[X86] `X86TTIImpl::getInterleavedMemoryOpCostAVX512()`: mask is i8 not i1

Even though AVX512's masked mem ops (unlike AVX1/2) have a mask
that is a `VF x i1`, replication of said masks happens after
promotion of it to `VF x i8`, so we should use `i8`, not `i1`,
when calculating the cost of mask replication.

diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index b16df78..e13bdfd 100644 (file)
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -5074,9 +5074,9 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX512(
         DemandedLoadStoreElts.setBit(Index + Elm * Factor);
     }
 
-    Type *I1Type = Type::getInt1Ty(VecTy->getContext());
-    auto *MaskVT = FixedVectorType::get(I1Type, VecTy->getNumElements());
-    auto *MaskSubVT = FixedVectorType::get(I1Type, VF);
+    Type *I8Type = Type::getInt8Ty(VecTy->getContext());
+    auto *MaskVT = FixedVectorType::get(I8Type, VecTy->getNumElements());
+    auto *MaskSubVT = FixedVectorType::get(I8Type, VF);
 
     // The Mask shuffling cost is extract all the elements of the Mask
     // and insert each of them Factor times into the wide vector:

diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-accesses-with-gaps.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-accesses-with-gaps.ll
index 336794e..5b7a7bd 100644 (file)
--- a/llvm/test/Analysis/CostModel/X86/interleaved-store-accesses-with-gaps.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-accesses-with-gaps.ll
@@ -46,10 +46,10 @@ target triple = "x86_64-unknown-linux-gnu"
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 21 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 33 for VF 8 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 36 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 66 for VF 16 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 73 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:
@@ -113,10 +113,10 @@ for.end:
 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 21 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 33 for VF 8 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 36 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 66 for VF 16 For instruction:   store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 73 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: