[llvm] d16da73 - Revert "[LV] Unconditionally branch from middle to scalar preheader if the scalar loop must execute"

Philip Reames via llvm-commits llvm-commits at lists.llvm.org
Mon May 17 16:49:55 PDT 2021


Author: Philip Reames
Date: 2021-05-17T16:49:32-07:00
New Revision: d16da7343d40bc974c1906a271128fbaa3035db5

URL: https://github.com/llvm/llvm-project/commit/d16da7343d40bc974c1906a271128fbaa3035db5
DIFF: https://github.com/llvm/llvm-project/commit/d16da7343d40bc974c1906a271128fbaa3035db5.diff

LOG: Revert "[LV] Unconditionally branch from middle to scalar preheader if the scalar loop must execute"

This reverts commit c23ce54b36b1a52eb280ea1d59802b56d6dd9800.  I apparently missed some newly added non-x86 tests.

Added: 
    

Modified: 
    llvm/lib/Transforms/Utils/LoopVersioning.cpp
    llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
    llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll
    llvm/test/Transforms/LoopVectorize/loop-form.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Utils/LoopVersioning.cpp b/llvm/lib/Transforms/Utils/LoopVersioning.cpp
index 8a89158788cf8..de4fb446fdf27 100644
--- a/llvm/lib/Transforms/Utils/LoopVersioning.cpp
+++ b/llvm/lib/Transforms/Utils/LoopVersioning.cpp
@@ -44,11 +44,11 @@ LoopVersioning::LoopVersioning(const LoopAccessInfo &LAI,
       AliasChecks(Checks.begin(), Checks.end()),
       Preds(LAI.getPSE().getUnionPredicate()), LAI(LAI), LI(LI), DT(DT),
       SE(SE) {
+  assert(L->getUniqueExitBlock() && "No single exit block");
 }
 
 void LoopVersioning::versionLoop(
     const SmallVectorImpl<Instruction *> &DefsUsedOutside) {
-  assert(VersionedLoop->getUniqueExitBlock() && "No single exit block");
   assert(VersionedLoop->isLoopSimplifyForm() &&
          "Loop is not in loop-simplify form");
 

diff  --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index ba3f540d2afcf..90343f3a57fa0 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -819,7 +819,7 @@ class InnerLoopVectorizer {
   /// Middle Block between the vector and the scalar.
   BasicBlock *LoopMiddleBlock;
 
-  /// The unique ExitBlock of the scalar loop if one exists.  Note that
+  /// The (unique) ExitBlock of the scalar loop.  Note that
   /// there can be multiple exiting edges reaching this block.
   BasicBlock *LoopExitBlock;
 
@@ -3249,13 +3249,9 @@ void InnerLoopVectorizer::emitMinimumIterationCountCheck(Loop *L,
                                DT->getNode(Bypass)->getIDom()) &&
          "TC check is expected to dominate Bypass");
 
-  // Update dominator for Bypass & LoopExit (if needed).
+  // Update dominator for Bypass & LoopExit.
   DT->changeImmediateDominator(Bypass, TCCheckBlock);
-  if (!Cost->requiresScalarEpilogue())
-    // If there is an epilogue which must run, there's no edge from the
-    // middle block to exit blocks  and thus no need to update the immediate
-    // dominator of the exit blocks.
-    DT->changeImmediateDominator(LoopExitBlock, TCCheckBlock);
+  DT->changeImmediateDominator(LoopExitBlock, TCCheckBlock);
 
   ReplaceInstWithInst(
       TCCheckBlock->getTerminator(),
@@ -3279,11 +3275,7 @@ BasicBlock *InnerLoopVectorizer::emitSCEVChecks(Loop *L, BasicBlock *Bypass) {
   // Update dominator only if this is first RT check.
   if (LoopBypassBlocks.empty()) {
     DT->changeImmediateDominator(Bypass, SCEVCheckBlock);
-    if (!Cost->requiresScalarEpilogue())
-      // If there is an epilogue which must run, there's no edge from the
-      // middle block to exit blocks  and thus no need to update the immediate
-      // dominator of the exit blocks.
-      DT->changeImmediateDominator(LoopExitBlock, SCEVCheckBlock);
+    DT->changeImmediateDominator(LoopExitBlock, SCEVCheckBlock);
   }
 
   LoopBypassBlocks.push_back(SCEVCheckBlock);
@@ -3436,10 +3428,9 @@ Value *InnerLoopVectorizer::emitTransformedIndex(
 Loop *InnerLoopVectorizer::createVectorLoopSkeleton(StringRef Prefix) {
   LoopScalarBody = OrigLoop->getHeader();
   LoopVectorPreHeader = OrigLoop->getLoopPreheader();
+  LoopExitBlock = OrigLoop->getUniqueExitBlock();
+  assert(LoopExitBlock && "Must have an exit block");
   assert(LoopVectorPreHeader && "Invalid loop structure");
-  LoopExitBlock = OrigLoop->getUniqueExitBlock(); // may be nullptr
-  assert((LoopExitBlock || Cost->requiresScalarEpilogue()) &&
-         "multiple exit loop without required epilogue?");
 
   LoopMiddleBlock =
       SplitBlock(LoopVectorPreHeader, LoopVectorPreHeader->getTerminator(), DT,
@@ -3448,20 +3439,12 @@ Loop *InnerLoopVectorizer::createVectorLoopSkeleton(StringRef Prefix) {
       SplitBlock(LoopMiddleBlock, LoopMiddleBlock->getTerminator(), DT, LI,
                  nullptr, Twine(Prefix) + "scalar.ph");
 
+  // Set up branch from middle block to the exit and scalar preheader blocks.
+  // completeLoopSkeleton will update the condition to use an iteration check,
+  // if required to decide whether to execute the remainder.
+  BranchInst *BrInst =
+      BranchInst::Create(LoopExitBlock, LoopScalarPreHeader, Builder.getTrue());
   auto *ScalarLatchTerm = OrigLoop->getLoopLatch()->getTerminator();
-
-  // Set up the middle block terminator.  Two cases:
-  // 1) If we know that we must execute the scalar epilogue, emit an
-  //    unconditional branch.
-  // 2) Otherwise, we must have a single unique exit block (due to how we
-  //    implement the multiple exit case).  In this case, set up a conditonal
-  //    branch from the middle block to the loop scalar preheader, and the
-  //    exit block.  completeLoopSkeleton will update the condition to use an
-  //    iteration check, if required to decide whether to execute the remainder.
-  BranchInst *BrInst = Cost->requiresScalarEpilogue() ?
-    BranchInst::Create(LoopScalarPreHeader) :
-    BranchInst::Create(LoopExitBlock, LoopScalarPreHeader,
-                       Builder.getTrue());
   BrInst->setDebugLoc(ScalarLatchTerm->getDebugLoc());
   ReplaceInstWithInst(LoopMiddleBlock->getTerminator(), BrInst);
 
@@ -3473,11 +3456,7 @@ Loop *InnerLoopVectorizer::createVectorLoopSkeleton(StringRef Prefix) {
                  nullptr, nullptr, Twine(Prefix) + "vector.body");
 
   // Update dominator for loop exit.
-  if (!Cost->requiresScalarEpilogue())
-    // If there is an epilogue which must run, there's no edge from the
-    // middle block to exit blocks  and thus no need to update the immediate
-    // dominator of the exit blocks.
-    DT->changeImmediateDominator(LoopExitBlock, LoopMiddleBlock);
+  DT->changeImmediateDominator(LoopExitBlock, LoopMiddleBlock);
 
   // Create and register the new vector loop.
   Loop *Lp = LI->AllocateLoop();
@@ -3579,14 +3558,10 @@ BasicBlock *InnerLoopVectorizer::completeLoopSkeleton(Loop *L,
   auto *ScalarLatchTerm = OrigLoop->getLoopLatch()->getTerminator();
 
   // Add a check in the middle block to see if we have completed
-  // all of the iterations in the first vector loop.  Three cases:
-  // 1) If we require a scalar epilogue, there is no conditional branch as
-  //    we unconditionally branch to the scalar preheader.  Do nothing.
-  // 2) If (N - N%VF) == N, then we *don't* need to run the remainder.
-  //    Thus if tail is to be folded, we know we don't need to run the
-  //    remainder and we can use the previous value for the condition (true).
-  // 3) Otherwise, construct a runtime check.
-  if (!Cost->requiresScalarEpilogue() && !Cost->foldTailByMasking()) {
+  // all of the iterations in the first vector loop.
+  // If (N - N%VF) == N, then we *don't* need to run the remainder.
+  // If tail is to be folded, we know we don't need to run the remainder.
+  if (!Cost->foldTailByMasking()) {
     Instruction *CmpN = CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_EQ,
                                         Count, VectorTripCount, "cmp.n",
                                         LoopMiddleBlock->getTerminator());
@@ -3650,17 +3625,17 @@ BasicBlock *InnerLoopVectorizer::createVectorizedLoopSkeleton() {
   |    [  ]_|   <-- vector loop.
   |     |
   |     v
-  \   -[ ]   <--- middle-block.
-   \/   |
-   /\   v
-   | ->[ ]     <--- new preheader.
+  |   -[ ]   <--- middle-block.
+  |  /  |
+  | /   v
+  -|- >[ ]     <--- new preheader.
    |    |
- (opt)  v      <-- edge from middle to exit iff epilogue is not required.
+   |    v
    |   [ ] \
-   |   [ ]_|   <-- old scalar loop to handle remainder (scalar epilogue).
+   |   [ ]_|   <-- old scalar loop to handle remainder.
     \   |
      \  v
-      >[ ]     <-- exit block(s).
+      >[ ]     <-- exit block.
    ...
    */
 
@@ -4097,19 +4072,13 @@ void InnerLoopVectorizer::fixVectorizedLoop(VPTransformState &State) {
   // Forget the original basic block.
   PSE.getSE()->forgetLoop(OrigLoop);
 
-  // If we inserted an edge from the middle block to the unique exit block,
-  // update uses outside the loop (phis) to account for the newly inserted
-  // edge.
-  if (!Cost->requiresScalarEpilogue()) { 
-    // Fix-up external users of the induction variables.
-    for (auto &Entry : Legal->getInductionVars())
-      fixupIVUsers(Entry.first, Entry.second,
-                   getOrCreateVectorTripCount(LI->getLoopFor(LoopVectorBody)),
-                   IVEndValues[Entry.first], LoopMiddleBlock);
-
-    fixLCSSAPHIs(State);
-  }
+  // Fix-up external users of the induction variables.
+  for (auto &Entry : Legal->getInductionVars())
+    fixupIVUsers(Entry.first, Entry.second,
+                 getOrCreateVectorTripCount(LI->getLoopFor(LoopVectorBody)),
+                 IVEndValues[Entry.first], LoopMiddleBlock);
 
+  fixLCSSAPHIs(State);
   for (Instruction *PI : PredicatedInstructions)
     sinkScalarOperands(&*PI);
 
@@ -4330,13 +4299,12 @@ void InnerLoopVectorizer::fixFirstOrderRecurrence(PHINode *Phi,
   // recurrence in the exit block, and then add an edge for the middle block.
   // Note that LCSSA does not imply single entry when the original scalar loop
   // had multiple exiting edges (as we always run the last iteration in the
-  // scalar epilogue); in that case, there is no edge from middle to exit and
-  // and thus no phis which needed updated.
-  if (!Cost->requiresScalarEpilogue())
-    for (PHINode &LCSSAPhi : LoopExitBlock->phis())
-      if (any_of(LCSSAPhi.incoming_values(),
-                 [Phi](Value *V) { return V == Phi; }))
-        LCSSAPhi.addIncoming(ExtractForPhiUsedOutsideLoop, LoopMiddleBlock);
+  // scalar epilogue); in that case, the exiting path through middle will be
+  // dynamically dead and the value picked for the phi doesn't matter.
+  for (PHINode &LCSSAPhi : LoopExitBlock->phis())
+    if (any_of(LCSSAPhi.incoming_values(),
+               [Phi](Value *V) { return V == Phi; }))
+      LCSSAPhi.addIncoming(ExtractForPhiUsedOutsideLoop, LoopMiddleBlock);
 }
 
 static bool useOrderedReductions(RecurrenceDescriptor &RdxDesc) {
@@ -4514,11 +4482,10 @@ void InnerLoopVectorizer::fixReduction(VPWidenPHIRecipe *PhiR,
   // We know that the loop is in LCSSA form. We need to update the PHI nodes
   // in the exit blocks.  See comment on analogous loop in
   // fixFirstOrderRecurrence for a more complete explaination of the logic.
-  if (!Cost->requiresScalarEpilogue())
-    for (PHINode &LCSSAPhi : LoopExitBlock->phis())
-      if (any_of(LCSSAPhi.incoming_values(),
-                 [LoopExitInst](Value *V) { return V == LoopExitInst; }))
-        LCSSAPhi.addIncoming(ReducedPartRdx, LoopMiddleBlock);
+  for (PHINode &LCSSAPhi : LoopExitBlock->phis())
+    if (any_of(LCSSAPhi.incoming_values(),
+               [LoopExitInst](Value *V) { return V == LoopExitInst; }))
+      LCSSAPhi.addIncoming(ReducedPartRdx, LoopMiddleBlock);
 
   // Fix the scalar loop reduction variable with the incoming reduction sum
   // from the vector body and from the backedge value.
@@ -8323,11 +8290,7 @@ BasicBlock *EpilogueVectorizerMainLoop::emitMinimumIterationCountCheck(
 
     // Update dominator for Bypass & LoopExit.
     DT->changeImmediateDominator(Bypass, TCCheckBlock);
-    if (!Cost->requiresScalarEpilogue())
-      // For loops with multiple exits, there's no edge from the middle block
-      // to exit blocks (as the epilogue must run) and thus no need to update
-      // the immediate dominator of the exit blocks.
-      DT->changeImmediateDominator(LoopExitBlock, TCCheckBlock);
+    DT->changeImmediateDominator(LoopExitBlock, TCCheckBlock);
 
     LoopBypassBlocks.push_back(TCCheckBlock);
 
@@ -8391,12 +8354,7 @@ EpilogueVectorizerEpilogueLoop::createEpilogueVectorizedLoopSkeleton() {
 
   DT->changeImmediateDominator(LoopScalarPreHeader,
                                EPI.EpilogueIterationCountCheck);
-  if (!Cost->requiresScalarEpilogue())
-    // If there is an epilogue which must run, there's no edge from the
-    // middle block to exit blocks  and thus no need to update the immediate
-    // dominator of the exit blocks.
-    DT->changeImmediateDominator(LoopExitBlock,
-                                 EPI.EpilogueIterationCountCheck);
+  DT->changeImmediateDominator(LoopExitBlock, EPI.EpilogueIterationCountCheck);
 
   // Keep track of bypass blocks, as they feed start values to the induction
   // phis in the scalar loop preheader.

diff  --git a/llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll b/llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
index 7535cb159c3d8..3a3c72a422d51 100644
--- a/llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
+++ b/llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
@@ -38,7 +38,7 @@ define void @can_sink_after_store(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr
 ; CHECK-NEXT:    store <4 x i32> [[TMP6]], <4 x i32>* [[TMP9]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1996
-; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1999, 1996
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 3
@@ -59,7 +59,7 @@ define void @can_sink_after_store(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr
 ; CHECK-NEXT:    store i32 [[ADD_2]], i32* [[IDX_2]], align 4
 ; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], 2000
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT]], label [[FOR]], !llvm.loop [[LOOP2:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT]], label [[FOR]], [[LOOP2:!llvm.loop !.*]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
@@ -122,7 +122,7 @@ define void @sink_sdiv(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
 ; CHECK-NEXT:    store <4 x i32> [[TMP6]], <4 x i32>* [[TMP9]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1996
-; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP4:!llvm.loop !.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1999, 1996
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 3
@@ -143,7 +143,7 @@ define void @sink_sdiv(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
 ; CHECK-NEXT:    store i32 [[ADD_2]], i32* [[IDX_2]], align 4
 ; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], 2000
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT]], label [[FOR]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT]], label [[FOR]], [[LOOP5:!llvm.loop !.*]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
@@ -467,11 +467,12 @@ define i16 @multiple_exit(i16* %p, i32 %n) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
 ; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP6:!llvm.loop !.*]]
 ; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP0]], [[N_VEC]]
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i32 3
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i32 2
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[IF_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[SCALAR_RECUR_INIT:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[VECTOR_RECUR_EXTRACT]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
@@ -483,14 +484,14 @@ define i16 @multiple_exit(i16* %p, i32 %n) {
 ; CHECK-NEXT:    [[B:%.*]] = getelementptr inbounds i16, i16* [[P]], i64 [[IPROM]]
 ; CHECK-NEXT:    [[REC_NEXT]] = load i16, i16* [[B]], align 2
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[I]], [[N]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    store i16 [[SCALAR_RECUR]], i16* [[B]], align 4
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I]], 1
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp slt i32 [[I]], 2096
-; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], [[LOOP7:!llvm.loop !.*]]
 ; CHECK:       if.end:
-; CHECK-NEXT:    [[REC_LCSSA:%.*]] = phi i16 [ [[SCALAR_RECUR]], [[FOR_BODY]] ], [ [[SCALAR_RECUR]], [[FOR_COND]] ]
+; CHECK-NEXT:    [[REC_LCSSA:%.*]] = phi i16 [ [[SCALAR_RECUR]], [[FOR_BODY]] ], [ [[SCALAR_RECUR]], [[FOR_COND]] ], [ [[VECTOR_RECUR_EXTRACT_FOR_PHI]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    ret i16 [[REC_LCSSA]]
 ;
 entry:
@@ -551,11 +552,12 @@ define i16 @multiple_exit2(i16* %p, i32 %n) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
 ; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP8:!llvm.loop !.*]]
 ; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP0]], [[N_VEC]]
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i32 3
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i32 2
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[IF_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[SCALAR_RECUR_INIT:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[VECTOR_RECUR_EXTRACT]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
@@ -567,14 +569,14 @@ define i16 @multiple_exit2(i16* %p, i32 %n) {
 ; CHECK-NEXT:    [[B:%.*]] = getelementptr inbounds i16, i16* [[P]], i64 [[IPROM]]
 ; CHECK-NEXT:    [[REC_NEXT]] = load i16, i16* [[B]], align 2
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[I]], [[N]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    store i16 [[SCALAR_RECUR]], i16* [[B]], align 4
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I]], 1
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp slt i32 [[I]], 2096
-; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], [[LOOP9:!llvm.loop !.*]]
 ; CHECK:       if.end:
-; CHECK-NEXT:    [[REC_LCSSA:%.*]] = phi i16 [ [[SCALAR_RECUR]], [[FOR_COND]] ], [ 10, [[FOR_BODY]] ]
+; CHECK-NEXT:    [[REC_LCSSA:%.*]] = phi i16 [ [[SCALAR_RECUR]], [[FOR_COND]] ], [ 10, [[FOR_BODY]] ], [ [[VECTOR_RECUR_EXTRACT_FOR_PHI]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    ret i16 [[REC_LCSSA]]
 ;
 entry:

diff  --git a/llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll b/llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll
index 3f179d11231ce..34e8917fdece4 100644
--- a/llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll
@@ -443,7 +443,7 @@ define void @even_load_static_tc(i32* noalias nocapture readonly %A, i32* noalia
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 508
 ; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 false, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1016, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
@@ -459,7 +459,7 @@ define void @even_load_static_tc(i32* noalias nocapture readonly %A, i32* noalia
 ; CHECK-NEXT:    store i32 [[MUL]], i32* [[ARRAYIDX2]], align 4
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 2
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[INDVARS_IV]], 1022
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP:%.*]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP]], !llvm.loop [[LOOP13:![0-9]+]]
 ;
 entry:
   br label %for.body
@@ -523,7 +523,7 @@ define void @even_load_dynamic_tc(i32* noalias nocapture readonly %A, i32* noali
 ; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 false, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
@@ -539,7 +539,7 @@ define void @even_load_dynamic_tc(i32* noalias nocapture readonly %A, i32* noali
 ; CHECK-NEXT:    store i32 [[MUL]], i32* [[ARRAYIDX2]], align 4
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 2
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[INDVARS_IV_NEXT]], [[N]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP:%.*]], !llvm.loop [[LOOP15:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP]], !llvm.loop [[LOOP15:![0-9]+]]
 ;
 entry:
   br label %for.body
@@ -959,7 +959,7 @@ define void @PR27626_0(%pair.i32 *%p, i32 %z, i64 %n) {
 ; CHECK-NEXT:    [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP24:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 false, label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
@@ -971,7 +971,7 @@ define void @PR27626_0(%pair.i32 *%p, i32 %z, i64 %n) {
 ; CHECK-NEXT:    store i32 [[Z]], i32* [[P_I_Y]], align 4
 ; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 1
 ; CHECK-NEXT:    [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
-; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END:%.*]], !llvm.loop [[LOOP25:![0-9]+]]
+; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP25:![0-9]+]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
@@ -1047,7 +1047,7 @@ define i32 @PR27626_1(%pair.i32 *%p, i64 %n) {
 ; CHECK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP26:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[TMP18:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP16]])
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 false, label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP18]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
@@ -1062,9 +1062,10 @@ define i32 @PR27626_1(%pair.i32 *%p, i64 %n) {
 ; CHECK-NEXT:    [[TMP20]] = add nsw i32 [[TMP19]], [[S]]
 ; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 1
 ; CHECK-NEXT:    [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
-; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END:%.*]], !llvm.loop [[LOOP27:![0-9]+]]
+; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP27:![0-9]+]]
 ; CHECK:       for.end:
-; CHECK-NEXT:    ret i32 [[TMP20]]
+; CHECK-NEXT:    [[TMP21:%.*]] = phi i32 [ [[TMP20]], [[FOR_BODY]] ], [ [[TMP18]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[TMP21]]
 ;
 entry:
   br label %for.body
@@ -1142,7 +1143,7 @@ define void @PR27626_2(%pair.i32 *%p, i64 %n, i32 %z) {
 ; CHECK-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP28:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 false, label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
@@ -1156,7 +1157,7 @@ define void @PR27626_2(%pair.i32 *%p, i64 %n, i32 %z) {
 ; CHECK-NEXT:    store i32 [[TMP20]], i32* [[P_I_Y]], align 4
 ; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 1
 ; CHECK-NEXT:    [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
-; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END:%.*]], !llvm.loop [[LOOP29:![0-9]+]]
+; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP29:![0-9]+]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
@@ -1238,7 +1239,7 @@ define i32 @PR27626_3(%pair.i32 *%p, i64 %n, i32 %z) {
 ; CHECK-NEXT:    br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP30:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[TMP21:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP19]])
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 false, label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP21]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
@@ -1256,9 +1257,10 @@ define i32 @PR27626_3(%pair.i32 *%p, i64 %n, i32 %z) {
 ; CHECK-NEXT:    [[TMP24]] = add nsw i32 [[TMP23]], [[S]]
 ; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 1
 ; CHECK-NEXT:    [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
-; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END:%.*]], !llvm.loop [[LOOP31:![0-9]+]]
+; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP31:![0-9]+]]
 ; CHECK:       for.end:
-; CHECK-NEXT:    ret i32 [[TMP24]]
+; CHECK-NEXT:    [[TMP25:%.*]] = phi i32 [ [[TMP24]], [[FOR_BODY]] ], [ [[TMP21]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[TMP25]]
 ;
 entry:
   br label %for.body

diff  --git a/llvm/test/Transforms/LoopVectorize/loop-form.ll b/llvm/test/Transforms/LoopVectorize/loop-form.ll
index 0b8fa53f59623..29ba6d731577c 100644
--- a/llvm/test/Transforms/LoopVectorize/loop-form.ll
+++ b/llvm/test/Transforms/LoopVectorize/loop-form.ll
@@ -25,7 +25,7 @@ define void @bottom_tested(i16* %p, i32 %n) {
 ; CHECK-NEXT:    store <2 x i16> zeroinitializer, <2 x i16>* [[TMP5]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP0]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[IF_END:%.*]], label [[SCALAR_PH]]
@@ -39,7 +39,7 @@ define void @bottom_tested(i16* %p, i32 %n) {
 ; CHECK-NEXT:    store i16 0, i16* [[B]], align 4
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I]], 1
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[I]], [[N]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_COND]], label [[IF_END]], !llvm.loop [[LOOP2:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_COND]], label [[IF_END]], [[LOOP2:!llvm.loop !.*]]
 ; CHECK:       if.end:
 ; CHECK-NEXT:    ret void
 ;
@@ -82,7 +82,7 @@ define void @bottom_tested(i16* %p, i32 %n) {
 ; TAILFOLD-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
 ; TAILFOLD-NEXT:    [[VEC_IND_NEXT]] = add <2 x i32> [[VEC_IND]], <i32 2, i32 2>
 ; TAILFOLD-NEXT:    [[TMP11:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; TAILFOLD-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; TAILFOLD-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
 ; TAILFOLD:       middle.block:
 ; TAILFOLD-NEXT:    br i1 true, label [[IF_END:%.*]], label [[SCALAR_PH]]
 ; TAILFOLD:       scalar.ph:
@@ -95,7 +95,7 @@ define void @bottom_tested(i16* %p, i32 %n) {
 ; TAILFOLD-NEXT:    store i16 0, i16* [[B]], align 4
 ; TAILFOLD-NEXT:    [[INC]] = add nsw i32 [[I]], 1
 ; TAILFOLD-NEXT:    [[CMP:%.*]] = icmp slt i32 [[I]], [[N]]
-; TAILFOLD-NEXT:    br i1 [[CMP]], label [[FOR_COND]], label [[IF_END]], !llvm.loop [[LOOP2:![0-9]+]]
+; TAILFOLD-NEXT:    br i1 [[CMP]], label [[FOR_COND]], label [[IF_END]], [[LOOP2:!llvm.loop !.*]]
 ; TAILFOLD:       if.end:
 ; TAILFOLD-NEXT:    ret void
 ;
@@ -141,22 +141,23 @@ define void @early_exit(i16* %p, i32 %n) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i32> [[VEC_IND]], <i32 2, i32 2>
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP4:!llvm.loop !.*]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP0]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[IF_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_COND:%.*]]
 ; CHECK:       for.cond:
 ; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY:%.*]] ]
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[I]], [[N]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[IPROM:%.*]] = sext i32 [[I]] to i64
 ; CHECK-NEXT:    [[B:%.*]] = getelementptr inbounds i16, i16* [[P]], i64 [[IPROM]]
 ; CHECK-NEXT:    store i16 0, i16* [[B]], align 4
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I]], 1
-; CHECK-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT:    br label [[FOR_COND]], [[LOOP5:!llvm.loop !.*]]
 ; CHECK:       if.end:
 ; CHECK-NEXT:    ret void
 ;
@@ -278,23 +279,24 @@ define void @multiple_unique_exit(i16* %p, i32 %n) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i32> [[VEC_IND]], <i32 2, i32 2>
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP6:!llvm.loop !.*]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP0]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[IF_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_COND:%.*]]
 ; CHECK:       for.cond:
 ; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY:%.*]] ]
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[I]], [[N]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[IPROM:%.*]] = sext i32 [[I]] to i64
 ; CHECK-NEXT:    [[B:%.*]] = getelementptr inbounds i16, i16* [[P]], i64 [[IPROM]]
 ; CHECK-NEXT:    store i16 0, i16* [[B]], align 4
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I]], 1
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp slt i32 [[I]], 2096
-; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], [[LOOP7:!llvm.loop !.*]]
 ; CHECK:       if.end:
 ; CHECK-NEXT:    ret void
 ;
@@ -363,25 +365,28 @@ define i32 @multiple_unique_exit2(i16* %p, i32 %n) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i32> [[VEC_IND]], <i32 2, i32 2>
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP8:!llvm.loop !.*]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP0]], [[N_VEC]]
+; CHECK-NEXT:    [[IND_ESCAPE:%.*]] = sub i32 [[N_VEC]], 1
+; CHECK-NEXT:    [[IND_ESCAPE1:%.*]] = sub i32 [[N_VEC]], 1
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[IF_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_COND:%.*]]
 ; CHECK:       for.cond:
 ; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY:%.*]] ]
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[I]], [[N]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[IPROM:%.*]] = sext i32 [[I]] to i64
 ; CHECK-NEXT:    [[B:%.*]] = getelementptr inbounds i16, i16* [[P]], i64 [[IPROM]]
 ; CHECK-NEXT:    store i16 0, i16* [[B]], align 4
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I]], 1
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp slt i32 [[I]], 2096
-; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], [[LOOP9:!llvm.loop !.*]]
 ; CHECK:       if.end:
-; CHECK-NEXT:    [[I_LCSSA:%.*]] = phi i32 [ [[I]], [[FOR_BODY]] ], [ [[I]], [[FOR_COND]] ]
+; CHECK-NEXT:    [[I_LCSSA:%.*]] = phi i32 [ [[I]], [[FOR_BODY]] ], [ [[I]], [[FOR_COND]] ], [ [[IND_ESCAPE1]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    ret i32 [[I_LCSSA]]
 ;
 ; TAILFOLD-LABEL: @multiple_unique_exit2(
@@ -450,25 +455,26 @@ define i32 @multiple_unique_exit3(i16* %p, i32 %n) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i32> [[VEC_IND]], <i32 2, i32 2>
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP10:!llvm.loop !.*]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP0]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[IF_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_COND:%.*]]
 ; CHECK:       for.cond:
 ; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY:%.*]] ]
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[I]], [[N]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[IF_END]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[IPROM:%.*]] = sext i32 [[I]] to i64
 ; CHECK-NEXT:    [[B:%.*]] = getelementptr inbounds i16, i16* [[P]], i64 [[IPROM]]
 ; CHECK-NEXT:    store i16 0, i16* [[B]], align 4
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I]], 1
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp slt i32 [[I]], 2096
-; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_COND]], label [[IF_END]], [[LOOP11:!llvm.loop !.*]]
 ; CHECK:       if.end:
-; CHECK-NEXT:    [[EXIT:%.*]] = phi i32 [ 0, [[FOR_COND]] ], [ 1, [[FOR_BODY]] ]
+; CHECK-NEXT:    [[EXIT:%.*]] = phi i32 [ 0, [[FOR_COND]] ], [ 1, [[FOR_BODY]] ], [ 0, [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    ret i32 [[EXIT]]
 ;
 ; TAILFOLD-LABEL: @multiple_unique_exit3(
@@ -983,9 +989,10 @@ define void @scalar_predication(float* %addr) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 2, i64 2>
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
-; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP12:!llvm.loop !.*]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 201, 200
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
@@ -993,7 +1000,7 @@ define void @scalar_predication(float* %addr) {
 ; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
 ; CHECK-NEXT:    [[GEP:%.*]] = getelementptr float, float* [[ADDR]], i64 [[IV]]
 ; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV]], 200
-; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[EXIT:%.*]], label [[LOOP_BODY:%.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[LOOP_BODY:%.*]]
 ; CHECK:       loop.body:
 ; CHECK-NEXT:    [[TMP11:%.*]] = load float, float* [[GEP]], align 4
 ; CHECK-NEXT:    [[PRED:%.*]] = fcmp oeq float [[TMP11]], 0.000000e+00
@@ -1003,7 +1010,7 @@ define void @scalar_predication(float* %addr) {
 ; CHECK-NEXT:    br label [[LOOP_LATCH]]
 ; CHECK:       loop.latch:
 ; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; CHECK-NEXT:    br label [[LOOP_HEADER]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK-NEXT:    br label [[LOOP_HEADER]], [[LOOP13:!llvm.loop !.*]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
@@ -1074,10 +1081,11 @@ define i32 @me_reduction(i32* %addr) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 2, i64 2>
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
-; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP14:!llvm.loop !.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[TMP5]])
-; CHECK-NEXT:    br label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 201, 200
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
@@ -1087,15 +1095,15 @@ define i32 @me_reduction(i32* %addr) {
 ; CHECK-NEXT:    [[ACCUM:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[ACCUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i32, i32* [[ADDR]], i64 [[IV]]
 ; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV]], 200
-; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[EXIT:%.*]], label [[LOOP_LATCH]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[LOOP_LATCH]]
 ; CHECK:       loop.latch:
 ; CHECK-NEXT:    [[TMP8:%.*]] = load i32, i32* [[GEP]], align 4
 ; CHECK-NEXT:    [[ACCUM_NEXT]] = add i32 [[ACCUM]], [[TMP8]]
 ; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
 ; CHECK-NEXT:    [[EXITCOND2_NOT:%.*]] = icmp eq i64 [[IV]], 400
-; CHECK-NEXT:    br i1 [[EXITCOND2_NOT]], label [[EXIT]], label [[LOOP_HEADER]], !llvm.loop [[LOOP15:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EXITCOND2_NOT]], label [[EXIT]], label [[LOOP_HEADER]], [[LOOP15:!llvm.loop !.*]]
 ; CHECK:       exit:
-; CHECK-NEXT:    [[LCSSA:%.*]] = phi i32 [ 0, [[LOOP_HEADER]] ], [ [[ACCUM_NEXT]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[LCSSA:%.*]] = phi i32 [ 0, [[LOOP_HEADER]] ], [ [[ACCUM_NEXT]], [[LOOP_LATCH]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    ret i32 [[LCSSA]]
 ;
 ; TAILFOLD-LABEL: @me_reduction(


        


More information about the llvm-commits mailing list