[llvm] 7a89847 - [CostModel][X86] vXi8 MUL is always promoted to vXi16
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Sat May 22 03:57:14 PDT 2021
Author: Simon Pilgrim
Date: 2021-05-22T11:56:49+01:00
New Revision: 7a898477bbd4e06113f9aa67c9c53904889c7cbf
URL: https://github.com/llvm/llvm-project/commit/7a898477bbd4e06113f9aa67c9c53904889c7cbf
DIFF: https://github.com/llvm/llvm-project/commit/7a898477bbd4e06113f9aa67c9c53904889c7cbf.diff
LOG: [CostModel][X86] vXi8 MUL is always promoted to vXi16
Added:
Modified:
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/X86/arith.ll
llvm/test/Analysis/CostModel/X86/rem.ll
llvm/test/Analysis/CostModel/X86/slm-arith-costs.ll
llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll
llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll
llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll
llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index a0a18143de97d..060e050076dec 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -184,6 +184,22 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
return BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info,
Op2Info, Opd1PropInfo,
Opd2PropInfo, Args, CxtI);
+
+ // vXi8 multiplications are always promoted to vXi16.
+ if (Opcode == Instruction::Mul && Ty->isVectorTy() &&
+ Ty->getScalarSizeInBits() == 8) {
+ Type *WideVecTy =
+ VectorType::getExtendedElementVectorType(cast<VectorType>(Ty));
+ return getCastInstrCost(Instruction::ZExt, WideVecTy, Ty,
+ TargetTransformInfo::CastContextHint::None,
+ CostKind) +
+ getCastInstrCost(Instruction::Trunc, Ty, WideVecTy,
+ TargetTransformInfo::CastContextHint::None,
+ CostKind) +
+ getArithmeticInstrCost(Opcode, WideVecTy, CostKind, Op1Info, Op2Info,
+ Opd1PropInfo, Opd2PropInfo);
+ }
+
// Legalize the type.
std::pair<InstructionCost, MVT> LT = TLI->getTypeLegalizationCost(DL, Ty);
@@ -205,7 +221,6 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
static const CostTblEntry SLMCostTable[] = {
{ ISD::MUL, MVT::v4i32, 11 }, // pmulld
{ ISD::MUL, MVT::v8i16, 2 }, // pmullw
- { ISD::MUL, MVT::v16i8, 14 }, // extend/pmullw/trunc sequence.
{ ISD::FMUL, MVT::f64, 2 }, // mulsd
{ ISD::FMUL, MVT::v2f64, 4 }, // mulpd
{ ISD::FMUL, MVT::v4f32, 2 }, // mulps
@@ -570,10 +585,6 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
{ ISD::SHL, MVT::v64i8, 11 }, // vpblendvb sequence.
{ ISD::SRL, MVT::v64i8, 11 }, // vpblendvb sequence.
{ ISD::SRA, MVT::v64i8, 24 }, // vpblendvb sequence.
-
- { ISD::MUL, MVT::v64i8, 11 }, // extend/pmullw/trunc sequence.
- { ISD::MUL, MVT::v32i8, 4 }, // extend/pmullw/trunc sequence.
- { ISD::MUL, MVT::v16i8, 4 }, // extend/pmullw/trunc sequence.
};
// Look for AVX512BW lowering tricks for custom cases.
@@ -598,9 +609,6 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
{ ISD::SRA, MVT::v4i64, 1 },
{ ISD::SRA, MVT::v8i64, 1 },
- { ISD::MUL, MVT::v64i8, 26 }, // extend/pmullw/trunc sequence.
- { ISD::MUL, MVT::v32i8, 13 }, // extend/pmullw/trunc sequence.
- { ISD::MUL, MVT::v16i8, 5 }, // extend/pmullw/trunc sequence.
{ ISD::MUL, MVT::v16i32, 1 }, // pmulld (Skylake from agner.org)
{ ISD::MUL, MVT::v8i32, 1 }, // pmulld (Skylake from agner.org)
{ ISD::MUL, MVT::v4i32, 1 }, // pmulld (Skylake from agner.org)
@@ -773,8 +781,6 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
{ ISD::SUB, MVT::v4i64, 1 }, // psubq
{ ISD::ADD, MVT::v4i64, 1 }, // paddq
- { ISD::MUL, MVT::v32i8, 17 }, // extend/pmullw/trunc sequence.
- { ISD::MUL, MVT::v16i8, 7 }, // extend/pmullw/trunc sequence.
{ ISD::MUL, MVT::v16i16, 1 }, // pmullw
{ ISD::MUL, MVT::v8i32, 2 }, // pmulld (Haswell from agner.org)
{ ISD::MUL, MVT::v4i64, 8 }, // 3*pmuludq/3*shift/2*add
@@ -825,8 +831,6 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
// instead of 8.
{ ISD::MUL, MVT::v4i64, 18 },
- { ISD::MUL, MVT::v32i8, 26 }, // extend/pmullw/trunc sequence.
-
{ ISD::FNEG, MVT::v4f64, 2 }, // BTVER2 from http://www.agner.org/
{ ISD::FNEG, MVT::v8f32, 2 }, // BTVER2 from http://www.agner.org/
@@ -922,7 +926,6 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost(
{ ISD::SRA, MVT::v2i64, 12 }, // srl/xor/sub sequence.
{ ISD::SRA, MVT::v4i64, 2*12+2 }, // srl/xor/sub sequence+split.
- { ISD::MUL, MVT::v16i8, 12 }, // extend/pmullw/trunc sequence.
{ ISD::MUL, MVT::v8i16, 1 }, // pmullw
{ ISD::MUL, MVT::v4i32, 6 }, // 3*pmuludq/4*shuffle
{ ISD::MUL, MVT::v2i64, 8 }, // 3*pmuludq/3*shift/2*add
diff --git a/llvm/test/Analysis/CostModel/X86/arith.ll b/llvm/test/Analysis/CostModel/X86/arith.ll
index d5cbc44ae93ca..3e92c36541e4e 100644
--- a/llvm/test/Analysis/CostModel/X86/arith.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith.ll
@@ -943,12 +943,12 @@ define i32 @mul(i32 %arg) {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = mul <16 x i16> undef, undef
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = mul <32 x i16> undef, undef
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I8 = mul <8 x i8> undef, undef
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32I8 = mul <32 x i8> undef, undef
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64I8 = mul <64 x i8> undef, undef
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = mul <4 x i8> undef, undef
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I8 = mul <16 x i8> undef, undef
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I8 = mul <32 x i8> undef, undef
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V64I8 = mul <64 x i8> undef, undef
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSE42-LABEL: 'mul'
@@ -965,12 +965,12 @@ define i32 @mul(i32 %arg) {
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = mul <16 x i16> undef, undef
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = mul <32 x i16> undef, undef
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I8 = mul <8 x i8> undef, undef
-; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
-; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32I8 = mul <32 x i8> undef, undef
-; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64I8 = mul <64 x i8> undef, undef
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = mul <16 x i8> undef, undef
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = mul <32 x i8> undef, undef
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = mul <64 x i8> undef, undef
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'mul'
@@ -987,9 +987,9 @@ define i32 @mul(i32 %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = mul <16 x i16> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = mul <32 x i16> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; 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 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32I8 = mul <32 x i8> undef, undef
; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V64I8 = mul <64 x i8> undef, undef
@@ -1009,12 +1009,12 @@ define i32 @mul(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = mul <16 x i16> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = mul <32 x i16> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; 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 7 for instruction: %V16I8 = mul <16 x i8> undef, undef
-; AVX2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V32I8 = mul <32 x i8> undef, undef
-; AVX2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V64I8 = mul <64 x i8> undef, undef
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; 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 14 for instruction: %V32I8 = mul <32 x i8> undef, undef
+; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'mul'
@@ -1031,12 +1031,12 @@ define i32 @mul(i32 %arg) {
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = mul <16 x i16> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = mul <32 x i16> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; 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 5 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32I8 = mul <32 x i8> undef, undef
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64I8 = mul <64 x i8> undef, undef
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'mul'
@@ -1053,12 +1053,12 @@ define i32 @mul(i32 %arg) {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = mul <16 x i16> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = mul <32 x i16> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; 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 4 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: %V64I8 = mul <64 x i8> undef, undef
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'mul'
@@ -1075,12 +1075,12 @@ define i32 @mul(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = mul <16 x i16> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = mul <32 x i16> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; 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 5 for instruction: %V16I8 = mul <16 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32I8 = mul <32 x i8> undef, undef
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64I8 = mul <64 x i8> undef, undef
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = mul <64 x i8> undef, undef
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SLM-LABEL: 'mul'
@@ -1097,12 +1097,12 @@ define i32 @mul(i32 %arg) {
; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = mul <16 x i16> undef, undef
; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = mul <32 x i16> undef, undef
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8I8 = mul <8 x i8> undef, undef
-; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = mul <16 x i8> undef, undef
-; SLM-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V32I8 = mul <32 x i8> undef, undef
-; SLM-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V64I8 = mul <64 x i8> undef, undef
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = mul <4 x i8> undef, undef
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; SLM-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16I8 = mul <16 x i8> undef, undef
+; SLM-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I8 = mul <32 x i8> undef, undef
+; SLM-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V64I8 = mul <64 x i8> undef, undef
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; GLM-LABEL: 'mul'
@@ -1119,12 +1119,12 @@ define i32 @mul(i32 %arg) {
; GLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = mul <16 x i16> undef, undef
; GLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = mul <32 x i16> undef, undef
; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I8 = mul <8 x i8> undef, undef
-; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
-; GLM-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32I8 = mul <32 x i8> undef, undef
-; GLM-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64I8 = mul <64 x i8> undef, undef
+; GLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; GLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
+; GLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; GLM-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = mul <16 x i8> undef, undef
+; GLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = mul <32 x i8> undef, undef
+; GLM-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = mul <64 x i8> undef, undef
; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'mul'
@@ -1141,9 +1141,9 @@ define i32 @mul(i32 %arg) {
; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = mul <16 x i16> undef, undef
; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = mul <32 x i16> undef, undef
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = mul i8 undef, undef
-; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V2I8 = mul <2 x i8> undef, undef
-; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = mul <4 x i8> undef, undef
-; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I8 = mul <8 x i8> undef, undef
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = mul <2 x i8> undef, undef
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = mul <4 x i8> undef, undef
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = mul <8 x i8> undef, undef
; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = mul <16 x i8> undef, undef
; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32I8 = mul <32 x i8> undef, undef
; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V64I8 = mul <64 x i8> undef, undef
diff --git a/llvm/test/Analysis/CostModel/X86/rem.ll b/llvm/test/Analysis/CostModel/X86/rem.ll
index 7978d7353c522..8c34117ce1d1d 100644
--- a/llvm/test/Analysis/CostModel/X86/rem.ll
+++ b/llvm/test/Analysis/CostModel/X86/rem.ll
@@ -740,9 +740,9 @@ define i32 @srem_constpow2() {
; SSE2-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; SSE2-NEXT: Cost Model: Found an estimated cost of 396 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; SSE2-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; SSE2-NEXT: Cost Model: Found an estimated cost of 296 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; SSE2-NEXT: Cost Model: Found an estimated cost of 592 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 288 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 576 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSSE3-LABEL: 'srem_constpow2'
@@ -759,9 +759,9 @@ define i32 @srem_constpow2() {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 396 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 296 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 592 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 288 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 576 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSE42-LABEL: 'srem_constpow2'
@@ -778,9 +778,9 @@ define i32 @srem_constpow2() {
; SSE42-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; SSE42-NEXT: Cost Model: Found an estimated cost of 180 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; SSE42-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; SSE42-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; SSE42-NEXT: Cost Model: Found an estimated cost of 296 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 138 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 276 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'srem_constpow2'
@@ -816,9 +816,9 @@ define i32 @srem_constpow2() {
; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; AVX2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; AVX2-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 78 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 156 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 75 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'srem_constpow2'
@@ -837,7 +837,7 @@ define i32 @srem_constpow2() {
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
; AVX512F-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'srem_constpow2'
@@ -856,7 +856,7 @@ define i32 @srem_constpow2() {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SLM-LABEL: 'srem_constpow2'
@@ -873,9 +873,9 @@ define i32 @srem_constpow2() {
; SLM-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; SLM-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; SLM-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; SLM-NEXT: Cost Model: Found an estimated cost of 152 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; SLM-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLM-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLM-NEXT: Cost Model: Found an estimated cost of 142 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLM-NEXT: Cost Model: Found an estimated cost of 284 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; GLM-LABEL: 'srem_constpow2'
@@ -892,9 +892,9 @@ define i32 @srem_constpow2() {
; GLM-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; GLM-NEXT: Cost Model: Found an estimated cost of 180 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; GLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; GLM-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; GLM-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; GLM-NEXT: Cost Model: Found an estimated cost of 296 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; GLM-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; GLM-NEXT: Cost Model: Found an estimated cost of 138 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; GLM-NEXT: Cost Model: Found an estimated cost of 276 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'srem_constpow2'
@@ -1035,9 +1035,9 @@ define i32 @srem_uniformconstpow2() {
; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; SSE2-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSSE3-LABEL: 'srem_uniformconstpow2'
@@ -1054,9 +1054,9 @@ define i32 @srem_uniformconstpow2() {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSE42-LABEL: 'srem_uniformconstpow2'
@@ -1073,9 +1073,9 @@ define i32 @srem_uniformconstpow2() {
; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; SSE42-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'srem_uniformconstpow2'
@@ -1111,9 +1111,9 @@ define i32 @srem_uniformconstpow2() {
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; AVX2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'srem_uniformconstpow2'
@@ -1132,7 +1132,7 @@ define i32 @srem_uniformconstpow2() {
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
; AVX512F-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'srem_uniformconstpow2'
@@ -1151,7 +1151,7 @@ define i32 @srem_uniformconstpow2() {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SLM-LABEL: 'srem_uniformconstpow2'
@@ -1168,9 +1168,9 @@ define i32 @srem_uniformconstpow2() {
; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; SLM-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; SLM-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; SLM-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; SLM-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLM-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLM-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLM-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; GLM-LABEL: 'srem_uniformconstpow2'
@@ -1187,9 +1187,9 @@ define i32 @srem_uniformconstpow2() {
; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; GLM-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; GLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
-; GLM-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; GLM-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; GLM-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; GLM-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; GLM-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; GLM-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; BTVER2-LABEL: 'srem_uniformconstpow2'
diff --git a/llvm/test/Analysis/CostModel/X86/slm-arith-costs.ll b/llvm/test/Analysis/CostModel/X86/slm-arith-costs.ll
index 723cf35aa953c..6516786da741f 100644
--- a/llvm/test/Analysis/CostModel/X86/slm-arith-costs.ll
+++ b/llvm/test/Analysis/CostModel/X86/slm-arith-costs.ll
@@ -47,11 +47,11 @@ entry:
define <2 x i8> @slm-costs_8_v2_mul(<2 x i8> %a, <2 x i8> %b) {
; SLM-LABEL: 'slm-costs_8_v2_mul'
-; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %res = mul nsw <2 x i8> %a, %b
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res = mul nsw <2 x i8> %a, %b
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i8> %res
;
; GLM-LABEL: 'slm-costs_8_v2_mul'
-; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %res = mul nsw <2 x i8> %a, %b
+; GLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %res = mul nsw <2 x i8> %a, %b
; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i8> %res
;
entry:
@@ -61,11 +61,11 @@ entry:
define <4 x i8> @slm-costs_8_v4_mul(<4 x i8> %a, <4 x i8> %b) {
; SLM-LABEL: 'slm-costs_8_v4_mul'
-; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %res = mul nsw <4 x i8> %a, %b
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res = mul nsw <4 x i8> %a, %b
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i8> %res
;
; GLM-LABEL: 'slm-costs_8_v4_mul'
-; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %res = mul nsw <4 x i8> %a, %b
+; GLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %res = mul nsw <4 x i8> %a, %b
; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i8> %res
;
entry:
@@ -177,11 +177,11 @@ entry:
define <8 x i8> @slm-costs_8_v8_mul(<8 x i8> %a, <8 x i8> %b) {
; SLM-LABEL: 'slm-costs_8_v8_mul'
-; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %res = mul nsw <8 x i8> %a, %b
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res = mul nsw <8 x i8> %a, %b
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i8> %res
;
; GLM-LABEL: 'slm-costs_8_v8_mul'
-; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %res = mul nsw <8 x i8> %a, %b
+; GLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %res = mul nsw <8 x i8> %a, %b
; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i8> %res
;
entry:
@@ -191,11 +191,11 @@ entry:
define <16 x i8> @slm-costs_8_v16_mul(<16 x i8> %a, <16 x i8> %b) {
; SLM-LABEL: 'slm-costs_8_v16_mul'
-; SLM-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %res = mul nsw <16 x i8> %a, %b
+; SLM-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %res = mul nsw <16 x i8> %a, %b
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %res
;
; GLM-LABEL: 'slm-costs_8_v16_mul'
-; GLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %res = mul nsw <16 x i8> %a, %b
+; GLM-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = mul nsw <16 x i8> %a, %b
; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %res
;
entry:
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll
index 98fe1dfc1a76d..f147911a6d1fe 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll
@@ -3,13 +3,9 @@
define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
; CHECK-LABEL: @g(
-; CHECK-NEXT: [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
-; CHECK-NEXT: [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
-; CHECK-NEXT: [[INS1:%.*]] = insertelement <2 x i8> poison, i8 [[X0X0]], i32 0
-; CHECK-NEXT: [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
-; CHECK-NEXT: ret <2 x i8> [[INS2]]
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 3>
+; CHECK-NEXT: [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
+; CHECK-NEXT: ret <2 x i8> [[TMP2]]
;
%x0 = extractelement <2 x i8> %x, i32 0
%y1 = extractelement <2 x i8> %y, i32 1
@@ -64,17 +60,9 @@ define <4 x i8> @h_undef(<4 x i8> %x, <4 x i8> %y) {
define i8 @i(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @i(
-; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
-; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
-; CHECK-NEXT: [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
-; CHECK-NEXT: [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
-; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
-; CHECK-NEXT: [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
-; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
-; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[Y1Y1]], [[Y2Y2]]
-; CHECK-NEXT: [[TMP3:%.*]] = add i8 [[TMP1]], [[TMP2]]
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <4 x i32> <i32 0, i32 3, i32 5, i32 6>
+; CHECK-NEXT: [[TMP2:%.*]] = mul <4 x i8> [[TMP1]], [[TMP1]]
+; CHECK-NEXT: [[TMP3:%.*]] = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> [[TMP2]])
; CHECK-NEXT: ret i8 [[TMP3]]
;
%x0 = extractelement <4 x i8> %x, i32 0
@@ -93,18 +81,15 @@ define i8 @i(<4 x i8> %x, <4 x i8> %y) {
define i8 @j(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @j(
-; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
-; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
-; CHECK-NEXT: [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
-; CHECK-NEXT: [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
-; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
-; CHECK-NEXT: [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
-; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
-; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[Y1Y1]], [[Y2Y2]]
-; CHECK-NEXT: [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
-; CHECK-NEXT: ret i8 [[TMP3]]
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 5>
+; CHECK-NEXT: [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i8> [[X]], <4 x i8> [[Y]], <2 x i32> <i32 3, i32 6>
+; CHECK-NEXT: [[TMP4:%.*]] = mul <2 x i8> [[TMP3]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i32 0
+; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i32 1
+; CHECK-NEXT: [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
+; CHECK-NEXT: ret i8 [[TMP8]]
;
%x0 = extractelement <4 x i8> %x, i32 0
%x3 = extractelement <4 x i8> %x, i32 3
@@ -122,18 +107,15 @@ define i8 @j(<4 x i8> %x, <4 x i8> %y) {
define i8 @k(<4 x i8> %x) {
; CHECK-LABEL: @k(
-; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
-; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
-; CHECK-NEXT: [[X1:%.*]] = extractelement <4 x i8> [[X]], i32 1
-; CHECK-NEXT: [[X2:%.*]] = extractelement <4 x i8> [[X]], i32 2
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
-; CHECK-NEXT: [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
-; CHECK-NEXT: [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
-; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
-; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
-; CHECK-NEXT: [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
-; CHECK-NEXT: ret i8 [[TMP3]]
+; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i8> [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> undef, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT: [[TMP3:%.*]] = mul <4 x i8> [[X]], [[X]]
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> undef, <2 x i32> <i32 3, i32 2>
+; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i32 0
+; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i32 1
+; CHECK-NEXT: [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
+; CHECK-NEXT: ret i8 [[TMP8]]
;
%x0 = extractelement <4 x i8> %x, i32 0
%x3 = extractelement <4 x i8> %x, i32 3
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll
index 210ae5d39a50a..1a4d0c3b50bd0 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll
@@ -3,13 +3,9 @@
define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
; CHECK-LABEL: @g(
-; CHECK-NEXT: [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
-; CHECK-NEXT: [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
-; CHECK-NEXT: [[INS1:%.*]] = insertelement <2 x i8> undef, i8 [[X0X0]], i32 0
-; CHECK-NEXT: [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
-; CHECK-NEXT: ret <2 x i8> [[INS2]]
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 3>
+; CHECK-NEXT: [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
+; CHECK-NEXT: ret <2 x i8> [[TMP2]]
;
%x0 = extractelement <2 x i8> %x, i32 0
%y1 = extractelement <2 x i8> %y, i32 1
@@ -64,17 +60,9 @@ define <4 x i8> @h_undef(<4 x i8> %x, <4 x i8> %y) {
define i8 @i(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @i(
-; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
-; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
-; CHECK-NEXT: [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
-; CHECK-NEXT: [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
-; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
-; CHECK-NEXT: [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
-; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
-; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[Y1Y1]], [[Y2Y2]]
-; CHECK-NEXT: [[TMP3:%.*]] = add i8 [[TMP1]], [[TMP2]]
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <4 x i32> <i32 0, i32 3, i32 5, i32 6>
+; CHECK-NEXT: [[TMP2:%.*]] = mul <4 x i8> [[TMP1]], [[TMP1]]
+; CHECK-NEXT: [[TMP3:%.*]] = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> [[TMP2]])
; CHECK-NEXT: ret i8 [[TMP3]]
;
%x0 = extractelement <4 x i8> %x, i32 0
@@ -93,18 +81,15 @@ define i8 @i(<4 x i8> %x, <4 x i8> %y) {
define i8 @j(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @j(
-; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
-; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
-; CHECK-NEXT: [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
-; CHECK-NEXT: [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
-; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
-; CHECK-NEXT: [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
-; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
-; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[Y1Y1]], [[Y2Y2]]
-; CHECK-NEXT: [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
-; CHECK-NEXT: ret i8 [[TMP3]]
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 5>
+; CHECK-NEXT: [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i8> [[X]], <4 x i8> [[Y]], <2 x i32> <i32 3, i32 6>
+; CHECK-NEXT: [[TMP4:%.*]] = mul <2 x i8> [[TMP3]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i32 0
+; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i32 1
+; CHECK-NEXT: [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
+; CHECK-NEXT: ret i8 [[TMP8]]
;
%x0 = extractelement <4 x i8> %x, i32 0
%x3 = extractelement <4 x i8> %x, i32 3
@@ -122,18 +107,15 @@ define i8 @j(<4 x i8> %x, <4 x i8> %y) {
define i8 @k(<4 x i8> %x) {
; CHECK-LABEL: @k(
-; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
-; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
-; CHECK-NEXT: [[X1:%.*]] = extractelement <4 x i8> [[X]], i32 1
-; CHECK-NEXT: [[X2:%.*]] = extractelement <4 x i8> [[X]], i32 2
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
-; CHECK-NEXT: [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
-; CHECK-NEXT: [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
-; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
-; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
-; CHECK-NEXT: [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
-; CHECK-NEXT: ret i8 [[TMP3]]
+; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i8> [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> undef, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT: [[TMP3:%.*]] = mul <4 x i8> [[X]], [[X]]
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> undef, <2 x i32> <i32 3, i32 2>
+; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i32 0
+; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i32 1
+; CHECK-NEXT: [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
+; CHECK-NEXT: ret i8 [[TMP8]]
;
%x0 = extractelement <4 x i8> %x, i32 0
%x3 = extractelement <4 x i8> %x, i32 3
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll
index f98b0dcd830bb..293dcc0b1ef9e 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll
@@ -5,11 +5,10 @@ define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
; CHECK-LABEL: @g(
; CHECK-NEXT: [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
; CHECK-NEXT: [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
-; CHECK-NEXT: [[INS1:%.*]] = insertelement <2 x i8> poison, i8 [[X0X0]], i32 0
-; CHECK-NEXT: [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
-; CHECK-NEXT: ret <2 x i8> [[INS2]]
+; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i8> poison, i8 [[X0]], i32 0
+; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x i8> [[TMP1]], i8 [[Y1]], i32 1
+; CHECK-NEXT: [[TMP3:%.*]] = mul <2 x i8> [[TMP2]], [[TMP2]]
+; CHECK-NEXT: ret <2 x i8> [[TMP3]]
;
%x0 = extractelement <2 x i8> %x, i32 0
%y1 = extractelement <2 x i8> %y, i32 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll b/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll
index efce8825558ba..61f25dd713775 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll
@@ -5,11 +5,10 @@ define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
; CHECK-LABEL: @g(
; CHECK-NEXT: [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
; CHECK-NEXT: [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
-; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
-; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
-; CHECK-NEXT: [[INS1:%.*]] = insertelement <2 x i8> undef, i8 [[X0X0]], i32 0
-; CHECK-NEXT: [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
-; CHECK-NEXT: ret <2 x i8> [[INS2]]
+; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i8> poison, i8 [[X0]], i32 0
+; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x i8> [[TMP1]], i8 [[Y1]], i32 1
+; CHECK-NEXT: [[TMP3:%.*]] = mul <2 x i8> [[TMP2]], [[TMP2]]
+; CHECK-NEXT: ret <2 x i8> [[TMP3]]
;
%x0 = extractelement <2 x i8> %x, i32 0
%y1 = extractelement <2 x i8> %y, i32 1
More information about the llvm-commits
mailing list