auto *SingleMemOpTy = FixedVectorType::get(VecTy->getElementType(),
LegalVT.getVectorNumElements());
InstructionCost MemOpCost;
- if (UseMaskForCond || UseMaskForGaps)
+ bool UseMaskedMemOp = UseMaskForCond || UseMaskForGaps;
+ if (UseMaskedMemOp)
MemOpCost = getMaskedMemoryOpCost(Opcode, SingleMemOpTy, Alignment,
AddressSpace, CostKind);
else
MVT VT = MVT::getVectorVT(MVT::getVT(VecTy->getScalarType()), VF);
InstructionCost MaskCost;
- if (UseMaskForCond || UseMaskForGaps) {
+ if (UseMaskedMemOp) {
APInt DemandedLoadStoreElts = APInt::getZero(VecTy->getNumElements());
for (unsigned Index : Indices) {
assert(Index < Factor && "Invalid index for interleaved memory op");
NumOfLoadsInInterleaveGrp;
// About a half of the loads may be folded in shuffles when we have only
- // one result. If we have more than one result, we do not fold loads at all.
+ // one result. If we have more than one result, or the loads are masked,
+ // we do not fold loads at all.
unsigned NumOfUnfoldedLoads =
- NumOfResults > 1 ? NumOfMemOps : NumOfMemOps / 2;
+ UseMaskedMemOp || NumOfResults > 1 ? NumOfMemOps : NumOfMemOps / 2;
// Get a number of shuffle operations per result.
unsigned NumOfShufflesPerResult =
; ENABLED_MASKED_STRIDED: LV: Checking a loop in "test"
;
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 13 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 7 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 9 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 9 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
define void @test(i16* noalias nocapture %points, i16* noalias nocapture readonly %x, i16* noalias nocapture readnone %y) {
entry: