[VectorCombine] foldBitcastShuffle - peek through any residual bitcasts before creating a new bitcast on top (#86119)

Encountered while working on #67803, wading through the chains of bitcasts that SSE intrinsics introduces - this patch helps prevents cases where the bitcast chains aren't cleared out and we can't perform further combines until after InstCombine/InstSimplify has run.

Author: RKSimon

llvm/lib/Transforms/Vectorize/VectorCombine.cpp

@@ -135,6 +135,14 @@ class VectorCombine {
 };
 } // namespace
 
+/// Return the source operand of a potentially bitcasted value. If there is no
+/// bitcast, return the input value itself.
+static Value *peekThroughBitcasts(Value *V) {
+  while (auto *BitCast = dyn_cast<BitCastInst>(V))
+    V = BitCast->getOperand(0);
+  return V;
+}
+
 static bool canWidenLoad(LoadInst *Load, const TargetTransformInfo &TTI) {
   // Do not widen load if atomic/volatile or under asan/hwasan/memtag/tsan.
   // The widened load may load data from dirty regions or create data races
@@ -751,8 +759,8 @@ bool VectorCombine::foldBitcastShuffle(Instruction &I) {
 
   // bitcast (shuf V0, V1, MaskC) --> shuf (bitcast V0), (bitcast V1), MaskC'
   ++NumShufOfBitcast;
-  Value *CastV0 = Builder.CreateBitCast(V0, NewShuffleTy);
-  Value *CastV1 = Builder.CreateBitCast(V1, NewShuffleTy);
+  Value *CastV0 = Builder.CreateBitCast(peekThroughBitcasts(V0), NewShuffleTy);
+  Value *CastV1 = Builder.CreateBitCast(peekThroughBitcasts(V1), NewShuffleTy);
   Value *Shuf = Builder.CreateShuffleVector(CastV0, CastV1, NewMask);
   replaceValue(I, *Shuf);
   return true;

llvm/test/Transforms/VectorCombine/X86/shuffle-inseltpoison.ll

@@ -133,8 +133,7 @@ define <2 x i64> @PR35454_1(<2 x i64> %v) {
 ; SSE-NEXT:    ret <2 x i64> [[BC3]]
 ;
 ; AVX-LABEL: @PR35454_1(
-; AVX-NEXT:    [[BC:%.*]] = bitcast <2 x i64> [[V:%.*]] to <4 x i32>
-; AVX-NEXT:    [[TMP1:%.*]] = bitcast <4 x i32> [[BC]] to <16 x i8>
+; AVX-NEXT:    [[TMP1:%.*]] = bitcast <2 x i64> [[V:%.*]] to <16 x i8>
 ; AVX-NEXT:    [[BC1:%.*]] = shufflevector <16 x i8> [[TMP1]], <16 x i8> poison, <16 x i32> <i32 12, i32 13, i32 14, i32 15, i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
 ; AVX-NEXT:    [[ADD:%.*]] = shl <16 x i8> [[BC1]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
 ; AVX-NEXT:    [[BC2:%.*]] = bitcast <16 x i8> [[ADD]] to <4 x i32>
@@ -164,8 +163,7 @@ define <2 x i64> @PR35454_2(<2 x i64> %v) {
 ; SSE-NEXT:    ret <2 x i64> [[BC3]]
 ;
 ; AVX-LABEL: @PR35454_2(
-; AVX-NEXT:    [[BC:%.*]] = bitcast <2 x i64> [[V:%.*]] to <4 x i32>
-; AVX-NEXT:    [[TMP1:%.*]] = bitcast <4 x i32> [[BC]] to <8 x i16>
+; AVX-NEXT:    [[TMP1:%.*]] = bitcast <2 x i64> [[V:%.*]] to <8 x i16>
 ; AVX-NEXT:    [[BC1:%.*]] = shufflevector <8 x i16> [[TMP1]], <8 x i16> poison, <8 x i32> <i32 6, i32 7, i32 4, i32 5, i32 2, i32 3, i32 0, i32 1>
 ; AVX-NEXT:    [[ADD:%.*]] = shl <8 x i16> [[BC1]], <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
 ; AVX-NEXT:    [[BC2:%.*]] = bitcast <8 x i16> [[ADD]] to <4 x i32>

llvm/test/Transforms/VectorCombine/X86/shuffle.ll

@@ -133,8 +133,7 @@ define <2 x i64> @PR35454_1(<2 x i64> %v) {
 ; SSE-NEXT:    ret <2 x i64> [[BC3]]
 ;
 ; AVX-LABEL: @PR35454_1(
-; AVX-NEXT:    [[BC:%.*]] = bitcast <2 x i64> [[V:%.*]] to <4 x i32>
-; AVX-NEXT:    [[TMP1:%.*]] = bitcast <4 x i32> [[BC]] to <16 x i8>
+; AVX-NEXT:    [[TMP1:%.*]] = bitcast <2 x i64> [[V:%.*]] to <16 x i8>
 ; AVX-NEXT:    [[BC1:%.*]] = shufflevector <16 x i8> [[TMP1]], <16 x i8> poison, <16 x i32> <i32 12, i32 13, i32 14, i32 15, i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
 ; AVX-NEXT:    [[ADD:%.*]] = shl <16 x i8> [[BC1]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
 ; AVX-NEXT:    [[BC2:%.*]] = bitcast <16 x i8> [[ADD]] to <4 x i32>
@@ -164,8 +163,7 @@ define <2 x i64> @PR35454_2(<2 x i64> %v) {
 ; SSE-NEXT:    ret <2 x i64> [[BC3]]
 ;
 ; AVX-LABEL: @PR35454_2(
-; AVX-NEXT:    [[BC:%.*]] = bitcast <2 x i64> [[V:%.*]] to <4 x i32>
-; AVX-NEXT:    [[TMP1:%.*]] = bitcast <4 x i32> [[BC]] to <8 x i16>
+; AVX-NEXT:    [[TMP1:%.*]] = bitcast <2 x i64> [[V:%.*]] to <8 x i16>
 ; AVX-NEXT:    [[BC1:%.*]] = shufflevector <8 x i16> [[TMP1]], <8 x i16> poison, <8 x i32> <i32 6, i32 7, i32 4, i32 5, i32 2, i32 3, i32 0, i32 1>
 ; AVX-NEXT:    [[ADD:%.*]] = shl <8 x i16> [[BC1]], <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
 ; AVX-NEXT:    [[BC2:%.*]] = bitcast <8 x i16> [[ADD]] to <4 x i32>