR:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[END_ADDR:%.*]] = alloca i32, align 4
+// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTCAPTURE_EXPR_2:%.*]] = alloca i32, align 4
-// CHECK2-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTFLOOR_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    [[DOTTILE_0_IV_I:%.*]] = alloca i32, align 4
 // CHECK2-NEXT:    store i32 [[START]], i32* [[START_ADDR]], align 4
 // CHECK2-NEXT:    store i32 [[END]], i32* [[END_ADDR]], align 4
 // CHECK2-NEXT:    [[TMP0:%.*]] = load i32, i32* [[START_ADDR]], align 4
-// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTCAPTURE_EXPR_]], align 4
-// CHECK2-NEXT:    [[TMP1:%.*]] = load i32, i32* [[END_ADDR]], align 4
-// CHECK2-NEXT:    store i32 [[TMP1]], i32* [[DOTCAPTURE_EXPR_1]], align 4
-// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
-// CHECK2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
-// CHECK2-NEXT:    [[SUB:%.*]] = sub i32 [[TMP2]], [[TMP3]]
+// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[I]], align 4
+// CHECK2-NEXT:    [[TMP1:%.*]] = load i32, i32* [[START_ADDR]], align 4
+// CHECK2-NEXT:    store i32 [[TMP1]], i32* [[DOTCAPTURE_EXPR_]], align 4
+// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[END_ADDR]], align 4
+// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTCAPTURE_EXPR_1]], align 4
+// CHECK2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
+// CHECK2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
+// CHECK2-NEXT:    [[SUB:%.*]] = sub i32 [[TMP3]], [[TMP4]]
 // CHECK2-NEXT:    [[SUB3:%.*]] = sub i32 [[SUB]], 1
 // CHECK2-NEXT:    [[ADD:%.*]] = add i32 [[SUB3]], 3
 // CHECK2-NEXT:    [[DIV:%.*]] = udiv i32 [[ADD]], 3
 // CHECK2-NEXT:    [[SUB4:%.*]] = sub i32 [[DIV]], 1
 // CHECK2-NEXT:    store i32 [[SUB4]], i32* [[DOTCAPTURE_EXPR_2]], align 4
-// CHECK2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[START_ADDR]], align 4
-// CHECK2-NEXT:    store i32 [[TMP4]], i32* [[I]], align 4
 // CHECK2-NEXT:    store i32 0, i32* [[DOTFLOOR_0_IV_I]], align 4
 // CHECK2-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK2:       for.cond:

diff --git a/clang/test/OpenMP/tile_codegen_for_dependent.cpp b/clang/test/OpenMP/tile_codegen_for_dependent.cpp
new file mode 100644 (file)
index 0000000..7bf0445
--- /dev/null
+++ b/clang/test/OpenMP/tile_codegen_for_dependent.cpp
@@ -0,0 +1,193 @@
+// Check code generation
+// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -emit-llvm %s -o - | FileCheck %s --check-prefix=IR
+
+// Check same results after serialization round-trip
+// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -emit-pch -o %t %s
+// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -include-pch %t -emit-llvm %s -o - | FileCheck %s --check-prefix=IR
+// expected-no-diagnostics
+
+// The loop trip count used by #pragma omp for depends on code generated
+// by #pragma omp file. Check that theses PreInits are emitted before
+// the code generated by #pragma omp for.
+
+#ifndef HEADER
+#define HEADER
+
+// placeholder for loop body code.
+extern "C" void body(...) {}
+
+
+// IR-LABEL: @func(
+// IR-NEXT:  [[ENTRY:.*]]:
+// IR-NEXT:    %[[START_ADDR:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[END_ADDR:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[STEP_ADDR:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_IV:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[TMP:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[I:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_1:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_2:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_3:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_6:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_8:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTFLOOR_0_IV_I:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_LB:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_UB:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_STRIDE:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_IS_LAST:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTFLOOR_0_IV_I12:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTTILE_0_IV_I:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[TMP0:.+]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @2)
+// IR-NEXT:    store i32 %[[START:.+]], i32* %[[START_ADDR]], align 4
+// IR-NEXT:    store i32 %[[END:.+]], i32* %[[END_ADDR]], align 4
+// IR-NEXT:    store i32 %[[STEP:.+]], i32* %[[STEP_ADDR]], align 4
+// IR-NEXT:    %[[TMP1:.+]] = load i32, i32* %[[START_ADDR]], align 4
+// IR-NEXT:    store i32 %[[TMP1]], i32* %[[I]], align 4
+// IR-NEXT:    %[[TMP2:.+]] = load i32, i32* %[[START_ADDR]], align 4
+// IR-NEXT:    store i32 %[[TMP2]], i32* %[[DOTCAPTURE_EXPR_]], align 4
+// IR-NEXT:    %[[TMP3:.+]] = load i32, i32* %[[END_ADDR]], align 4
+// IR-NEXT:    store i32 %[[TMP3]], i32* %[[DOTCAPTURE_EXPR_1]], align 4
+// IR-NEXT:    %[[TMP4:.+]] = load i32, i32* %[[STEP_ADDR]], align 4
+// IR-NEXT:    store i32 %[[TMP4]], i32* %[[DOTCAPTURE_EXPR_2]], align 4
+// IR-NEXT:    %[[TMP5:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_1]], align 4
+// IR-NEXT:    %[[TMP6:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_]], align 4
+// IR-NEXT:    %[[SUB:.+]] = sub i32 %[[TMP5]], %[[TMP6]]
+// IR-NEXT:    %[[SUB4:.+]] = sub i32 %[[SUB]], 1
+// IR-NEXT:    %[[TMP7:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_2]], align 4
+// IR-NEXT:    %[[ADD:.+]] = add i32 %[[SUB4]], %[[TMP7]]
+// IR-NEXT:    %[[TMP8:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_2]], align 4
+// IR-NEXT:    %[[DIV:.+]] = udiv i32 %[[ADD]], %[[TMP8]]
+// IR-NEXT:    %[[SUB5:.+]] = sub i32 %[[DIV]], 1
+// IR-NEXT:    store i32 %[[SUB5]], i32* %[[DOTCAPTURE_EXPR_3]], align 4
+// IR-NEXT:    %[[TMP9:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_3]], align 4
+// IR-NEXT:    %[[ADD7:.+]] = add i32 %[[TMP9]], 1
+// IR-NEXT:    store i32 %[[ADD7]], i32* %[[DOTCAPTURE_EXPR_6]], align 4
+// IR-NEXT:    %[[TMP10:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_6]], align 4
+// IR-NEXT:    %[[SUB9:.+]] = sub i32 %[[TMP10]], -3
+// IR-NEXT:    %[[DIV10:.+]] = udiv i32 %[[SUB9]], 4
+// IR-NEXT:    %[[SUB11:.+]] = sub i32 %[[DIV10]], 1
+// IR-NEXT:    store i32 %[[SUB11]], i32* %[[DOTCAPTURE_EXPR_8]], align 4
+// IR-NEXT:    store i32 0, i32* %[[DOTFLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP11:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_6]], align 4
+// IR-NEXT:    %[[CMP:.+]] = icmp ult i32 0, %[[TMP11]]
+// IR-NEXT:    br i1 %[[CMP]], label %[[OMP_PRECOND_THEN:.+]], label %[[OMP_PRECOND_END:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_PRECOND_THEN]]:
+// IR-NEXT:    store i32 0, i32* %[[DOTOMP_LB]], align 4
+// IR-NEXT:    %[[TMP12:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_8]], align 4
+// IR-NEXT:    store i32 %[[TMP12]], i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    store i32 1, i32* %[[DOTOMP_STRIDE]], align 4
+// IR-NEXT:    store i32 0, i32* %[[DOTOMP_IS_LAST]], align 4
+// IR-NEXT:    call void @__kmpc_for_static_init_4u(%struct.ident_t* @1, i32 %[[TMP0]], i32 34, i32* %[[DOTOMP_IS_LAST]], i32* %[[DOTOMP_LB]], i32* %[[DOTOMP_UB]], i32* %[[DOTOMP_STRIDE]], i32 1, i32 1)
+// IR-NEXT:    %[[TMP13:.+]] = load i32, i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    %[[TMP14:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_8]], align 4
+// IR-NEXT:    %[[CMP13:.+]] = icmp ugt i32 %[[TMP13]], %[[TMP14]]
+// IR-NEXT:    br i1 %[[CMP13]], label %[[COND_TRUE:.+]], label %[[COND_FALSE:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_TRUE]]:
+// IR-NEXT:    %[[TMP15:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_8]], align 4
+// IR-NEXT:    br label %[[COND_END:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_FALSE]]:
+// IR-NEXT:    %[[TMP16:.+]] = load i32, i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    br label %[[COND_END]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_END]]:
+// IR-NEXT:    %[[COND:.+]] = phi i32 [ %[[TMP15]], %[[COND_TRUE]] ], [ %[[TMP16]], %[[COND_FALSE]] ]
+// IR-NEXT:    store i32 %[[COND]], i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    %[[TMP17:.+]] = load i32, i32* %[[DOTOMP_LB]], align 4
+// IR-NEXT:    store i32 %[[TMP17]], i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    br label %[[OMP_INNER_FOR_COND:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_INNER_FOR_COND]]:
+// IR-NEXT:    %[[TMP18:.+]] = load i32, i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    %[[TMP19:.+]] = load i32, i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    %[[ADD14:.+]] = add i32 %[[TMP19]], 1
+// IR-NEXT:    %[[CMP15:.+]] = icmp ult i32 %[[TMP18]], %[[ADD14]]
+// IR-NEXT:    br i1 %[[CMP15]], label %[[OMP_INNER_FOR_BODY:.+]], label %[[OMP_INNER_FOR_END:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_INNER_FOR_BODY]]:
+// IR-NEXT:    %[[TMP20:.+]] = load i32, i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    %[[MUL:.+]] = mul i32 %[[TMP20]], 4
+// IR-NEXT:    %[[ADD16:.+]] = add i32 0, %[[MUL]]
+// IR-NEXT:    store i32 %[[ADD16]], i32* %[[DOTFLOOR_0_IV_I12]], align 4
+// IR-NEXT:    %[[TMP21:.+]] = load i32, i32* %[[DOTFLOOR_0_IV_I12]], align 4
+// IR-NEXT:    store i32 %[[TMP21]], i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    br label %[[FOR_COND:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_COND]]:
+// IR-NEXT:    %[[TMP22:.+]] = load i32, i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP23:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_3]], align 4
+// IR-NEXT:    %[[ADD17:.+]] = add i32 %[[TMP23]], 1
+// IR-NEXT:    %[[TMP24:.+]] = load i32, i32* %[[DOTFLOOR_0_IV_I12]], align 4
+// IR-NEXT:    %[[ADD18:.+]] = add nsw i32 %[[TMP24]], 4
+// IR-NEXT:    %[[CMP19:.+]] = icmp ult i32 %[[ADD17]], %[[ADD18]]
+// IR-NEXT:    br i1 %[[CMP19]], label %[[COND_TRUE20:.+]], label %[[COND_FALSE22:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_TRUE20]]:
+// IR-NEXT:    %[[TMP25:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_3]], align 4
+// IR-NEXT:    %[[ADD21:.+]] = add i32 %[[TMP25]], 1
+// IR-NEXT:    br label %[[COND_END24:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_FALSE22]]:
+// IR-NEXT:    %[[TMP26:.+]] = load i32, i32* %[[DOTFLOOR_0_IV_I12]], align 4
+// IR-NEXT:    %[[ADD23:.+]] = add nsw i32 %[[TMP26]], 4
+// IR-NEXT:    br label %[[COND_END24]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_END24]]:
+// IR-NEXT:    %[[COND25:.+]] = phi i32 [ %[[ADD21]], %[[COND_TRUE20]] ], [ %[[ADD23]], %[[COND_FALSE22]] ]
+// IR-NEXT:    %[[CMP26:.+]] = icmp ult i32 %[[TMP22]], %[[COND25]]
+// IR-NEXT:    br i1 %[[CMP26]], label %[[FOR_BODY:.+]], label %[[FOR_END:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_BODY]]:
+// IR-NEXT:    %[[TMP27:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_]], align 4
+// IR-NEXT:    %[[TMP28:.+]] = load i32, i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP29:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_2]], align 4
+// IR-NEXT:    %[[MUL27:.+]] = mul i32 %[[TMP28]], %[[TMP29]]
+// IR-NEXT:    %[[ADD28:.+]] = add i32 %[[TMP27]], %[[MUL27]]
+// IR-NEXT:    store i32 %[[ADD28]], i32* %[[I]], align 4
+// IR-NEXT:    %[[TMP30:.+]] = load i32, i32* %[[START_ADDR]], align 4
+// IR-NEXT:    %[[TMP31:.+]] = load i32, i32* %[[END_ADDR]], align 4
+// IR-NEXT:    %[[TMP32:.+]] = load i32, i32* %[[STEP_ADDR]], align 4
+// IR-NEXT:    %[[TMP33:.+]] = load i32, i32* %[[I]], align 4
+// IR-NEXT:    call void (...) @body(i32 %[[TMP30]], i32 %[[TMP31]], i32 %[[TMP32]], i32 %[[TMP33]])
+// IR-NEXT:    br label %[[FOR_INC:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_INC]]:
+// IR-NEXT:    %[[TMP34:.+]] = load i32, i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    %[[INC:.+]] = add nsw i32 %[[TMP34]], 1
+// IR-NEXT:    store i32 %[[INC]], i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    br label %[[FOR_COND]], !llvm.loop ![[LOOP2:[0-9]+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_END]]:
+// IR-NEXT:    br label %[[OMP_BODY_CONTINUE:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_BODY_CONTINUE]]:
+// IR-NEXT:    br label %[[OMP_INNER_FOR_INC:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_INNER_FOR_INC]]:
+// IR-NEXT:    %[[TMP35:.+]] = load i32, i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    %[[ADD29:.+]] = add i32 %[[TMP35]], 1
+// IR-NEXT:    store i32 %[[ADD29]], i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    br label %[[OMP_INNER_FOR_COND]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_INNER_FOR_END]]:
+// IR-NEXT:    br label %[[OMP_LOOP_EXIT:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_LOOP_EXIT]]:
+// IR-NEXT:    call void @__kmpc_for_static_fini(%struct.ident_t* @1, i32 %[[TMP0]])
+// IR-NEXT:    br label %[[OMP_PRECOND_END]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_PRECOND_END]]:
+// IR-NEXT:    call void @__kmpc_barrier(%struct.ident_t* @3, i32 %[[TMP0]])
+// IR-NEXT:    ret void
+// IR-NEXT:  }
+extern "C" void func(int start, int end, int step) {
+#pragma omp for
+#pragma omp tile sizes(4)
+  for (int i = start; i < end; i += step)
+    body(start, end, step, i);
+}
+
+#endif /* HEADER */

diff --git a/clang/test/OpenMP/tile_codegen_tile_for.cpp b/clang/test/OpenMP/tile_codegen_tile_for.cpp
new file mode 100644 (file)
index 0000000..314446c
--- /dev/null
+++ b/clang/test/OpenMP/tile_codegen_tile_for.cpp
@@ -0,0 +1,253 @@
+// Check code generation
+// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -emit-llvm %s -o - | FileCheck %s --check-prefix=IR
+
+// Check same results after serialization round-trip
+// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -emit-pch -o %t %s
+// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -include-pch %t -emit-llvm %s -o - | FileCheck %s --check-prefix=IR
+// expected-no-diagnostics
+
+// Account for multiple transformations of a loop before consumed by
+// #pragma omp for.
+
+#ifndef HEADER
+#define HEADER
+
+// placeholder for loop body code.
+extern "C" void body(...) {}
+
+
+// IR-LABEL: @func(
+// IR-NEXT:  [[ENTRY:.*]]:
+// IR-NEXT:    %[[START_ADDR:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[END_ADDR:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[STEP_ADDR:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_IV:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[TMP:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[I:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_1:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_2:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_3:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTFLOOR_0_IV_I:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_6:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_8:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_12:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTCAPTURE_EXPR_14:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTFLOOR_0_IV__FLOOR_0_IV_I:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_LB:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_UB:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_STRIDE:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTOMP_IS_LAST:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTTILE_0_IV__FLOOR_0_IV_I:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[DOTTILE_0_IV_I:.+]] = alloca i32, align 4
+// IR-NEXT:    %[[TMP0:.+]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @2)
+// IR-NEXT:    store i32 %[[START:.+]], i32* %[[START_ADDR]], align 4
+// IR-NEXT:    store i32 %[[END:.+]], i32* %[[END_ADDR]], align 4
+// IR-NEXT:    store i32 %[[STEP:.+]], i32* %[[STEP_ADDR]], align 4
+// IR-NEXT:    %[[TMP1:.+]] = load i32, i32* %[[START_ADDR]], align 4
+// IR-NEXT:    store i32 %[[TMP1]], i32* %[[I]], align 4
+// IR-NEXT:    %[[TMP2:.+]] = load i32, i32* %[[START_ADDR]], align 4
+// IR-NEXT:    store i32 %[[TMP2]], i32* %[[DOTCAPTURE_EXPR_]], align 4
+// IR-NEXT:    %[[TMP3:.+]] = load i32, i32* %[[END_ADDR]], align 4
+// IR-NEXT:    store i32 %[[TMP3]], i32* %[[DOTCAPTURE_EXPR_1]], align 4
+// IR-NEXT:    %[[TMP4:.+]] = load i32, i32* %[[STEP_ADDR]], align 4
+// IR-NEXT:    store i32 %[[TMP4]], i32* %[[DOTCAPTURE_EXPR_2]], align 4
+// IR-NEXT:    %[[TMP5:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_1]], align 4
+// IR-NEXT:    %[[TMP6:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_]], align 4
+// IR-NEXT:    %[[SUB:.+]] = sub i32 %[[TMP5]], %[[TMP6]]
+// IR-NEXT:    %[[SUB4:.+]] = sub i32 %[[SUB]], 1
+// IR-NEXT:    %[[TMP7:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_2]], align 4
+// IR-NEXT:    %[[ADD:.+]] = add i32 %[[SUB4]], %[[TMP7]]
+// IR-NEXT:    %[[TMP8:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_2]], align 4
+// IR-NEXT:    %[[DIV:.+]] = udiv i32 %[[ADD]], %[[TMP8]]
+// IR-NEXT:    %[[SUB5:.+]] = sub i32 %[[DIV]], 1
+// IR-NEXT:    store i32 %[[SUB5]], i32* %[[DOTCAPTURE_EXPR_3]], align 4
+// IR-NEXT:    store i32 0, i32* %[[DOTFLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP9:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_3]], align 4
+// IR-NEXT:    %[[ADD7:.+]] = add i32 %[[TMP9]], 1
+// IR-NEXT:    store i32 %[[ADD7]], i32* %[[DOTCAPTURE_EXPR_6]], align 4
+// IR-NEXT:    %[[TMP10:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_6]], align 4
+// IR-NEXT:    %[[SUB9:.+]] = sub i32 %[[TMP10]], -3
+// IR-NEXT:    %[[DIV10:.+]] = udiv i32 %[[SUB9]], 4
+// IR-NEXT:    %[[SUB11:.+]] = sub i32 %[[DIV10]], 1
+// IR-NEXT:    store i32 %[[SUB11]], i32* %[[DOTCAPTURE_EXPR_8]], align 4
+// IR-NEXT:    %[[TMP11:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_8]], align 4
+// IR-NEXT:    %[[ADD13:.+]] = add i32 %[[TMP11]], 1
+// IR-NEXT:    store i32 %[[ADD13]], i32* %[[DOTCAPTURE_EXPR_12]], align 4
+// IR-NEXT:    %[[TMP12:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_12]], align 4
+// IR-NEXT:    %[[SUB15:.+]] = sub i32 %[[TMP12]], -2
+// IR-NEXT:    %[[DIV16:.+]] = udiv i32 %[[SUB15]], 3
+// IR-NEXT:    %[[SUB17:.+]] = sub i32 %[[DIV16]], 1
+// IR-NEXT:    store i32 %[[SUB17]], i32* %[[DOTCAPTURE_EXPR_14]], align 4
+// IR-NEXT:    store i32 0, i32* %[[DOTFLOOR_0_IV__FLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP13:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_12]], align 4
+// IR-NEXT:    %[[CMP:.+]] = icmp ult i32 0, %[[TMP13]]
+// IR-NEXT:    br i1 %[[CMP]], label %[[OMP_PRECOND_THEN:.+]], label %[[OMP_PRECOND_END:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_PRECOND_THEN]]:
+// IR-NEXT:    store i32 0, i32* %[[DOTOMP_LB]], align 4
+// IR-NEXT:    %[[TMP14:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_14]], align 4
+// IR-NEXT:    store i32 %[[TMP14]], i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    store i32 1, i32* %[[DOTOMP_STRIDE]], align 4
+// IR-NEXT:    store i32 0, i32* %[[DOTOMP_IS_LAST]], align 4
+// IR-NEXT:    call void @__kmpc_for_static_init_4u(%struct.ident_t* @1, i32 %[[TMP0]], i32 34, i32* %[[DOTOMP_IS_LAST]], i32* %[[DOTOMP_LB]], i32* %[[DOTOMP_UB]], i32* %[[DOTOMP_STRIDE]], i32 1, i32 1)
+// IR-NEXT:    %[[TMP15:.+]] = load i32, i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    %[[TMP16:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_14]], align 4
+// IR-NEXT:    %[[CMP19:.+]] = icmp ugt i32 %[[TMP15]], %[[TMP16]]
+// IR-NEXT:    br i1 %[[CMP19]], label %[[COND_TRUE:.+]], label %[[COND_FALSE:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_TRUE]]:
+// IR-NEXT:    %[[TMP17:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_14]], align 4
+// IR-NEXT:    br label %[[COND_END:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_FALSE]]:
+// IR-NEXT:    %[[TMP18:.+]] = load i32, i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    br label %[[COND_END]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_END]]:
+// IR-NEXT:    %[[COND:.+]] = phi i32 [ %[[TMP17]], %[[COND_TRUE]] ], [ %[[TMP18]], %[[COND_FALSE]] ]
+// IR-NEXT:    store i32 %[[COND]], i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    %[[TMP19:.+]] = load i32, i32* %[[DOTOMP_LB]], align 4
+// IR-NEXT:    store i32 %[[TMP19]], i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    br label %[[OMP_INNER_FOR_COND:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_INNER_FOR_COND]]:
+// IR-NEXT:    %[[TMP20:.+]] = load i32, i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    %[[TMP21:.+]] = load i32, i32* %[[DOTOMP_UB]], align 4
+// IR-NEXT:    %[[ADD20:.+]] = add i32 %[[TMP21]], 1
+// IR-NEXT:    %[[CMP21:.+]] = icmp ult i32 %[[TMP20]], %[[ADD20]]
+// IR-NEXT:    br i1 %[[CMP21]], label %[[OMP_INNER_FOR_BODY:.+]], label %[[OMP_INNER_FOR_END:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_INNER_FOR_BODY]]:
+// IR-NEXT:    %[[TMP22:.+]] = load i32, i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    %[[MUL:.+]] = mul i32 %[[TMP22]], 3
+// IR-NEXT:    %[[ADD22:.+]] = add i32 0, %[[MUL]]
+// IR-NEXT:    store i32 %[[ADD22]], i32* %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18]], align 4
+// IR-NEXT:    %[[TMP23:.+]] = load i32, i32* %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18]], align 4
+// IR-NEXT:    store i32 %[[TMP23]], i32* %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
+// IR-NEXT:    br label %[[FOR_COND:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_COND]]:
+// IR-NEXT:    %[[TMP24:.+]] = load i32, i32* %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP25:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_8]], align 4
+// IR-NEXT:    %[[ADD23:.+]] = add i32 %[[TMP25]], 1
+// IR-NEXT:    %[[TMP26:.+]] = load i32, i32* %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18]], align 4
+// IR-NEXT:    %[[ADD24:.+]] = add i32 %[[TMP26]], 3
+// IR-NEXT:    %[[CMP25:.+]] = icmp ult i32 %[[ADD23]], %[[ADD24]]
+// IR-NEXT:    br i1 %[[CMP25]], label %[[COND_TRUE26:.+]], label %[[COND_FALSE28:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_TRUE26]]:
+// IR-NEXT:    %[[TMP27:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_8]], align 4
+// IR-NEXT:    %[[ADD27:.+]] = add i32 %[[TMP27]], 1
+// IR-NEXT:    br label %[[COND_END30:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_FALSE28]]:
+// IR-NEXT:    %[[TMP28:.+]] = load i32, i32* %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18]], align 4
+// IR-NEXT:    %[[ADD29:.+]] = add i32 %[[TMP28]], 3
+// IR-NEXT:    br label %[[COND_END30]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_END30]]:
+// IR-NEXT:    %[[COND31:.+]] = phi i32 [ %[[ADD27]], %[[COND_TRUE26]] ], [ %[[ADD29]], %[[COND_FALSE28]] ]
+// IR-NEXT:    %[[CMP32:.+]] = icmp ult i32 %[[TMP24]], %[[COND31]]
+// IR-NEXT:    br i1 %[[CMP32]], label %[[FOR_BODY:.+]], label %[[FOR_END51:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_BODY]]:
+// IR-NEXT:    %[[TMP29:.+]] = load i32, i32* %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[MUL33:.+]] = mul i32 %[[TMP29]], 4
+// IR-NEXT:    %[[ADD34:.+]] = add i32 0, %[[MUL33]]
+// IR-NEXT:    store i32 %[[ADD34]], i32* %[[DOTFLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP30:.+]] = load i32, i32* %[[DOTFLOOR_0_IV_I]], align 4
+// IR-NEXT:    store i32 %[[TMP30]], i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    br label %[[FOR_COND35:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_COND35]]:
+// IR-NEXT:    %[[TMP31:.+]] = load i32, i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP32:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_3]], align 4
+// IR-NEXT:    %[[ADD36:.+]] = add i32 %[[TMP32]], 1
+// IR-NEXT:    %[[TMP33:.+]] = load i32, i32* %[[DOTFLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[ADD37:.+]] = add nsw i32 %[[TMP33]], 4
+// IR-NEXT:    %[[CMP38:.+]] = icmp ult i32 %[[ADD36]], %[[ADD37]]
+// IR-NEXT:    br i1 %[[CMP38]], label %[[COND_TRUE39:.+]], label %[[COND_FALSE41:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_TRUE39]]:
+// IR-NEXT:    %[[TMP34:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_3]], align 4
+// IR-NEXT:    %[[ADD40:.+]] = add i32 %[[TMP34]], 1
+// IR-NEXT:    br label %[[COND_END43:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_FALSE41]]:
+// IR-NEXT:    %[[TMP35:.+]] = load i32, i32* %[[DOTFLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[ADD42:.+]] = add nsw i32 %[[TMP35]], 4
+// IR-NEXT:    br label %[[COND_END43]]
+// IR-EMPTY:
+// IR-NEXT:  [[COND_END43]]:
+// IR-NEXT:    %[[COND44:.+]] = phi i32 [ %[[ADD40]], %[[COND_TRUE39]] ], [ %[[ADD42]], %[[COND_FALSE41]] ]
+// IR-NEXT:    %[[CMP45:.+]] = icmp ult i32 %[[TMP31]], %[[COND44]]
+// IR-NEXT:    br i1 %[[CMP45]], label %[[FOR_BODY46:.+]], label %[[FOR_END:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_BODY46]]:
+// IR-NEXT:    %[[TMP36:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_]], align 4
+// IR-NEXT:    %[[TMP37:.+]] = load i32, i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    %[[TMP38:.+]] = load i32, i32* %[[DOTCAPTURE_EXPR_2]], align 4
+// IR-NEXT:    %[[MUL47:.+]] = mul i32 %[[TMP37]], %[[TMP38]]
+// IR-NEXT:    %[[ADD48:.+]] = add i32 %[[TMP36]], %[[MUL47]]
+// IR-NEXT:    store i32 %[[ADD48]], i32* %[[I]], align 4
+// IR-NEXT:    %[[TMP39:.+]] = load i32, i32* %[[START_ADDR]], align 4
+// IR-NEXT:    %[[TMP40:.+]] = load i32, i32* %[[END_ADDR]], align 4
+// IR-NEXT:    %[[TMP41:.+]] = load i32, i32* %[[STEP_ADDR]], align 4
+// IR-NEXT:    %[[TMP42:.+]] = load i32, i32* %[[I]], align 4
+// IR-NEXT:    call void (...) @body(i32 %[[TMP39]], i32 %[[TMP40]], i32 %[[TMP41]], i32 %[[TMP42]])
+// IR-NEXT:    br label %[[FOR_INC:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_INC]]:
+// IR-NEXT:    %[[TMP43:.+]] = load i32, i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    %[[INC:.+]] = add nsw i32 %[[TMP43]], 1
+// IR-NEXT:    store i32 %[[INC]], i32* %[[DOTTILE_0_IV_I]], align 4
+// IR-NEXT:    br label %[[FOR_COND35]], !llvm.loop ![[LOOP2:[0-9]+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_END]]:
+// IR-NEXT:    br label %[[FOR_INC49:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_INC49]]:
+// IR-NEXT:    %[[TMP44:.+]] = load i32, i32* %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
+// IR-NEXT:    %[[INC50:.+]] = add i32 %[[TMP44]], 1
+// IR-NEXT:    store i32 %[[INC50]], i32* %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
+// IR-NEXT:    br label %[[FOR_COND]], !llvm.loop ![[LOOP4:[0-9]+]]
+// IR-EMPTY:
+// IR-NEXT:  [[FOR_END51]]:
+// IR-NEXT:    br label %[[OMP_BODY_CONTINUE:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_BODY_CONTINUE]]:
+// IR-NEXT:    br label %[[OMP_INNER_FOR_INC:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_INNER_FOR_INC]]:
+// IR-NEXT:    %[[TMP45:.+]] = load i32, i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    %[[ADD52:.+]] = add i32 %[[TMP45]], 1
+// IR-NEXT:    store i32 %[[ADD52]], i32* %[[DOTOMP_IV]], align 4
+// IR-NEXT:    br label %[[OMP_INNER_FOR_COND]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_INNER_FOR_END]]:
+// IR-NEXT:    br label %[[OMP_LOOP_EXIT:.+]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_LOOP_EXIT]]:
+// IR-NEXT:    call void @__kmpc_for_static_fini(%struct.ident_t* @1, i32 %[[TMP0]])
+// IR-NEXT:    br label %[[OMP_PRECOND_END]]
+// IR-EMPTY:
+// IR-NEXT:  [[OMP_PRECOND_END]]:
+// IR-NEXT:    call void @__kmpc_barrier(%struct.ident_t* @3, i32 %[[TMP0]])
+// IR-NEXT:    ret void
+// IR-NEXT:  }
+extern "C" void func(int start, int end, int step) {
+#pragma omp for
+#pragma omp tile sizes(3)
+#pragma omp tile sizes(4)
+  for (int i = start; i < end; i += step)
+    body(start, end, step, i);
+}
+
+#endif /* HEADER */
+// IR: ![[META0:[0-9]+]] = !{i32 1, !"wchar_size", i32 4}
+// IR: ![[META1:[0-9]+]] = !{!"clang version {{[^"]*}}"}
+// IR: ![[LOOP2]] = distinct !{![[LOOP2]], ![[LOOPPROP3:[0-9]+]]}
+// IR: ![[LOOPPROP3]] = !{!"llvm.loop.mustprogress"}
+// IR: ![[LOOP4]] = distinct !{![[LOOP4]], ![[LOOPPROP3]]}