[VectorCombine] foldShuffleOfCastops - ensure we add all new instructions onto the worklist

When creating cast(shuffle(x,y)) we were only adding the cast() to the worklist, not the new shuffle, preventing recursive combines.

foldShuffleOfBinops is also failing to do this, but I still need to add test coverage for this.

Author: RKSimon

llvm/lib/Transforms/Vectorize/VectorCombine.cpp

@@ -1440,6 +1440,8 @@ bool VectorCombine::foldShuffleOfBinops(Instruction &I) {
     NewInst->copyIRFlags(B0);
     NewInst->andIRFlags(B1);
   }
+
+  // TODO: Add Shuf0/Shuf1 to WorkList?
   replaceValue(I, *NewBO);
   return true;
 }
@@ -1533,6 +1535,7 @@ bool VectorCombine::foldShuffleOfCastops(Instruction &I) {
     NewInst->andIRFlags(C1);
   }
 
+  Worklist.pushValue(Shuf);
   replaceValue(I, *Cast);
   return true;
 }

llvm/test/Transforms/VectorCombine/X86/pr67803.ll

@@ -8,9 +8,8 @@ define <4 x i64> @PR67803(<8 x i32> %x, <8 x i32> %y, <8 x float> %a, <8 x float
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt <8 x i32> [[X:%.*]], [[Y:%.*]]
 ; CHECK-NEXT:    [[CMP_LO:%.*]] = shufflevector <8 x i1> [[CMP]], <8 x i1> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:    [[CMP_HI:%.*]] = shufflevector <8 x i1> [[CMP]], <8 x i1> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[SEXT_LO:%.*]] = sext <4 x i1> [[CMP_LO]] to <4 x i32>
-; CHECK-NEXT:    [[SEXT_HI:%.*]] = sext <4 x i1> [[CMP_HI]] to <4 x i32>
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[SEXT_LO]], <4 x i32> [[SEXT_HI]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <4 x i1> [[CMP_LO]], <4 x i1> [[CMP_HI]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[TMP1:%.*]] = sext <8 x i1> [[TMP0]] to <8 x i32>
 ; CHECK-NEXT:    [[CONCAT:%.*]] = bitcast <8 x i32> [[TMP1]] to <4 x i64>
 ; CHECK-NEXT:    [[MASK:%.*]] = bitcast <4 x i64> [[CONCAT]] to <8 x float>
 ; CHECK-NEXT:    [[SEL:%.*]] = tail call noundef <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float> [[A:%.*]], <8 x float> [[B:%.*]], <8 x float> [[MASK]])