diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -115,6 +115,7 @@
 #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"
@@ -502,6 +503,9 @@
   /// 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;
 
@@ -3460,6 +3464,8 @@
 
   // Remove redundant induction instructions.
   cse(LoopVectorBody);
+
+  fixProfileInfo();
 }
 
 void InnerLoopVectorizer::fixCrossIterationPHIs() {
@@ -3969,6 +3975,81 @@
   }
 }
 
+// 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.
+// Note: There are cases like foldTailByMasking() and requiresScalarEpiloque()
+// for which computations below don't give precise result but that should be OK
+// since profile is not precise anyway.
+void InnerLoopVectorizer::fixProfileInfo() {
+  uint64_t OrigTakenWeight = 0;
+  uint64_t OrigExitWeight = 0;
+  Loop *OrigLoop = LI->getLoopFor(LoopScalarBody);
+  auto *OrigBackBranchI = OrigLoop->getLoopLatch()->getTerminator();
+
+  if (!OrigBackBranchI->extractProfMetadata(OrigTakenWeight,
+                                           OrigExitWeight))
+    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(OrigTakenWeight, OrigExitWeight);
+
+  if  (OrigExitWeight == 0)
+    return;
+
+  // Calculate number of iterations in original scalar loop which is equal to
+  // (number of times header block was executed) /
+  //                    (number of times header was reached from pre-header) ==
+  // (OrigTakenWeight + OrigExitWeight) / OrigExitWeight ==
+  // (OrigTakenWeight / OrigExitWeight + 1)
+  // Note: Uses of OrigIterCount below 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 OrigAverageTripCount = OrigTakenWeight / OrigExitWeight + 1;
+  // Calculate number of iterations in vector loop.
+  uint64_t VecAverageTripCount = OrigAverageTripCount / (VF * UF);
+  // Calculate number of iterations for prolog/epilog loop.
+  uint64_t PEIterCount = OrigAverageTripCount % (VF * UF);
+
+  // Calculate taken and fall through counts for vector loop.
+  uint64_t VecTakenCount = 0;
+  uint64_t VecFallThrough = 0;
+  if (VecAverageTripCount > 0)  {
+    VecTakenCount = (VecAverageTripCount - 1) * OrigExitWeight;
+    VecFallThrough = OrigExitWeight;
+  }
+
+  // Now calculate counters for prolog/epilog loop.
+  uint64_t PETakenCount = 0;
+  uint64_t PEFallThroughCount = 0;
+  if (PEIterCount > 0) {
+    PETakenCount = (PEIterCount - 1) * OrigExitWeight;
+    PEFallThroughCount = OrigExitWeight;
+  }
+
+  // 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);
diff --git a/llvm/test/Transforms/LoopVectorize/check-prof-info.ll b/llvm/test/Transforms/LoopVectorize/check-prof-info.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/check-prof-info.ll
@@ -0,0 +1,97 @@
+; 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" -force-vector-width=4 -force-vector-interleave=4 -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_255:\!.*]],
+; 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_63:\!.*]],
+; 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_255:\!.*]],
+; CHECK:  [[FOR_BODY:for\.body]]:
+; CHECK:    br i1 [[EXITCOND:%.*]], label [[FOR_END_LOOPEXIT:%.*]], label %[[FOR_BODY]], !prof [[LP1_2:\!.*]],
+; CHECK-MASKED:  [[VECTOR_BODY:vector\.body]]:
+; CHECK-MASKED:    br i1 [[TMP:%.*]], label [[MIDDLE_BLOCK:%.*]], label %[[VECTOR_BODY]], !prof [[LP1_63:\!.*]],
+; CHECK-MASKED:  [[FOR_BODY:for\.body]]:
+; CHECK-MASKED:    br i1 [[EXITCOND:%.*]], label [[FOR_END_LOOPEXIT:%.*]], label %[[FOR_BODY]], !prof [[LP1_2:\!.*]],
+;
+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_255]] = !{!"branch_weights", i32 1, i32 255}
+; CHECK: [[LP0_0]] = !{!"branch_weights", i32 0, i32 0}
+; CHECK-MASKED: [[LP1_63]] = !{!"branch_weights", i32 1, i32 63}
+; CHECK-MASKED: [[LP0_0]] = !{!"branch_weights", i32 0, i32 0}
+; CHECK: [[LP1_2]] = !{!"branch_weights", i32 1, i32 2}
+
+!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 1023}
+!7 = !{!"branch_weights", i32 1, i32 1026}
diff --git a/llvm/test/Transforms/LoopVectorize/hot_short_tc_loop.ll b/llvm/test/Transforms/LoopVectorize/hot_short_tc_loop.ll
--- a/llvm/test/Transforms/LoopVectorize/hot_short_tc_loop.ll
+++ b/llvm/test/Transforms/LoopVectorize/hot_short_tc_loop.ll
@@ -13,12 +13,16 @@
 
 ; 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
@@ -74,6 +78,7 @@
 
 ; 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:%.*]]
@@ -118,11 +123,14 @@
 
 ; 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
@@ -188,6 +196,10 @@
 !llvm.module.flags = !{!0}
 !llvm.ident = !{!1}
 
+; CHECK: [[LP12]] = !{!"branch_weights", i32 999, i32 0}
+; CHECK: [[LP15]] = !{!"branch_weights", i32 999, i32 999}
+; 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}
diff --git a/llvm/test/Transforms/LoopVectorize/tripcount.ll b/llvm/test/Transforms/LoopVectorize/tripcount.ll
--- a/llvm/test/Transforms/LoopVectorize/tripcount.ll
+++ b/llvm/test/Transforms/LoopVectorize/tripcount.ll
@@ -61,8 +61,10 @@
 ; 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
 
@@ -205,6 +207,9 @@
   ret i32 0
 }
 
+; CHECK: [[LP3]] = !{!"branch_weights", i32 10, i32 2490}
+; CHECK: [[LP6]] = !{!"branch_weights", i32 10, i32 0}
+
 !0 = !{!"function_entry_count", i64 100}
 !1 = !{!"branch_weights", i32 100, i32 0}
 !2 = !{!"branch_weights", i32 10, i32 90}