[LV] Vectorizer should adjust trip count in profile information

[ebrevnov]

Summary

Vectorized loop processes VFxUF number of elements in one iteration thus total number of iterations decreases proportionally. In addition epilog loop may not have more than VFxUF - 1 iterations. This patch updates profile information accordingly.

[ebrevnov]

Minor test update

[ebrevnov]

ping

[DaniilSuchkov]

LGTM

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

3980

Nit: VFxUF - 1

3986–3988

Style: it is usually advised to turn such conditions into early exits, it would reduce required indentation and slightly improve readability.

4007

Maybe introduce a new variable for this value (like EpilogueTakenCount)? Right now it's a bit surprising that OrigSomething is being changed. Same goes to OrigFallThroughCount.

[ebrevnov]

Minor fixes as requested by reviewer.

[ebrevnov]

I realized that current implementation has a flaw and and we should take into account that actual number of iterations is one greater than back edge taken count. In addition I believe that current structuring of calculations is easier for understanding.

[DaniilSuchkov]

LGTM

[Ayal]

Adding a few comments. Would be good to generalize and apply also to loop unroll (and jam).

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

3989

OrigFallThroughCount can still be either the exit count or the continue-to-next-iteration count, according to the code below. Wait to test if its zero until we know what it stands for?

4001

Better use distinct names, e.g., OrigExitCount and OrigBackedgeTakenCount, than continue to call them Taken and FallThrough. Perhaps use Weight instead of Count, to denote total profile frequencies, as the latter is used elsewhere to denote the actual per-invocation TripCount.

4004

bel[l]ow

4006

How about "OrigAverageTripCount"?

Explanation about its computation:
OrigAverageTripCount = (number of times header block was executed) / (number of times header was reached from pre-header == number of times latch exited)
== (OrigTakenCount + OrigFallThroughCount) / OrigFallThroughCount
== OrigTakenCount / OrigFallThroughCount + 1.

4008

How about VecAverageTripCount = OrigAverageTripCount / (VF * UF);

4012

Just to clarify, maintaining branch frequencies through optimizations is best-effort and imprecise - a total weight that does not divide VF*UF implies that the trip count of at-least one invocation did not divide VF*UF, not necessarily all of them; w/o considering also the distribution of trip counts in addition to their sum.

Setting PRIterCount = 0 and VecAverageTipCount = round(OrigAverageTripCount / (VF*UV)) when Cost->foldTailByMasking() is probably the best that can be done. The former is redundant given that it applies to dead code, and the latter should perhaps apply to all cases, in general.

4016

There's also the special case of requiresScalarEpiloque() where 0 < PEIterCount <= VF*UF for each invocation of the loop, and hence the average is also strictly positive FWIW. But best keep the approximation general instead of trying to improve it, given general lack of information.

4023

This assumes the number of times the vector loop will be reached is equal to the number of times the original scalar loop was reached (OrigFallThrougCount). This holds is Cost->foldTailByMasking(), but otherwise invocations whose trip count < VF*UF will bypass the vector loop (and also == VF*UF if requireScalarEpilogue()), plus other run time guards.

4032

Similar to above comment, invocations whose trip count divides VF*UF will bypass the scalar remainder loop (w/o foldTailByMasking nor requireScalarEpilogue), so in general PEFallThroughCount <= OrigFallThroughCount.

llvm/test/Transforms/LoopVectorize/check-prof-info.ll

4

May want to also check with UF>1.

[ebrevnov]

Addressed Ayal's comments

[ebrevnov]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

3989

Good catch. Thanks!

4001

I fixed names. But I don't see reasons to use different variables here (if this is what you meant)

4004

fixed

4006

Ok. Turned your explanation to a comment.

4016

Agree. Let me remove this special case then.

4023

Please note that VecFallThrough is zero initially and set to OrigFallThrougCount only if vector loop is expected to be executed (VecIterCount > 0)

4032

Same explanation as for the above.

llvm/test/Transforms/LoopVectorize/check-prof-info.ll

4

I replaced masked case since we don't do anything special for it now.

[ebrevnov]

ping @Ayal

[Ayal]

Still think it would be better to provide this as a standalone function in Transforms/Utils/LoopUtils, for potential benefit of loop unroll (and jam) passes in addition to LV. Having agreed to ignore foldTail and requiresScalarEpilog, there's nothing vectorization-specific to do here. There's still an issue though with the fact that LV may use the scalar loop for both the remaining TC%(VF*UF) iterations when running the vector loop, and for all TC iterations when runtime guards bypass the vector loop. In absence of information, each such guard could be assigned 0.5 probability, or one could be aggressively optimistic and hope vector loop is always reached. In any case this deserves a comment.

Suggesting further variable name changes for the three Orig, Unrolled, and Remainder Loops, each having a LoopEntry==LoopExit edge weight, a Backedge weight, a HeaderBlock weight, and an AverageTripCount. The actual weights are recorded as TrueVal and FalseVal of the latch branches.

Patch needs to be clang-format'ed.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

3978

"is less ... than original TC" >> "is smaller than the original TC by a factor of VFxUF"

3985

OrigTakenWeight >> OrigBackedgeTakenWeight or OrigBackedgeWeight ?
OrigExitWeight >> OrigLoopExitWeight?
May help to also set OrigLoopEntryWeight = OrigLoopExitWeight?

3988

OrigBackBranchI >> OrigLoopLatchBranch ?

3991

It seems clearer to call extractProfMetadata(TrueVal, FalseVal) and then set BackedgeTaken and LoopExit/Entry weights according to if (OrigLoopLatchBranch->getSuccessor(0) == OrigLoop->getHeader()), following LoopUtil's getLoopEstimatedTripCount(). Analogously for createBranchWeights(TrueVal, FalseVal).

In any case, better rename "IsTrueBackEdge*Loop".

4005

Patch needs to be clang-format'ed

4012

Instead of providing the explanation in a comment, seems better to implement the code this way, leaving the +1 for the compiler to optimize. I.e.,

const uint64_t OrigHeaderBlockWeight = OrigBackedgeTakenWeight + OrigLoopEntryWeight;
const unit64_t OrigAverageTripCount = OrigHeaderBlockWeight / OrigLoopEntryWeight;

4019

Better rename/expand "PE".
PEIterCount >> RemainderLoopAverageTripCount?

4023

In the general context, "Vec" >> "UnrolledLoop".
VecTakenCount >> UnrolledLoopBackedgeWeight
VecFallThrough >> UnrolledLoopExitWeight and/or UnrolledLoopEntryWeight

4025

How about

if (UnrolledLoopAverageTripCount > 0) {
  UnrolledLoopEntryWeight = OrigLoopEntryWeight;
  uint64_t UnrolledLoopHeaderWeight = UnrolledLoopAverageTripCount * UnrolledLoopEntryWeight; // Analogous to computing OrigLoopAverageTripCount from Header and Entry weights above.
  UnrolledLoopBackedgeWeight = UnrolledLoopHeaderWeight - UnrolledLoopEntryWeight;
}

leaving the -1 optimization to the compiler.

4031

PETakenCount >> RemainderLoopBackedgeWeight
PEFallThroughCount >> RemainderLoopExitWeight and/or RemainderLoopEntryWeight

[ebrevnov]

In D67905#1770563, @Ayal wrote:

Still think it would be better to provide this as a standalone function in Transforms/Utils/LoopUtils, for potential benefit of loop unroll (and jam) passes in addition to LV. Having agreed to ignore foldTail and requiresScalarEpilog, there's nothing vectorization-specific to do here. There's still an issue though with the fact that LV may use the scalar loop for both the remaining TC%(VF*UF) iterations when running the vector loop, and for all TC iterations when runtime guards bypass the vector loop. In absence of information, each such guard could be assigned 0.5 probability, or one could be aggressively optimistic and hope vector loop is always reached. In any case this deserves a comment.

Suggesting further variable name changes for the three Orig, Unrolled, and Remainder Loops, each having a LoopEntry==LoopExit edge weight, a Backedge weight, a HeaderBlock weight, and an AverageTripCount. The actual weights are recorded as TrueVal and FalseVal of the latch branches.

Patch needs to be clang-format'ed.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

3991

Don't feel convinced. My point would be that extra variables and conditional reassignments make the code less readable. I think this is very subjective thing.

4025

That will make computations less stable to overflow. Personally I feel the way it's written today has the same level of complexity for understanding.

[ebrevnov]

Addressing issues raised by Ayal.

[ebrevnov]

Typo fixed.

[ebrevnov]

ping @Ayal

[Ayal]

llvm/include/llvm/Transforms/Utils/LoopUtils.h

361 ↗

(On Diff #232779)

The fact that OrigLoop is both the original loop containing the original profile weights, and acts as the RemainderLoop dedicated to leftover iterations, should be clarified. Alternatively, this utility can receive three loops: OrigLoop, UnrolledLoop and RemainderLoop, leaving it to the caller to decide if to pass OrigLoop also as RemainderLoop.

Would probably be clearer to start with UnrolledLoop receiving weights that reflect TC/UF iterations, and then OrigLoop which receives weights that reflect the remaining TC%UF iterations.

363 ↗

(On Diff #232779)

U[n]rolledLoop, several occurrences.

"\UF" >> "\p UF"

llvm/lib/Transforms/Utils/LoopUtils.cpp

1040 ↗

(On Diff #232779)

Worth commenting that OrigLoopEntryWeight also holds OrigLoopExitWeight, which is more clearly the weight associated with the (exit direction of the) latch branch.

1048 ↗

(On Diff #232779)

UnrolledBBI >> Unrolled[Loop]LatchBranch, as in OrigLoopLatchBranch.

As the names end up overflowing lines, can use Orig, Unrolled and Remainder to stand for OrigLoop, UnrolledLoop and RemainderLoop; i.e., taking "Loop" out.

1051 ↗

(On Diff #232779)

VecLoop >> UnrolledLoop

1061 ↗

(On Diff #232779)

Can drop the 'const', for consistency; these temporaries are obviously const's.

1064 ↗

(On Diff #232779)

Note that this is rounding down. Can add half of the denominator to the nominator before dividing in order to round more accurately; this is what getLoopEstimatedTripCount() does, but it seems to be off by 1 as it computes BackEdgeTakenWeight / LoopEntryWeight rounded to nearest, instead of HeaderBlockWeight / LoopEntryWeight rounded to nearest...

Simply call OrigAverageTripCount = getLoopEstimatedTripCount(OrigLoop)?

Perhaps having a setLoopEstimatedTripCount(Loop, EstimatedTripCount, EstimatedEntryWeight) would help fold the identical treatment of UnrolledLoop and RemainderLoop into one function, which also takes care of figuring out the True/False vs. Backedge/Exit directions?

1066 ↗

(On Diff #232779)

U[n]rolledAverageTripCount

1076 ↗

(On Diff #232779)

Seems slightly more logical to first set UnrolledLoopEntryWeight, and then using it set UnrolledLoopBackedgeWeight.

1085 ↗

(On Diff #232779)

ditto

1098 ↗

(On Diff #232779)

(This actually replaces the old profile metadata with the new one.)

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

118

Is this include still needed here?

3467

Comment below should start with a short sentence explaining that profile weights associated with the original loop are now distributed among the vector and scalar loops.

[ebrevnov]

llvm/lib/Transforms/Utils/LoopUtils.cpp

1040 ↗

(On Diff #232779)

IMHO instead of trying to clarify with a comment we better find self descriptive name for such a simple and commonly used thing. Strictly speaking OrigLoopEntryWeight != OrigLoopExitWeight. Do you find OrigBackEdgeExitWeight good enough?

1048 ↗

(On Diff #232779)

Removed "Loop" from most names to make them a little shorter.

1064 ↗

(On Diff #232779)

This "off by 1" stopped me from using it in the first place since that could be important in some cases. OK, let's reuse getLoopEstimatedTripCount. To be able to do that there are some changes to getLoopEstimatedTripCount.

[ebrevnov]

Updated as requested.

[ebrevnov]

Hi @Ayal. Thanks for you input. I fixed all places as you suggested. Please check.

[Ayal]

Thanks for making all the changes! More comments inline.

llvm/lib/Transforms/Utils/LoopUtils.cpp

680 ↗

(On Diff #235335)

Comment what this new function is for. Rename (see below)? Retain "Support loops ..." comment, added in D64553?

712 ↗

(On Diff #235335)

dyn_cast >> cast

Perhaps update above function to do here something like
BranchInst *LatchBR = getExpectedExitLoopLatchBranch(L)
checking if it returned nullptr or not?

733 ↗

(On Diff #235335)

Thanks for taking care of this fix to improve accuracy of estimated TC!
But doing so deserves a separate patch, and tests. Note that it also effects loop unrolling, i.e., its effects are beyond LV. This part can be introduced either before or after the part that teaches LV to maintain profiling info.

754 ↗

(On Diff #235335)

ditto (dyn_cast >> cast, ...)

755 ↗

(On Diff #235335)

Better check similar to above if (LatchBR->getSuccessor(0) != L->getHeader())

1085 ↗

(On Diff #235335)

"the \p UnrolledLoop \p RemainderLoop" >>
"\p UnrolledLoop and \p RemainderLoop"

1089 ↗

(On Diff #235335)

May also be worthwhile asserting that UF is positive (or greater than 1?)

1090 ↗

(On Diff #235335)

are expected to be distinct

1040 ↗

(On Diff #232779)

IMHO instead of trying to clarify with a comment we better find self descriptive name for such a simple and commonly used thing.

Definitely agree with (the preference of) finding self descriptive variable names.

Strictly speaking OrigLoopEntryWeight != OrigLoopExitWeight"

How so, given that OrigLoop has a single-entry, and an "expected" single-exit: there may be other "side/deopt" exits, but these are expected to have zero weight. E.g., when computing LoopHeaderWeight above, adding LoopEntryWeight (instead of LoopExitWeight) to BackEdgeTakenWeight seems more logical.

Do you find OrigBackEdgeExitWeight good enough?

Strictly speaking, a BackEdge cannot exit: it is an edge going from a latch block to a header block, and "BackEdgeTaken" is the number of times this edge is taken=traversed, which equals the number of times its latch branch is "taken" rather than "falls-thru" (if it's true direction points to the header). Perhaps LoopEntryExitWeight or LoopInvocationWeight could be used instead/in addition.

1064 ↗

(On Diff #232779)

This "off by 1" stopped me from using it in the first place since that could be important in some cases. OK, let's reuse getLoopEstimatedTripCount. To be able to do that there are some changes to getLoopEstimatedTripCount.

Indeed, best fix and reuse, in a dedicated patch as raised above, thereby isolating impact on such "some cases".

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

3476

"is not taken into account as unlikely case" >>
"is ignored, assigning all the weight to the vector loop, optimistically"

llvm/test/Transforms/LoopVectorize/check-prof-info.ll

7

Tests targeting x86 need to reside in LoopVectorize/X86

[ebrevnov]

One more round of updates.

[ebrevnov]

llvm/lib/Transforms/Utils/LoopUtils.cpp

680 ↗

(On Diff #235335)

The comment is related to get/setLoopEstimatedTripCount and still there...

712 ↗

(On Diff #235335)

I was thinking about that in the first place but didn't come up with a "good" enough name. I can go with that name if you like :-)

733 ↗

(On Diff #235335)

Ok.

1089 ↗

(On Diff #235335)

I think we better support 1 which could be used in some corner cases....

1040 ↗

(On Diff #232779)

How so, given that OrigLoop has a single-entry, and an "expected" single-exit: there may be other "side/deopt" exits, but these are expected to have zero weight. E.g., when computing LoopHeaderWeight above, adding LoopEntryWeight (instead of LoopExitWeight) to BackEdgeTakenWeight seems more logical.

For infinite loop entry is 1 while exit is 0 :-). I understand this is extreme we will never meet but still....

Strictly speaking, a BackEdge cannot exit: it is an edge going from a latch block to a header block, and "BackEdgeTaken" is the number of times this edge is taken=traversed, which equals the number of times its latch branch is "taken" rather than "falls-thru" (if it's true direction points to the header).

That's why I used TakenCount and FallThroughCount in the very first version what perfectly matches your description. I don't feel we are getting any better names with more iterations.... Perhaps LatchCycleWeight - number of times we go to loop header from the latch and LatchExitWeight - number of times we go to loop exit from the latch?

Perhaps LoopEntryExitWeight or LoopInvocationWeight could be used instead/in addition.

I think LoopEntryExitWeight may be confusing....
I think it makes sense to use EstimatedLoopInvocationWeight in conjunction with EstimatedTripCount as parameters to get/setEstimatedTripCount interface while LatchCycleWeight and LatchExitWeight in the implementation as they are little-bit more low level.

[ebrevnov]

Rebase

[ebrevnov]

Rebase

[ebrevnov]

ping @Ayal

[Ayal]

This looks good to me, thanks!

llvm/lib/Transforms/Utils/LoopUtils.cpp

775 ↗

(On Diff #236991)

The last part could call fixupBranchWeights() if moved here from Transforms/Utils/LoopUnrollPeel.cpp

llvm/test/Transforms/LoopVectorize/tripcount.ll

211

Following this, to clarify:
original loop has latchExitWeight=10 and backedgeTakenWeight=10,000, therefore estimatedBackedgeTakenCount=1,000 and estimatedTripCount=1,001.
Vectorizing by 4 produces
estimatedTripCounts of 1,001/4=250 and 1,001%4=1 for vectorized and remainder loops, respectively, therefore their
estimatedBackedgeTakenCounts are 249 and 0, and so the weights recorded with loop invocation weights of 10 are the above {10, 2490} and {10, 0}.

[ebrevnov]

llvm/lib/Transforms/Utils/LoopUtils.cpp

775 ↗

(On Diff #236991)

That would require to change implementation for fixupBranchWeights since it disregards to update when back edge taken count is zero.

llvm/test/Transforms/LoopVectorize/tripcount.ll

211

I will add this text to the test. I that what you wanted (just not sure :-))?

[ebrevnov]

Rebase

[Ayal]

llvm/lib/Transforms/Utils/LoopUtils.cpp

775 ↗

(On Diff #236991)

Agreed. Regarding disregarding to update when backedge taken weight is zero, note that in fixupBranchWeights(), BackedgeTakenWeight is called FallThroughWeight(?) "The weight of the edge from Latch to Header", and that

// FallThroughWeight is 0 means that there is no branch weights on original
// latch block or estimated trip count is zero.

Regarding the first meaning of 0, whoever calls fixupBranchWeights() should do so only if there were such weights on the original latch block, similar to the caller of setLoopEstimatedTripCount(). Regarding the second meaning of 0, it seem fixupBranchWeights() suffers from same +1 issue: estimating trip count to be zero when backedge taken weight is zero.

It would be good to fix and centralize the support for updating weights of loops, but such refactoring can be done as a separate follow-up patch, after landing this (accepted) patch.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

 #include "llvm/IR/Function.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/MDBuilder.h"
 #include "llvm/IR/Metadata.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/Use.h"
 #include "llvm/IR/User.h"
 #include "llvm/IR/Value.h"
 #include "llvm/IR/ValueHandle.h"
public:
 
   /// Set the debug location in the builder using the debug location in
   /// the instruction.
   void setDebugLocFromInst(IRBuilder<> &B, const Value *Ptr);
 
   /// Fix the non-induction PHIs in the OrigPHIsToFix vector.
   void fixNonInductionPHIs(void);
 
+  /// Update profile info of the vector and prolog/epilog loops.
+  void fixProfileInfo();
+
 protected:
   friend class LoopVectorizationPlanner;
 
   /// A small list of PHINodes.
   using PhiVector = SmallVector<PHINode *, 4>;
 
   /// A type for scalarized values in the new loop. Each value from the
   /// original loop, when scalarized, is represented by UF x VF scalar values
fixupIVUsers(Entry.first, Entry.second,
                  IVEndValues[Entry.first], LoopMiddleBlock);
 
   fixLCSSAPHIs();
   for (Instruction *PI : PredicatedInstructions)
     sinkScalarOperands(&*PI);
 
   // Remove redundant induction instructions.
   cse(LoopVectorBody);
+
+  fixProfileInfo();
 }
 
 void InnerLoopVectorizer::fixCrossIterationPHIs() {
   // In order to support recurrences we need to be able to vectorize Phi nodes.
   // Phi nodes have cycles, so we need to vectorize them in two stages. This is
   // stage #2: We now need to fix the recurrences by adding incoming edges to
   // the currently empty PHI nodes. At this point every instruction in the
   // original loop is widened to a vector form so we can use them to construct
   // the incoming edges.
   for (PHINode &Phi : OrigLoop->getHeader()->phis()) {
     // Handle first-order recurrences and reductions that need to be fixed.
     if (Legal->isFirstOrderRecurrence(&Phi))
       fixFirstOrderRecurrence(&Phi);
     else if (Legal->isReductionVariable(&Phi))
       fixReduction(&Phi);
   }
for (unsigned i = 0; i < NumIncomingValues; ++i) {
 
       // Scalar incoming value may need a broadcast
       Value *NewIncV = getOrCreateVectorValue(ScIncV, 0);
       NewPhi->addIncoming(NewIncV, NewPredBB);
     }
   }
 }
 
+// Update profile info since expected TC of vectorized loop is less by VFxUF
+// than original TC. At the same time original loop becomes prolog/epilog loop
+// and has less than VFxUF iterations.
+void InnerLoopVectorizer::fixProfileInfo() {
+  uint64_t OrigTakenCount = 0;
+  uint64_t OrigFallThroughCount = 0;
+  Loop *OrigLoop = LI->getLoopFor(LoopScalarBody);
+  auto *OrigBackBranchI = OrigLoop->getLoopLatch()->getTerminator();
+
+  if (!OrigBackBranchI->extractProfMetadata(OrigTakenCount,
+                                           OrigFallThroughCount) ||
+      OrigFallThroughCount == 0)
+    return;
+
+  Loop *VecLoop = LI->getLoopFor(LoopVectorBody);
+  MDBuilder MDB(OrigBackBranchI->getContext());
+  auto *VectorBackBranchI = VecLoop->getLoopLatch()->getTerminator();
+  bool IsTrueBackEdgeOrigLoop =
+      OrigLoop->contains(*succ_begin(OrigLoop->getLoopLatch()));
+  bool IsTrueBackEdgeVecLoop =
+      VecLoop->contains(*succ_begin(VecLoop->getLoopLatch()));
+
+  if (!IsTrueBackEdgeOrigLoop)
+    std::swap(OrigTakenCount, OrigFallThroughCount);
+
+  // Uses of OrigIterCount bellow should not be simplified as it will
+  // produce a different value. In other words: (A mod N) * B != (A*B) mod N
+  const uint64_t OrigIterCount = OrigTakenCount / OrigFallThroughCount;
+  // Calculate taken and fall through counts for vector loop.
+  uint64_t VecTakenCount = (OrigIterCount / (VF * UF)) * OrigFallThroughCount;
+  uint64_t VecFallThrough = OrigFallThroughCount;
+  // Now calculate counters for prolog/epilog loop.
+  uint64_t PETakenCount = (OrigIterCount % (VF * UF)) * OrigFallThroughCount;
+  uint64_t PEFallThroughCount = OrigTakenCount;
+
+  // Adjust number of iterations in vector and epilog loops if epilog
+  // iterations executed as part of the main loop.
+  if (PETakenCount != 0 && Cost->foldTailByMasking()) {
+    ++VecTakenCount;
+    PETakenCount = 0;
+  }
+  // Bottom test is never reached if loop has zero iterations.
+  if (VecTakenCount == 0)
+    VecFallThrough = 0;
+  // Bottom test is never reached if loop has zero iterations.
+  if (PETakenCount == 0)
+    PEFallThroughCount = 0;
+  // Make a swap if back edge is taken when condition "false".
+  if (!IsTrueBackEdgeVecLoop)
+    std::swap(VecTakenCount, VecFallThrough);
+  // Set new profile metadata.
+  VectorBackBranchI->setMetadata(
+      LLVMContext::MD_prof,
+      MDB.createBranchWeights(VecTakenCount, VecFallThrough));
+  // Make a swap if back edge is taken when condition "false".
+  if (!IsTrueBackEdgeOrigLoop)
+    std::swap(PETakenCount, PEFallThroughCount);
+  // Set new profile metadata.
+  OrigBackBranchI->setMetadata(
+      LLVMContext::MD_prof,
+      MDB.createBranchWeights(PETakenCount, PEFallThroughCount));
+}
+
 void InnerLoopVectorizer::widenPHIInstruction(Instruction *PN, unsigned UF,
                                               unsigned VF) {
   PHINode *P = cast<PHINode>(PN);
   if (EnableVPlanNativePath) {
     // Currently we enter here in the VPlan-native path for non-induction
     // PHIs where all control flow is uniform. We simply widen these PHIs.
     // Create a vector phi with no operands - the vector phi operands will be
     // set at the end of vector code generation.

llvm/test/Transforms/LoopVectorize/check-prof-info.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt  -passes="print<block-freq>,loop-vectorize" -force-vector-width=4 -force-vector-interleave=1 -S < %s |  FileCheck %s
+; RUN: opt  -passes="print<block-freq>,loop-vectorize" -prefer-predicate-over-epilog=true -force-vector-width=4 -force-vector-interleave=1 -S < %s |  FileCheck %s -check-prefix=CHECK-MASKED
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@a = dso_local global [1024 x i32] zeroinitializer, align 16
+@b = dso_local global [1024 x i32] zeroinitializer, align 16
+
+; Check correctness of profile info for vectorization without epilog.
+; Function Attrs: nofree norecurse nounwind uwtable
+define dso_local void @_Z3foov() local_unnamed_addr #0 {
+; CHECK-LABEL: @_Z3foov(
+; CHECK:  [[VECTOR_BODY:vector\.body]]:
+; CHECK:    br i1 [[TMP:%.*]], label [[MIDDLE_BLOCK:%.*]], label %[[VECTOR_BODY]], !prof [[LP1_256:\!.*]],
+; CHECK:  [[FOR_BODY:for\.body]]:
+; CHECK:    br i1 [[EXITCOND:%.*]], label [[FOR_END_LOOPEXIT:%.*]], label %[[FOR_BODY]], !prof [[LP0_0:\!.*]],
+; CHECK-MASKED:  [[VECTOR_BODY:vector\.body]]:
+; CHECK-MASKED:    br i1 [[TMP:%.*]], label [[MIDDLE_BLOCK:%.*]], label %[[VECTOR_BODY]], !prof [[LP1_256:\!.*]],
+; CHECK-MASKED:  [[FOR_BODY:for\.body]]:
+; CHECK-MASKED:    br i1 [[EXITCOND:%.*]], label [[FOR_END_LOOPEXIT:%.*]], label %[[FOR_BODY]], !prof [[LP0_0:\!.*]],
+;
+entry:
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body
+  ret void
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds [1024 x i32], [1024 x i32]* @b, i64 0, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4, !tbaa !2
+  %1 = trunc i64 %indvars.iv to i32
+  %mul = mul nsw i32 %0, %1
+  %arrayidx2 = getelementptr inbounds [1024 x i32], [1024 x i32]* @a, i64 0, i64 %indvars.iv
+  %2 = load i32, i32* %arrayidx2, align 4, !tbaa !2
+  %add = add nsw i32 %2, %mul
+  store i32 %add, i32* %arrayidx2, align 4, !tbaa !2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body, !prof !6
+}
+
+; Check correctness of profile info for vectorization with epilog.
+; Function Attrs: nofree norecurse nounwind uwtable
+define dso_local void @_Z3foo2v() local_unnamed_addr #0 {
+; CHECK-LABEL: @_Z3foo2v(
+; CHECK:  [[VECTOR_BODY:vector\.body]]:
+; CHECK:    br i1 [[TMP:%.*]], label [[MIDDLE_BLOCK:%.*]], label %[[VECTOR_BODY]], !prof [[LP1_256:\!.*]],
+; CHECK:  [[FOR_BODY:for\.body]]:
+; CHECK:    br i1 [[EXITCOND:%.*]], label [[FOR_END_LOOPEXIT:%.*]], label %[[FOR_BODY]], !prof [[LP1_3:\!.*]],
+; CHECK-MASKED:  [[VECTOR_BODY:vector\.body]]:
+; CHECK-MASKED:    br i1 [[TMP:%.*]], label [[MIDDLE_BLOCK:%.*]], label %[[VECTOR_BODY]], !prof [[LP1_257:\!.*]],
+; CHECK-MASKED:  [[FOR_BODY:for\.body]]:
+; CHECK-MASKED:    br i1 [[EXITCOND:%.*]], label [[FOR_END_LOOPEXIT:%.*]], label %[[FOR_BODY]], !prof [[LP0_0:\!.*]],
+;
+entry:
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body
+  ret void
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds [1024 x i32], [1024 x i32]* @b, i64 0, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4, !tbaa !2
+  %1 = trunc i64 %indvars.iv to i32
+  %mul = mul nsw i32 %0, %1
+  %arrayidx2 = getelementptr inbounds [1024 x i32], [1024 x i32]* @a, i64 0, i64 %indvars.iv
+  %2 = load i32, i32* %arrayidx2, align 4, !tbaa !2
+  %add = add nsw i32 %2, %mul
+  store i32 %add, i32* %arrayidx2, align 4, !tbaa !2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1027
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body, !prof !7
+}
+
+attributes #0 = { "use-soft-float"="false" }
+
+!llvm.module.flags = !{!0}
+!llvm.ident = !{!1}
+
+; CHECK: [[LP1_256]] = !{!"branch_weights", i32 1, i32 256}
+; CHECK: [[LP0_0]] = !{!"branch_weights", i32 0, i32 0}
+; CHECK-MASKED: [[LP0_0]] = !{!"branch_weights", i32 0, i32 0}
+; CHECK: [[LP1_3]] = !{!"branch_weights", i32 1, i32 3}
+; CHECK-MASKED: [[LP1_257]] = !{!"branch_weights", i32 1, i32 257}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{!"clang version 10.0.0 (https://github.com/llvm/llvm-project c292b5b5e059e6ce3e6449e6827ef7e1037c21c4)"}
+!2 = !{!3, !3, i64 0}
+!3 = !{!"int", !4, i64 0}
+!4 = !{!"omnipotent char", !5, i64 0}
+!5 = !{!"Simple C++ TBAA"}
+!6 = !{!"branch_weights", i32 1, i32 1024}
+!7 = !{!"branch_weights", i32 1, i32 1027}

llvm/test/Transforms/LoopVectorize/hot_short_tc_loop.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -passes="print<block-freq>,loop-vectorize" -S < %s 2>&1 |  FileCheck %s
 
 ; Check vectorization of hot short trip count with epilog. In this case inner
 ; loop trip count is not constant and its value is estimated by profile.
 
 ; ModuleID = 'test.cpp'
 target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 @a = dso_local global [5 x i32] zeroinitializer, align 16
 @b = dso_local global [5 x i32] zeroinitializer, align 16
 
 ; Function Attrs: uwtable
 define dso_local void @_Z3fooi(i32 %M) local_unnamed_addr #0 !prof !11 {
+; CHECK-LABEL: @_Z3fooi(
+; CHECK:  [[VECTOR_BODY:vector\.body]]:
 ; CHECK:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP15:%.*]]
 ; CHECK:    [[TMP18:%.*]] = mul nsw <4 x i32> [[WIDE_LOAD]], [[VEC_IND6:%.*]]
 ; CHECK:    [[WIDE_LOAD10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP23:%.*]]
 ; CHECK:    [[TMP26:%.*]] = add nsw <4 x i32> [[WIDE_LOAD10]], [[TMP18]]
 ; CHECK:    store <4 x i32> [[TMP26]], <4 x i32>* [[TMP28:%.*]]
-;
+; CHECK:    br i1 [[TMP30:%.*]], label [[MIDDLE_BLOCK:%.*]], label %[[VECTOR_BODY]], !prof [[LP12:\!.*]],
+; CHECK:  [[SCAL_BODY:for\.body4\.us]]:
+; CHECK:    br i1 [[EXITCOND:%.*]], label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US:%.*]], label %[[SCAL_BODY]], !prof [[LP15:\!.*]],
 entry:
   %a = alloca [5 x i32], align 16
   %b = alloca [5 x i32], align 16
   %0 = bitcast [5 x i32]* %a to i8*
   call void @llvm.lifetime.start.p0i8(i64 20, i8* nonnull %0) #3
   %1 = bitcast [5 x i32]* %b to i8*
   call void @llvm.lifetime.start.p0i8(i64 20, i8* nonnull %1) #3
   %arraydecay = getelementptr inbounds [5 x i32], [5 x i32]* %a, i64 0, i64 0
for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit24, %for.cond.cleanup.loopexit
   ret void
 }
 
 ; Check vectorization of hot short trip count with epilog. In this case inner
 ; loop trip count is known constant value.
 
 ; Function Attrs: uwtable
 define dso_local void @_Z3fooi2() local_unnamed_addr #0 !prof !11 {
+; CHECK-LABEL: @_Z3fooi2(
 ; CHECK:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP15:%.*]]
 ; CHECK:    [[TMP18:%.*]] = mul nsw <4 x i32> [[WIDE_LOAD]], [[VEC_IND6:%.*]]
 ; CHECK:    [[WIDE_LOAD10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP23:%.*]]
 ; CHECK:    [[TMP26:%.*]] = add nsw <4 x i32> [[WIDE_LOAD10]], [[TMP18]]
 ; CHECK:    store <4 x i32> [[TMP26]], <4 x i32>* [[TMP28:%.*]]
 ;
 entry:
   br label %for.body

 
 ; This is negative test. Check that vectorization is not performed for COLD
 ; short trip count loop requiring epilog. Note that outer loop has only 20
 ; iterations and there is no associated profile info.
 
 
 ; Function Attrs: uwtable
 define dso_local void @_Z3fooi3(i32 %M) local_unnamed_addr #0 !prof !11 {
+; CHECK-LABEL: @_Z3fooi3(
+; CHECK:  [[SCAL_BODY:for\.body4\.us]]:
 ; CHECK:    [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX_US:%.*]]
 ; CHECK:    [[MUL_US:%.*]] = mul nsw i32 [[TMP2]], [[TMP3:%.*]]
 ; CHECK:    [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX6_US:%.*]]
 ; CHECK:    [[ADD_US:%.*]] = add nsw i32 [[TMP4]], [[MUL_US]]
 ; CHECK:    store i32 [[ADD_US]], i32* [[ARRAYIDX6_US]]
+; CHECK:    br i1 [[EXITCOND:%.*]], label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US:%.*]], label %[[SCAL_BODY]], !prof [[LP26:\!.*]]
 ;
 entry:
   %a = alloca [5 x i32], align 16
   %b = alloca [5 x i32], align 16
   %0 = bitcast [5 x i32]* %a to i8*
   call void @llvm.lifetime.start.p0i8(i64 20, i8* nonnull %0) #3
   %1 = bitcast [5 x i32]* %b to i8*
   call void @llvm.lifetime.start.p0i8(i64 20, i8* nonnull %1) #3

 declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture) #1
 
 attributes #0 = { "use-soft-float"="false" }
 attributes #1 = { argmemonly nounwind willreturn }
 
 !llvm.module.flags = !{!0}
 !llvm.ident = !{!1}
 
+; CHECK: [[LP12]] = !{!"branch_weights", i32 0, i32 0}
+; CHECK: [[LP15]] = !{!"branch_weights", i32 999, i32 4995}
+; CHECK: [[LP26]] = !{!"branch_weights", i32 9, i32 45}
+
 !0 = !{i32 1, !"wchar_size", i32 4}
 !1 = !{!"clang version 10.0.0 (https://github.com/llvm/llvm-project f379dd57b978c4e1483d721f422c79e3c0c5ccdc)"}
 !2 = !{!3, !3, i64 0}
 !3 = !{!"int", !4, i64 0}
 !4 = !{!"omnipotent char", !5, i64 0}
 !5 = !{!"Simple C++ TBAA"}
 !6 = distinct !{!6, !7}
 !7 = !{!"llvm.loop.isvectorized", i32 1}
 !8 = distinct !{!8, !9, !7}
 !9 = !{!"llvm.loop.unroll.runtime.disable"}
 !10 = !{!"branch_weights", i32 999, i32 4995}
 !11 = !{!"function_entry_count", i64 1}
 !12 = !{!"branch_weights", i32 1, i32 999}
 !13 = !{!"branch_weights", i32 1000, i32 1}
 !14 = !{!"branch_weights", i32 9, i32 45}

llvm/test/Transforms/LoopVectorize/tripcount.ll

for.end:                                          ; preds = %for.body
   ret i32 0
 }
 
 define i32 @foo_low_trip_count3(i1 %cond, i32 %bound) !prof !0 {
 ; The loop has low invocation count compare to the function invocation count,
 ; but has a high trip count per invocation. Vectorize it.
 
 ; CHECK-LABEL: @foo_low_trip_count3(
-; CHECK: vector.body:
-
+; CHECK:  [[VECTOR_BODY:vector\.body]]:
+; CHECK:    br i1 [[TMP9:%.*]], label [[MIDDLE_BLOCK:%.*]], label %[[VECTOR_BODY]], !prof [[LP3:\!.*]],
+; CHECK:  [[FOR_BODY:for\.body]]:
+; CHECK:    br i1 [[EXITCOND:%.*]], label [[FOR_END_LOOPEXIT:%.*]], label %[[FOR_BODY]], !prof [[LP6:\!.*]],
 entry:
   br i1 %cond, label %for.preheader, label %for.end, !prof !2
 
 for.preheader:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %i.08 = phi i32 [ 0, %for.preheader ], [ %inc, %for.body ]
for.body:                                         ; preds = %for.body, %entry
   %inc = add nsw i32 %i.08, 1
   %exitcond = icmp slt i32 %i.08, 1000
   br i1 %exitcond, label %for.body, label %for.end, !prof !1
 
 for.end:                                          ; preds = %for.body
   ret i32 0
 }
 
+; CHECK: [[LP3]] = !{!"branch_weights", i32 10, i32 2500}
+; CHECK: [[LP6]] = !{!"branch_weights", i32 0, i32 0}
+
 !0 = !{!"function_entry_count", i64 100}
 !1 = !{!"branch_weights", i32 100, i32 0}
 !2 = !{!"branch_weights", i32 10, i32 90}
 !3 = !{!"branch_weights", i32 10, i32 10000}