[X86][Costmodel] Now that getReplicationShuffleCost() is good, update getInterleavedMemoryOpCostAVX512()

... to actually ask about i1-elt-wide mask, since that is what will probably be used on AVX512.
This unblocks D111460.

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D114316

Author: LebedevRI

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

@@ -5285,7 +5285,6 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX512(
   unsigned VF = VecTy->getNumElements() / Factor;
   MVT VT = MVT::getVectorVT(MVT::getVT(VecTy->getScalarType()), VF);
 
-  // FIXME: this is the most conservative estimate for the mask cost.
   InstructionCost MaskCost;
   if (UseMaskForCond || UseMaskForGaps) {
     APInt DemandedLoadStoreElts = APInt::getZero(VecTy->getNumElements());
@@ -5295,10 +5294,10 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX512(
         DemandedLoadStoreElts.setBit(Index + Elm * Factor);
     }
 
-    Type *I8Type = Type::getInt8Ty(VecTy->getContext());
+    Type *I1Type = Type::getInt1Ty(VecTy->getContext());
 
     MaskCost = getReplicationShuffleCost(
-        I8Type, Factor, VF,
+        I1Type, Factor, VF,
         UseMaskForGaps ? DemandedLoadStoreElts
                        : APInt::getAllOnes(VecTy->getNumElements()),
         CostKind);
@@ -5309,7 +5308,7 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX512(
     // memory access, we need to account for the cost of And-ing the two masks
     // inside the loop.
     if (UseMaskForGaps) {
-      auto *MaskVT = FixedVectorType::get(I8Type, VecTy->getNumElements());
+      auto *MaskVT = FixedVectorType::get(I1Type, VecTy->getNumElements());
       MaskCost += getArithmeticInstrCost(BinaryOperator::And, MaskVT, CostKind);
     }
   }

llvm/test/Analysis/CostModel/X86/interleaved-store-accesses-with-gaps.ll

@@ -43,13 +43,13 @@ target triple = "x86_64-unknown-linux-gnu"
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 13 for VF 2 For instruction:   store i16 %2, i16* %arrayidx7, align 2
 ;
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction:   store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 13 for VF 4 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction:   store i16 %2, i16* %arrayidx7, align 2
 ;
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction:   store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 16 for VF 8 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 8 For instruction:   store i16 %2, i16* %arrayidx7, align 2
 ;
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction:   store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 31 for VF 16 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 27 for VF 16 For instruction:   store i16 %2, i16* %arrayidx7, align 2
 
 define void @test1(i16* noalias nocapture %points, i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y) {
 entry:
@@ -110,13 +110,13 @@ for.end:
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 13 for VF 2 For instruction:   store i16 %2, i16* %arrayidx7, align 2
 ;
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction:   store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 13 for VF 4 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction:   store i16 %2, i16* %arrayidx7, align 2
 ;
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction:   store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 16 for VF 8 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 8 For instruction:   store i16 %2, i16* %arrayidx7, align 2
 ;
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction:   store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 31 for VF 16 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 27 for VF 16 For instruction:   store i16 %2, i16* %arrayidx7, align 2
 
 define void @test2(i16* noalias nocapture %points, i32 %numPoints, i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y) {
 entry: