IsSingleScalar

Author: Mel-Chen

llvm/lib/Transforms/Vectorize/VPlanUtils.cpp

@@ -171,6 +171,10 @@ bool vputils::isSingleScalar(const VPValue *VPV) {
     return PreservesUniformity(WidenR->getOpcode()) &&
            all_of(WidenR->operands(), isSingleScalar);
   }
+  if (auto *CastR = dyn_cast<VPWidenCastRecipe>(VPV)) {
+    return PreservesUniformity(CastR->getOpcode()) &&
+           all_of(CastR->operands(), isSingleScalar);
+  }
   if (auto *VPI = dyn_cast<VPInstruction>(VPV))
     return VPI->isSingleScalar() || VPI->isVectorToScalar() ||
            (PreservesUniformity(VPI->getOpcode()) &&

llvm/test/Transforms/LoopVectorize/single-scalar-cast-minbw.ll

@@ -18,8 +18,9 @@ define void @minbw_cast(ptr %dst, i64 %n, i1 %bool1, i1 %bool2) {
 ; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP0:%.*]] = trunc <4 x i32> [[BROADCAST_SPLAT2]] to <4 x i8>
 ; CHECK-NEXT:    [[TMP1:%.*]] = zext <4 x i1> [[BROADCAST_SPLAT]] to <4 x i8>
-; CHECK-NEXT:    [[TMP2:%.*]] = xor <4 x i8> [[TMP0]], [[TMP1]]
-; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i8> [[TMP2]], i32 3
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i8> [[TMP0]], i32 0
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x i8> [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = xor i8 [[TMP2]], [[TMP5]]
 ; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
 ; CHECK:       [[VECTOR_BODY]]:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]