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
@@ -8902,6 +8902,18 @@
   VPBasicBlock *MiddleVPBB = new VPBasicBlock("middle.block");
   VPBlockUtils::insertBlockAfter(MiddleVPBB, TopRegion);
 
+  // Add VPValues for known constant strides guaranteed by predicate scalar
+  // evolution.
+  for (auto [_, Stride] : Legal->getLAI()->getSymbolicStrides()) {
+    auto *ScevStride = cast<SCEVConstant>(PSE.getSCEV(Stride));
+    Constant *CI = ConstantInt::get(Stride->getType(), ScevStride->getAPInt());
+    if (Plan->hasVPValueFor(Stride))
+      assert(Plan->getVPValue(Stride)->getLiveInIRValue() == CI &&
+             "Added different constants for the same stride!");
+    else
+      Plan->addVPValue(Stride, new VPValue(CI));
+  }
+
   // Don't use getDecisionAndClampRange here, because we don't know the UF
   // so this function is better to be conservative, rather than to split
   // it up into different VPlans.
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.h b/llvm/lib/Transforms/Vectorize/VPlan.h
--- a/llvm/lib/Transforms/Vectorize/VPlan.h
+++ b/llvm/lib/Transforms/Vectorize/VPlan.h
@@ -2345,6 +2345,8 @@
     Value2VPValue.erase(V);
   }
 
+  bool hasVPValueFor(Value *V) const { return Value2VPValue.contains(V); }
+
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
   /// Print this VPlan to \p O.
   void print(raw_ostream &O) const;
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-gather-scatter-tailpred.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-gather-scatter-tailpred.ll
--- a/llvm/test/Transforms/LoopVectorize/ARM/mve-gather-scatter-tailpred.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-gather-scatter-tailpred.ll
@@ -341,7 +341,7 @@
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[TMP0]], i32 [[N]])
-; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw nsw i32 [[TMP0]], [[STRIDE]]
+; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw nsw i32 [[TMP0]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, ptr [[DATA:%.*]], i32 [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[TMP3]], i32 0
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll b/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
--- a/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
@@ -233,7 +233,7 @@
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP6:%.*]] = mul nuw nsw i64 [[TMP5]], [[STRIDE]]
+; CHECK-NEXT:    [[TMP6:%.*]] = mul nuw nsw i64 [[TMP5]], 1
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
@@ -419,7 +419,7 @@
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP10:%.*]] = mul nuw nsw i64 [[TMP9]], [[STRIDE]]
+; CHECK-NEXT:    [[TMP10:%.*]] = mul nuw nsw i64 [[TMP9]], 1
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[P]], i64 [[TMP10]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[TMP11]], i32 0
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP12]], align 4
diff --git a/llvm/test/Transforms/LoopVectorize/runtime-check-needed-but-empty.ll b/llvm/test/Transforms/LoopVectorize/runtime-check-needed-but-empty.ll
--- a/llvm/test/Transforms/LoopVectorize/runtime-check-needed-but-empty.ll
+++ b/llvm/test/Transforms/LoopVectorize/runtime-check-needed-but-empty.ll
@@ -17,12 +17,12 @@
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 1
 ; CHECK-NEXT:    [[TMP4:%.*]] = trunc i64 [[TMP3]] to i32
-; CHECK-NEXT:    [[TMP5:%.*]] = mul i32 [[TMP4]], [[X]]
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i32 [[TMP4]], 1
 ; CHECK-NEXT:    [[TMP6:%.*]] = zext i32 [[TMP5]] to i64
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds float, ptr [[A:%.*]], i64 [[TMP6]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds float, ptr [[TMP7]], i32 0
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP8]], align 4
-; CHECK-NEXT:    [[TMP9:%.*]] = mul i32 [[TMP1]], [[X]]
+; CHECK-NEXT:    [[TMP9:%.*]] = mul i32 [[TMP1]], 1
 ; CHECK-NEXT:    [[TMP10:%.*]] = zext i32 [[TMP9]] to i64
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP10]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds float, ptr [[TMP11]], i32 0