Skip to content

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets #95690

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jun 25, 2024
Merged

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets #95690

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
00775f8
[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets
RKSimon Jun 15, 2024
c093c6e
[CostModel][X86] Update vXi8 mul costs for pmaddubsw codegen
RKSimon Jun 16, 2024
4d90c89
Strip extra newline
RKSimon Jun 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 12 additions & 10 deletions llvm/lib/Target/X86/X86ISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28503,17 +28503,19 @@ static SDValue LowerMUL(SDValue Op, const X86Subtarget &Subtarget,

MVT ExVT = MVT::getVectorVT(MVT::i16, NumElts / 2);

// For vXi8 mul-by-constant, try PMADDUBSW to avoid the need for extension.
// For vXi8 mul, try PMADDUBSW to avoid the need for extension.
// Don't do this if we only need to unpack one half.
if (Subtarget.hasSSSE3() &&
ISD::isBuildVectorOfConstantSDNodes(B.getNode())) {
bool IsLoLaneAllZeroOrUndef = true;
bool IsHiLaneAllZeroOrUndef = true;
for (auto [Idx, Val] : enumerate(B->ops())) {
if ((Idx % NumEltsPerLane) >= (NumEltsPerLane / 2))
IsHiLaneAllZeroOrUndef &= isNullConstantOrUndef(Val);
else
IsLoLaneAllZeroOrUndef &= isNullConstantOrUndef(Val);
if (Subtarget.hasSSSE3()) {
bool BIsBuildVector = isa<BuildVectorSDNode>(B);
bool IsLoLaneAllZeroOrUndef = BIsBuildVector;
bool IsHiLaneAllZeroOrUndef = BIsBuildVector;
if (BIsBuildVector) {
for (auto [Idx, Val] : enumerate(B->ops())) {
if ((Idx % NumEltsPerLane) >= (NumEltsPerLane / 2))
IsHiLaneAllZeroOrUndef &= isNullConstantOrUndef(Val);
else
IsLoLaneAllZeroOrUndef &= isNullConstantOrUndef(Val);
}
}
if (!(IsLoLaneAllZeroOrUndef || IsHiLaneAllZeroOrUndef)) {
SDValue Mask = DAG.getBitcast(VT, DAG.getConstant(0x00FF, dl, ExVT));
Expand Down
20 changes: 14 additions & 6 deletions llvm/lib/Target/X86/X86TargetTransformInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -852,8 +852,8 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
{ ISD::SUB, MVT::v32i16, { 1, 1, 1, 1 } }, // psubw

{ ISD::MUL, MVT::v16i8, { 4, 12, 4, 5 } }, // extend/pmullw/trunc
{ ISD::MUL, MVT::v32i8, { 6, 11,10,11 } }, // extend/pmullw/trunc
{ ISD::MUL, MVT::v64i8, { 6, 12,10,11 } }, // unpack/pmullw
{ ISD::MUL, MVT::v32i8, { 3, 10, 7,10 } }, // pmaddubsw
{ ISD::MUL, MVT::v64i8, { 3, 11, 7,10 } }, // pmaddubsw
{ ISD::MUL, MVT::v32i16, { 1, 5, 1, 1 } }, // pmullw

{ ISD::SUB, MVT::v32i8, { 1, 1, 1, 1 } }, // psubb
Expand Down Expand Up @@ -1119,7 +1119,7 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
{ ISD::ADD, MVT::v4i64, { 1, 1, 1, 2 } }, // paddq

{ ISD::MUL, MVT::v16i8, { 5, 18, 6,12 } }, // extend/pmullw/pack
{ ISD::MUL, MVT::v32i8, { 6, 11,10,20 } }, // unpack/pmullw
{ ISD::MUL, MVT::v32i8, { 4, 8, 8,16 } }, // pmaddubsw
{ ISD::MUL, MVT::v16i16, { 2, 5, 1, 2 } }, // pmullw
{ ISD::MUL, MVT::v8i32, { 4, 10, 1, 2 } }, // pmulld
{ ISD::MUL, MVT::v4i32, { 2, 10, 1, 2 } }, // pmulld
Expand Down Expand Up @@ -1170,8 +1170,8 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
// We don't have to scalarize unsupported ops. We can issue two half-sized
// operations and we only need to extract the upper YMM half.
// Two ops + 1 extract + 1 insert = 4.
{ ISD::MUL, MVT::v32i8, { 12, 12, 22, 23 } }, // unpack/pmullw + split
{ ISD::MUL, MVT::v16i8, { 5, 6, 10, 12 } }, // unpack/pmullw
{ ISD::MUL, MVT::v32i8, { 10, 11, 18, 19 } }, // pmaddubsw + split
{ ISD::MUL, MVT::v16i8, { 5, 6, 8, 12 } }, // 2*pmaddubsw/3*and/psllw/or
{ ISD::MUL, MVT::v16i16, { 4, 8, 5, 6 } }, // pmullw + split
{ ISD::MUL, MVT::v8i32, { 5, 8, 5, 10 } }, // pmulld + split
{ ISD::MUL, MVT::v4i32, { 2, 5, 1, 3 } }, // pmulld
Expand Down Expand Up @@ -1311,7 +1311,6 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
{ ISD::SRA, MVT::v4i32, { 16, 17,15,19 } }, // Shift each lane + blend.
{ ISD::SRA, MVT::v2i64, { 8, 17, 5, 7 } }, // splat+shuffle sequence.

{ ISD::MUL, MVT::v16i8, { 6, 18,10,12 } }, // 2*unpack/2*pmullw/2*and/pack
{ ISD::MUL, MVT::v4i32, { 2, 11, 1, 1 } } // pmulld (Nehalem from agner.org)
};

Expand All @@ -1320,6 +1319,15 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
if (auto KindCost = Entry->Cost[CostKind])
return LT.first * *KindCost;

static const CostKindTblEntry SSSE3CostTable[] = {
{ ISD::MUL, MVT::v16i8, { 5, 18,10,12 } }, // 2*pmaddubsw/3*and/psllw/or
};

if (ST->hasSSSE3())
if (const auto *Entry = CostTableLookup(SSSE3CostTable, ISD, LT.second))
if (auto KindCost = Entry->Cost[CostKind])
return LT.first * *KindCost;

static const CostKindTblEntry SSE2CostTable[] = {
// We don't correctly identify costs of casts because they are marked as
// custom.
Expand Down
24 changes: 12 additions & 12 deletions llvm/test/Analysis/CostModel/X86/arith-int-codesize.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -791,9 +791,9 @@ define i32 @mul(i32 %arg) {
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32I8 = mul <32 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64I8 = mul <64 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16I8 = mul <16 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32I8 = mul <32 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = mul <64 x i8> undef, undef
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; SSE42-LABEL: 'mul'
Expand Down Expand Up @@ -835,9 +835,9 @@ define i32 @mul(i32 %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX2-LABEL: 'mul'
Expand All @@ -858,8 +858,8 @@ define i32 @mul(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'mul'
Expand All @@ -880,7 +880,7 @@ define i32 @mul(i32 %arg) {
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
Expand All @@ -902,8 +902,8 @@ define i32 @mul(i32 %arg) {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'mul'
Expand All @@ -924,7 +924,7 @@ define i32 @mul(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
Expand Down
16 changes: 8 additions & 8 deletions llvm/test/Analysis/CostModel/X86/arith-int-latency.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -680,8 +680,8 @@ define i32 @mul(i32 %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX2-LABEL: 'mul'
Expand All @@ -702,8 +702,8 @@ define i32 @mul(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'mul'
Expand All @@ -724,7 +724,7 @@ define i32 @mul(i32 %arg) {
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
Expand All @@ -746,8 +746,8 @@ define i32 @mul(i32 %arg) {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'mul'
Expand All @@ -768,7 +768,7 @@ define i32 @mul(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
Expand Down
16 changes: 8 additions & 8 deletions llvm/test/Analysis/CostModel/X86/arith-int-sizelatency.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -680,8 +680,8 @@ define i32 @mul(i32 %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX2-LABEL: 'mul'
Expand All @@ -702,8 +702,8 @@ define i32 @mul(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'mul'
Expand All @@ -724,7 +724,7 @@ define i32 @mul(i32 %arg) {
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
Expand All @@ -746,8 +746,8 @@ define i32 @mul(i32 %arg) {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'mul'
Expand All @@ -768,7 +768,7 @@ define i32 @mul(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
Expand Down
Loading
Loading