Skip to content

Commit

Permalink
Revert "[LV] Unconditionally branch from middle to scalar preheader i…
Browse files Browse the repository at this point in the history 
…f the scalar loop must execute"

This reverts commit c23ce54.  I apparently missed some newly added non-x86 tests.
  • Loading branch information
@preames
preames committed May 17, 2021
1 parent c23ce54 commit d16da73
Show file tree
Hide file tree
Showing 5 changed files with 113 additions and 143 deletions.
2 changes: 1 addition & 1 deletion llvm/lib/Transforms/Utils/LoopVersioning.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -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");

Expand Down
124 changes: 41 additions & 83 deletions llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -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;

Expand Down Expand Up @@ -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(),
Expand All @@ -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);
Expand Down Expand Up @@ -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,
Expand All @@ -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);

Expand All @@ -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();
Expand Down Expand Up @@ -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());
Expand Down Expand Up @@ -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.
...
*/

Expand Down Expand Up @@ -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);

Expand Down Expand Up @@ -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) {
Expand Down Expand Up @@ -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.
Expand Down Expand Up @@ -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);

Expand Down Expand Up @@ -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.
Expand Down
30 changes: 16 additions & 14 deletions llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand All @@ -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
;
Expand Down Expand Up @@ -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
Expand All @@ -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
;
Expand Down Expand Up @@ -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]] ]
Expand All @@ -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:
Expand Down Expand Up @@ -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]] ]
Expand All @@ -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:
Expand Down
Loading

0 comments on commit d16da73

Please sign in to comment.