diff --git a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
--- a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
+++ b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
@@ -134,13 +134,16 @@
     return false;
 
   // Check safety of replacing the scalar load with a larger vector load.
+  // We use minimal alignment (maximum flexibility) because we only care about
+  // the dereferenceable region. When calculating cost and creating a new op,
+  // we may use a larger value based on alignment attributes.
   unsigned MinVecNumElts = MinVectorSize / ScalarSize;
   auto *MinVecTy = VectorType::get(ScalarTy, MinVecNumElts, false);
-  Align Alignment = Load->getAlign();
-  if (!isSafeToLoadUnconditionally(SrcPtr, MinVecTy, Alignment, DL, Load, &DT))
+  if (!isSafeToLoadUnconditionally(SrcPtr, MinVecTy, Align(1), DL, Load, &DT))
     return false;
 
   // Original pattern: insertelt undef, load [free casts of] PtrOp, 0
+  Align Alignment = Load->getAlign();
   Type *LoadTy = Load->getType();
   int OldCost = TTI.getMemoryOpCost(Instruction::Load, LoadTy, Alignment, AS);
   APInt DemandedElts = APInt::getOneBitSet(MinVecNumElts, 0);
diff --git a/llvm/test/Transforms/VectorCombine/X86/load.ll b/llvm/test/Transforms/VectorCombine/X86/load.ll
--- a/llvm/test/Transforms/VectorCombine/X86/load.ll
+++ b/llvm/test/Transforms/VectorCombine/X86/load.ll
@@ -403,12 +403,14 @@
   ret <4 x float> %r
 }
 
-; Negative test? - pointer is not as aligned as load.
+; Pointer is not as aligned as load, but that's ok.
+; The new load uses the larger alignment value.
 
 define <4 x float> @load_f32_insert_v4f32_align(float* align 1 dereferenceable(16) %p) {
 ; CHECK-LABEL: @load_f32_insert_v4f32_align(
-; CHECK-NEXT:    [[S:%.*]] = load float, float* [[P:%.*]], align 4
-; CHECK-NEXT:    [[R:%.*]] = insertelement <4 x float> undef, float [[S]], i32 0
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast float* [[P:%.*]] to <4 x float>*
+; CHECK-NEXT:    [[TMP2:%.*]] = load <4 x float>, <4 x float>* [[TMP1]], align 4
+; CHECK-NEXT:    [[R:%.*]] = shufflevector <4 x float> [[TMP2]], <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
 ; CHECK-NEXT:    ret <4 x float> [[R]]
 ;
   %s = load float, float* %p, align 4