Index: llvm/lib/Analysis/ConstantFolding.cpp
===================================================================
--- llvm/lib/Analysis/ConstantFolding.cpp
+++ llvm/lib/Analysis/ConstantFolding.cpp
@@ -420,7 +420,7 @@
 /// the CurPtr buffer. DL is the DataLayout.
 bool ReadDataFromGlobal(Constant *C, uint64_t ByteOffset, unsigned char *CurPtr,
                         unsigned BytesLeft, const DataLayout &DL) {
-  assert(ByteOffset <= DL.getTypeAllocSize(C->getType()) &&
+  assert(ByteOffset <= DL.getTypeAllocSize(C->getType()).getKnownMinValue() &&
          "Out of range access");
 
   // If this element is zero or undefined, we can just return since *CurPtr is
@@ -499,7 +499,9 @@
     // not reached.
   }
 
-  if (isa<ConstantArray>(C) || isa<ConstantVector>(C) ||
+  Constant *SplatVal =
+      isa<VectorType>(C->getType()) ? C->getSplatValue(false) : nullptr;
+  if (SplatVal || isa<ConstantArray>(C) || isa<ConstantVector>(C) ||
       isa<ConstantDataSequential>(C)) {
     uint64_t NumElts;
     Type *EltTy;
@@ -507,16 +509,17 @@
       NumElts = AT->getNumElements();
       EltTy = AT->getElementType();
     } else {
-      NumElts = cast<FixedVectorType>(C->getType())->getNumElements();
-      EltTy = cast<FixedVectorType>(C->getType())->getElementType();
+      NumElts =
+          cast<VectorType>(C->getType())->getElementCount().getKnownMinValue();
+      EltTy = cast<VectorType>(C->getType())->getElementType();
     }
-    uint64_t EltSize = DL.getTypeAllocSize(EltTy);
+    uint64_t EltSize = DL.getTypeAllocSize(EltTy).getFixedSize();
     uint64_t Index = ByteOffset / EltSize;
     uint64_t Offset = ByteOffset - Index * EltSize;
 
     for (; Index != NumElts; ++Index) {
-      if (!ReadDataFromGlobal(C->getAggregateElement(Index), Offset, CurPtr,
-                              BytesLeft, DL))
+      Constant *El = SplatVal ? SplatVal : C->getAggregateElement(Index);
+      if (!ReadDataFromGlobal(El, Offset, CurPtr, BytesLeft, DL))
         return false;
 
       uint64_t BytesWritten = EltSize - Offset;
@@ -589,15 +592,15 @@
   if (BytesLoaded > 32 || BytesLoaded == 0)
     return nullptr;
 
-  int64_t InitializerSize = DL.getTypeAllocSize(C->getType()).getFixedSize();
+  TypeSize InitializerSize = DL.getTypeAllocSize(C->getType());
 
   // If we're not accessing anything in this constant, the result is undefined.
   if (Offset <= -1 * static_cast<int64_t>(BytesLoaded))
     return UndefValue::get(IntType);
 
   // If we're not accessing anything in this constant, the result is undefined.
-  if (Offset >= InitializerSize)
-    return UndefValue::get(IntType);
+  if (Offset >= static_cast<int64_t>(InitializerSize.getKnownMinValue()))
+    return InitializerSize.isScalable() ? nullptr : UndefValue::get(IntType);
 
   unsigned char RawBytes[32] = {0};
   unsigned char *CurPtr = RawBytes;
Index: llvm/test/Transforms/InstCombine/load-store-forward.ll
===================================================================
--- llvm/test/Transforms/InstCombine/load-store-forward.ll
+++ llvm/test/Transforms/InstCombine/load-store-forward.ll
@@ -120,3 +120,170 @@
   %load = load i32, i32* %p5, align 2
   ret i32 %load
 }
+
+define i32 @load_i32_store_nxv4i32(i32* %a) vscale_range(1,16) {
+; CHECK-LABEL: @load_i32_store_nxv4i32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <vscale x 4 x i32>*
+; CHECK-NEXT:    store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* [[TMP0]], align 16
+; CHECK-NEXT:    ret i32 1
+;
+entry:
+  %0 = bitcast i32* %a to <vscale x 4 x i32>*
+  store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* %0, align 16
+  %1 = load i32, i32* %a, align 4
+  ret i32 %1
+}
+
+define i64 @load_i64_store_nxv8i8(i8* %a) vscale_range(1,16) {
+; CHECK-LABEL: @load_i64_store_nxv8i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i8* [[A:%.*]] to <vscale x 8 x i8>*
+; CHECK-NEXT:    store <vscale x 8 x i8> shufflevector (<vscale x 8 x i8> insertelement (<vscale x 8 x i8> poison, i8 1, i32 0), <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer), <vscale x 8 x i8>* [[TMP0]], align 16
+; CHECK-NEXT:    ret i64 72340172838076673
+;
+entry:
+  %0 = bitcast i8* %a to <vscale x 8 x i8>*
+  store <vscale x 8 x i8> shufflevector (<vscale x 8 x i8> insertelement (<vscale x 8 x i8> poison, i8 1, i32 0), <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer), <vscale x 8 x i8>* %0, align 16
+  %a2 = bitcast i8* %a to i64*
+  %load = load i64, i64* %a2, align 8
+  ret i64 %load
+}
+
+define i64 @load_i64_store_nxv4i32(i32* %a) vscale_range(1,16) {
+; CHECK-LABEL: @load_i64_store_nxv4i32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <vscale x 4 x i32>*
+; CHECK-NEXT:    store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* [[TMP0]], align 16
+; CHECK-NEXT:    ret i64 4294967297
+;
+entry:
+  %0 = bitcast i32* %a to <vscale x 4 x i32>*
+  store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* %0, align 16
+  %a2 = bitcast i32* %a to i64*
+  %load = load i64, i64* %a2, align 8
+  ret i64 %load
+}
+
+define i8 @load_i8_store_nxv4i32(i32* %a) vscale_range(1,16) {
+; LITTLE-LABEL: @load_i8_store_nxv4i32(
+; LITTLE-NEXT:  entry:
+; LITTLE-NEXT:    [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <vscale x 4 x i32>*
+; LITTLE-NEXT:    store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* [[TMP0]], align 16
+; LITTLE-NEXT:    ret i8 1
+;
+; BIG-LABEL: @load_i8_store_nxv4i32(
+; BIG-NEXT:  entry:
+; BIG-NEXT:    [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <vscale x 4 x i32>*
+; BIG-NEXT:    store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* [[TMP0]], align 16
+; BIG-NEXT:    ret i8 0
+;
+entry:
+  %0 = bitcast i32* %a to <vscale x 4 x i32>*
+  store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* %0, align 16
+  %a2 = bitcast i32* %a to i8*
+  %load = load i8, i8* %a2, align 1
+  ret i8 %load
+}
+
+define float @load_f32_store_nxv4f32(float* %a) vscale_range(1,16) {
+; CHECK-LABEL: @load_f32_store_nxv4f32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[A:%.*]] to <vscale x 4 x float>*
+; CHECK-NEXT:    store <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 1.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x float>* [[TMP0]], align 16
+; CHECK-NEXT:    ret float 1.000000e+00
+;
+entry:
+  %0 = bitcast float* %a to <vscale x 4 x float>*
+  store <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 1.0, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x float>* %0, align 16
+  %1 = load float, float* %a, align 4
+  ret float %1
+}
+
+define i32 @load_i32_store_nxv4f32(float* %a) vscale_range(1,16) {
+; CHECK-LABEL: @load_i32_store_nxv4f32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[A:%.*]] to <vscale x 4 x float>*
+; CHECK-NEXT:    store <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 1.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x float>* [[TMP0]], align 16
+; CHECK-NEXT:    ret i32 1065353216
+;
+entry:
+  %0 = bitcast float* %a to <vscale x 4 x float>*
+  store <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 1.0, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x float>* %0, align 16
+  %a2 = bitcast float* %a to i32*
+  %load = load i32, i32* %a2, align 4
+  ret i32 %load
+}
+
+define <4 x i32> @load_v4i32_store_nxv4i32(i32* %a) vscale_range(1,16) {
+; CHECK-LABEL: @load_v4i32_store_nxv4i32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <vscale x 4 x i32>*
+; CHECK-NEXT:    store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* [[TMP0]], align 16
+; CHECK-NEXT:    ret <4 x i32> <i32 1, i32 1, i32 1, i32 1>
+;
+entry:
+  %0 = bitcast i32* %a to <vscale x 4 x i32>*
+  store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* %0, align 16
+  %1 = bitcast i32* %a to <4 x i32>*
+  %2 = load <4 x i32>, <4 x i32>* %1, align 16
+  ret <4 x i32> %2
+}
+
+define <4 x i16> @load_v4i16_store_nxv4i32(i32* %a) vscale_range(1,16) {
+; LITTLE-LABEL: @load_v4i16_store_nxv4i32(
+; LITTLE-NEXT:  entry:
+; LITTLE-NEXT:    [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <vscale x 4 x i32>*
+; LITTLE-NEXT:    store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* [[TMP0]], align 16
+; LITTLE-NEXT:    ret <4 x i16> <i16 1, i16 0, i16 1, i16 0>
+;
+; BIG-LABEL: @load_v4i16_store_nxv4i32(
+; BIG-NEXT:  entry:
+; BIG-NEXT:    [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <vscale x 4 x i32>*
+; BIG-NEXT:    store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* [[TMP0]], align 16
+; BIG-NEXT:    ret <4 x i16> <i16 0, i16 1, i16 0, i16 1>
+;
+entry:
+  %0 = bitcast i32* %a to <vscale x 4 x i32>*
+  store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* %0, align 16
+  %1 = bitcast i32* %a to <4 x i16>*
+  %2 = load <4 x i16>, <4 x i16>* %1, align 16
+  ret <4 x i16> %2
+}
+
+; Loaded data type exceeds the known minimum size of the store.
+define i64 @load_i64_store_nxv4i8(i8* %a) vscale_range(1,16) {
+; CHECK-LABEL: @load_i64_store_nxv4i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i8* [[A:%.*]] to <vscale x 4 x i8>*
+; CHECK-NEXT:    store <vscale x 4 x i8> shufflevector (<vscale x 4 x i8> insertelement (<vscale x 4 x i8> poison, i8 1, i32 0), <vscale x 4 x i8> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i8>* [[TMP0]], align 16
+; CHECK-NEXT:    [[A2:%.*]] = bitcast i8* [[A]] to i64*
+; CHECK-NEXT:    [[LOAD:%.*]] = load i64, i64* [[A2]], align 8
+; CHECK-NEXT:    ret i64 [[LOAD]]
+;
+entry:
+  %0 = bitcast i8* %a to <vscale x 4 x i8>*
+  store <vscale x 4 x i8> shufflevector (<vscale x 4 x i8> insertelement (<vscale x 4 x i8> poison, i8 1, i32 0), <vscale x 4 x i8> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i8>* %0, align 16
+  %a2 = bitcast i8* %a to i64*
+  %load = load i64, i64* %a2, align 8
+  ret i64 %load
+}
+
+; Loaded data size is unknown - we cannot guarantee it won't
+; exceed the store size.
+define <vscale x 4 x i8> @load_nxv4i8_store_nxv4i32(i32* %a) vscale_range(1,16) {
+; CHECK-LABEL: @load_nxv4i8_store_nxv4i32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <vscale x 4 x i32>*
+; CHECK-NEXT:    store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* [[TMP0]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32* [[A]] to <vscale x 4 x i8>*
+; CHECK-NEXT:    [[TMP2:%.*]] = load <vscale x 4 x i8>, <vscale x 4 x i8>* [[TMP1]], align 16
+; CHECK-NEXT:    ret <vscale x 4 x i8> [[TMP2]]
+;
+entry:
+  %0 = bitcast i32* %a to <vscale x 4 x i32>*
+  store <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32>* %0, align 16
+  %1 = bitcast i32* %a to <vscale x 4 x i8>*
+  %2 = load <vscale x 4 x i8>, <vscale x 4 x i8>* %1, align 16
+  ret <vscale x 4 x i8> %2
+}