[InstCombine] Bail out of load-store forwarding for scalable vector types

[david-arm]

Summary

This patch fixes an invalid TypeSize->uint64_t implicit conversion in
FoldReinterpretLoadFromConst. If the size of the constant is scalable
we bail out of the optimisation for now.

Tests added here:

Transforms/InstCombine/load-store-forward.ll

[sdesmalen]

llvm/lib/Analysis/ConstantFolding.cpp

591–592

nit: move this closer to its first use, i.e. line 599, thus below the if (Offset <= -1 * static_cast<....) condition that returns UndefValue.

llvm/test/Transforms/InstCombine/load-store-forward.ll

276

vscale_range isn't specifically required for these tests, you can remove it.

llvm/lib/Analysis/ConstantFolding.cpp

if (Constant *Res = FoldReinterpretLoadFromConst(C, MapTy, Offset, DL)) {
       return Res;
     }
     return nullptr;
   }
 
   unsigned BytesLoaded = (IntType->getBitWidth() + 7) / 8;
   if (BytesLoaded > 32 || BytesLoaded == 0)
     return nullptr;
 
-  int64_t InitializerSize = DL.getTypeAllocSize(C->getType()).getFixedSize();
-
   // 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);
 
+  // TODO: We should be able to support scalable types.
+  TypeSize InitializerSize = DL.getTypeAllocSize(C->getType());
+  if (InitializerSize.isScalable())
+    return nullptr;
+
   // If we're not accessing anything in this constant, the result is undefined.
-  if (Offset >= InitializerSize)
+  if (Offset >= InitializerSize.getFixedValue())
     return UndefValue::get(IntType);
 
   unsigned char RawBytes[32] = {0};
   unsigned char *CurPtr = RawBytes;
   unsigned BytesLeft = BytesLoaded;
 
   // If we're loading off the beginning of the global, some bytes may be valid.
   if (Offset < 0) {

llvm/test/Transforms/InstCombine/load-store-forward.ll

;
   %p2 = bitcast i32* %p to <2 x i32>*
   store <2 x i32> <i32 1, i32 2>, <2 x i32>* %p2
   %p3 = bitcast i32* %p to i8*
   %p4 = getelementptr i8, i8* %p3, i64 2
   %p5 = bitcast i8* %p4 to i32*
   %load = load i32, i32* %p5, align 2
   ret i32 %load
 }
+
+define i32 @load_i32_store_nxv4i32(i32* %a) {
+; 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:    [[TMP1:%.*]] = load i32, i32* [[A]], align 4
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
+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) {
+; 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:    [[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 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) {
+; 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:    [[A2:%.*]] = bitcast i32* [[A]] to i64*
+; CHECK-NEXT:    [[LOAD:%.*]] = load i64, i64* [[A2]], align 8
+; CHECK-NEXT:    ret i64 [[LOAD]]
+;
+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) {
+; CHECK-LABEL: @load_i8_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:    [[A2:%.*]] = bitcast i32* [[A]] to i8*
+; CHECK-NEXT:    [[LOAD:%.*]] = load i8, i8* [[A2]], align 1
+; CHECK-NEXT:    ret i8 [[LOAD]]
+;
+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) {
+; 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:    [[TMP1:%.*]] = load float, float* [[A]], align 4
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+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) {
+; 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:    [[A2:%.*]] = bitcast float* [[A]] to i32*
+; CHECK-NEXT:    [[LOAD:%.*]] = load i32, i32* [[A2]], align 4
+; CHECK-NEXT:    ret i32 [[LOAD]]
+;
+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) {
+; 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:    [[TMP1:%.*]] = bitcast i32* [[A]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 16
+; CHECK-NEXT:    ret <4 x i32> [[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 <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) {
+; CHECK-LABEL: @load_v4i16_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 <4 x i16>*
+; CHECK-NEXT:    [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* [[TMP1]], align 16
+; CHECK-NEXT:    ret <4 x i16> [[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 <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) {
+; 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) {
+; 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
+}