forked from OSchip/llvm-project
[CostModel][X86] Add CostKinds handling for vector integer comparisons
These were based off a mixture of vector integer add/sub costs and the numbers from the 'cost-tables vs llvm-mca' script from D103695 - the extra costs for different predicates are still proving tricky to implement, but I've gotten most costs to within +/1 now - the AVX512 are tricky as we still don't handle predicate results properly, so most of these were done by hand.
This commit is contained in:
Simon Pilgrim
parent
292cb114b0
commit
f8fa04295f
|
|
@ -3104,8 +3104,10 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
};
|
||||
|
||||
static const CostKindTblEntry AVX512BWCostTbl[] = {
|
||||
{ ISD::SETCC, MVT::v32i16, { 1 } },
|
||||
{ ISD::SETCC, MVT::v64i8, { 1 } },
|
||||
{ ISD::SETCC, MVT::v32i16, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v16i16, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v64i8, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v32i8, { 1, 1, 1, 1 } },
|
||||
|
||||
{ ISD::SELECT, MVT::v32i16, { 1, 1, 1, 1 } },
|
||||
{ ISD::SELECT, MVT::v64i8, { 1, 1, 1, 1 } },
|
||||
|
|
@ -3117,8 +3119,13 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
{ ISD::SETCC, MVT::v16f32, { 1, 4, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v8f32, { 1, 4, 1, 1 } },
|
||||
|
||||
{ ISD::SETCC, MVT::v8i64, { 1 } },
|
||||
{ ISD::SETCC, MVT::v16i32, { 1 } },
|
||||
{ ISD::SETCC, MVT::v8i64, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v4i64, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v2i64, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v16i32, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v8i32, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v32i16, { 3, 7, 5, 5 } },
|
||||
{ ISD::SETCC, MVT::v64i8, { 3, 7, 5, 5 } },
|
||||
|
||||
{ ISD::SELECT, MVT::v8i64, { 1, 1, 1, 1 } },
|
||||
{ ISD::SELECT, MVT::v4i64, { 1, 1, 1, 1 } },
|
||||
|
|
@ -3135,9 +3142,6 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
{ ISD::SELECT, MVT::v4f32, { 1, 1, 1, 1 } },
|
||||
{ ISD::SELECT, MVT::f32 , { 1, 1, 1, 1 } },
|
||||
|
||||
{ ISD::SETCC, MVT::v32i16, { 2 } }, // FIXME: should probably be 4
|
||||
{ ISD::SETCC, MVT::v64i8, { 2 } }, // FIXME: should probably be 4
|
||||
|
||||
{ ISD::SELECT, MVT::v32i16, { 2, 2, 4, 4 } },
|
||||
{ ISD::SELECT, MVT::v16i16, { 1, 1, 1, 1 } },
|
||||
{ ISD::SELECT, MVT::v8i16, { 1, 1, 1, 1 } },
|
||||
|
|
@ -3154,10 +3158,10 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
{ ISD::SETCC, MVT::v4f32, { 1, 4, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::f32, { 1, 4, 1, 1 } },
|
||||
|
||||
{ ISD::SETCC, MVT::v4i64, { 1 } },
|
||||
{ ISD::SETCC, MVT::v8i32, { 1 } },
|
||||
{ ISD::SETCC, MVT::v16i16, { 1 } },
|
||||
{ ISD::SETCC, MVT::v32i8, { 1 } },
|
||||
{ ISD::SETCC, MVT::v4i64, { 1, 1, 1, 2 } },
|
||||
{ ISD::SETCC, MVT::v8i32, { 1, 1, 1, 2 } },
|
||||
{ ISD::SETCC, MVT::v16i16, { 1, 1, 1, 2 } },
|
||||
{ ISD::SETCC, MVT::v32i8, { 1, 1, 1, 2 } },
|
||||
|
||||
{ ISD::SELECT, MVT::v4f64, { 2, 2, 1, 2 } }, // vblendvpd
|
||||
{ ISD::SELECT, MVT::v8f32, { 2, 2, 1, 2 } }, // vblendvps
|
||||
|
|
@ -3167,6 +3171,11 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
{ ISD::SELECT, MVT::v32i8, { 2, 2, 1, 2 } }, // pblendvb
|
||||
};
|
||||
|
||||
static const CostKindTblEntry XOPCostTbl[] = {
|
||||
{ ISD::SETCC, MVT::v4i64, { 4, 2, 5, 6 } },
|
||||
{ ISD::SETCC, MVT::v2i64, { 1, 1, 1, 1 } },
|
||||
};
|
||||
|
||||
static const CostKindTblEntry AVX1CostTbl[] = {
|
||||
{ ISD::SETCC, MVT::v4f64, { 2, 3, 1, 2 } },
|
||||
{ ISD::SETCC, MVT::v2f64, { 1, 3, 1, 1 } },
|
||||
|
|
@ -3176,10 +3185,10 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
{ ISD::SETCC, MVT::f32, { 1, 3, 1, 1 } },
|
||||
|
||||
// AVX1 does not support 8-wide integer compare.
|
||||
{ ISD::SETCC, MVT::v4i64, { 4 } },
|
||||
{ ISD::SETCC, MVT::v8i32, { 4 } },
|
||||
{ ISD::SETCC, MVT::v16i16, { 4 } },
|
||||
{ ISD::SETCC, MVT::v32i8, { 4 } },
|
||||
{ ISD::SETCC, MVT::v4i64, { 4, 2, 5, 6 } },
|
||||
{ ISD::SETCC, MVT::v8i32, { 4, 2, 5, 6 } },
|
||||
{ ISD::SETCC, MVT::v16i16, { 4, 2, 5, 6 } },
|
||||
{ ISD::SETCC, MVT::v32i8, { 4, 2, 5, 6 } },
|
||||
|
||||
{ ISD::SELECT, MVT::v4f64, { 3, 3, 1, 2 } }, // vblendvpd
|
||||
{ ISD::SELECT, MVT::v8f32, { 3, 3, 1, 2 } }, // vblendvps
|
||||
|
|
@ -3190,7 +3199,7 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
};
|
||||
|
||||
static const CostKindTblEntry SSE42CostTbl[] = {
|
||||
{ ISD::SETCC, MVT::v2i64, { 1 } },
|
||||
{ ISD::SETCC, MVT::v2i64, { 1, 2, 1, 2 } },
|
||||
};
|
||||
|
||||
static const CostKindTblEntry SSE41CostTbl[] = {
|
||||
|
|
@ -3211,10 +3220,10 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
{ ISD::SETCC, MVT::v2f64, { 2, 5, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::f64, { 1, 5, 1, 1 } },
|
||||
|
||||
{ ISD::SETCC, MVT::v2i64, { 5 } }, // pcmpeqd/pcmpgtd expansion
|
||||
{ ISD::SETCC, MVT::v4i32, { 1 } },
|
||||
{ ISD::SETCC, MVT::v8i16, { 1 } },
|
||||
{ ISD::SETCC, MVT::v16i8, { 1 } },
|
||||
{ ISD::SETCC, MVT::v2i64, { 5, 4, 5, 5 } }, // pcmpeqd/pcmpgtd expansion
|
||||
{ ISD::SETCC, MVT::v4i32, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v8i16, { 1, 1, 1, 1 } },
|
||||
{ ISD::SETCC, MVT::v16i8, { 1, 1, 1, 1 } },
|
||||
|
||||
{ ISD::SELECT, MVT::v2f64, { 2, 2, 3, 3 } }, // andpd + andnpd + orpd
|
||||
{ ISD::SELECT, MVT::f64, { 2, 2, 3, 3 } }, // andpd + andnpd + orpd
|
||||
|
|
@ -3252,6 +3261,11 @@ InstructionCost X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
|
|||
if (auto KindCost = Entry->Cost[CostKind])
|
||||
return LT.first * (ExtraCost + KindCost.value());
|
||||
|
||||
if (ST->hasXOP())
|
||||
if (const auto *Entry = CostTableLookup(XOPCostTbl, ISD, MTy))
|
||||
if (auto KindCost = Entry->Cost[CostKind])
|
||||
return LT.first * (ExtraCost + KindCost.value());
|
||||
|
||||
if (ST->hasAVX())
|
||||
if (const auto *Entry = CostTableLookup(AVX1CostTbl, ISD, MTy))
|
||||
if (auto KindCost = Entry->Cost[CostKind])
|
||||
|
|
|
|||
|
|
@ -124,11 +124,11 @@ define i32 @sadd(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'sadd'
|
||||
|
|
@ -162,11 +162,11 @@ define i32 @sadd(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SLM-LABEL: 'sadd'
|
||||
|
|
@ -362,11 +362,11 @@ define i32 @uadd(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'uadd'
|
||||
|
|
@ -400,11 +400,11 @@ define i32 @uadd(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SLM-LABEL: 'uadd'
|
||||
|
|
@ -600,11 +600,11 @@ define i32 @ssub(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'ssub'
|
||||
|
|
@ -638,11 +638,11 @@ define i32 @ssub(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SLM-LABEL: 'ssub'
|
||||
|
|
@ -838,11 +838,11 @@ define i32 @usub(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'usub'
|
||||
|
|
@ -876,11 +876,11 @@ define i32 @usub(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SLM-LABEL: 'usub'
|
||||
|
|
@ -1076,11 +1076,11 @@ define i32 @smul(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'smul'
|
||||
|
|
@ -1114,11 +1114,11 @@ define i32 @smul(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SLM-LABEL: 'smul'
|
||||
|
|
@ -1314,11 +1314,11 @@ define i32 @umul(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'umul'
|
||||
|
|
@ -1352,11 +1352,11 @@ define i32 @umul(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SLM-LABEL: 'umul'
|
||||
|
|
|
|||
|
|
@ -180,7 +180,7 @@ define void @var_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <32 x i
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshl.i16(i16 %a16, i16 %b16, i16 %c16)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8I16 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> %c128)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> %c256)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %c512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %c512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'var_funnel_i16'
|
||||
|
|
@ -194,7 +194,7 @@ define void @var_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <32 x i
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshl.i16(i16 %a16, i16 %b16, i16 %c16)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8I16 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> %c128)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> %c256)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %c512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %c512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'var_funnel_i16'
|
||||
|
|
@ -258,7 +258,7 @@ define void @var_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x i8> %
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshl.i8(i8 %a8, i8 %b8, i8 %c8)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> %c128)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I8 = call <32 x i8> @llvm.fshl.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> %c256)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %c512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %c512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'var_funnel_i8'
|
||||
|
|
@ -272,7 +272,7 @@ define void @var_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x i8> %
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshl.i8(i8 %a8, i8 %b8, i8 %c8)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> %c128)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I8 = call <32 x i8> @llvm.fshl.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> %c256)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %c512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %c512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'var_funnel_i8'
|
||||
|
|
@ -496,7 +496,7 @@ define void @splatvar_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <3
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %u512 = shufflevector <32 x i16> %c512, <32 x i16> undef, <32 x i32> zeroinitializer
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> %u128)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> %u256)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %u512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %u512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'splatvar_funnel_i16'
|
||||
|
|
@ -514,7 +514,7 @@ define void @splatvar_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <3
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %u512 = shufflevector <32 x i16> %c512, <32 x i16> undef, <32 x i32> zeroinitializer
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> %u128)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> %u256)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %u512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %u512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'splatvar_funnel_i16'
|
||||
|
|
@ -587,7 +587,7 @@ define void @splatvar_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %u512 = shufflevector <64 x i8> %c512, <64 x i8> undef, <64 x i32> zeroinitializer
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16I8 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> %u128)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32I8 = call <32 x i8> @llvm.fshl.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> %u256)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %u512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %u512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'splatvar_funnel_i8'
|
||||
|
|
@ -605,7 +605,7 @@ define void @splatvar_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %u512 = shufflevector <64 x i8> %c512, <64 x i8> undef, <64 x i32> zeroinitializer
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16I8 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> %u128)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32I8 = call <32 x i8> @llvm.fshl.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> %u256)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %u512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %u512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'splatvar_funnel_i8'
|
||||
|
|
@ -802,7 +802,7 @@ define void @constant_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <3
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshl.i16(i16 %a16, i16 %b16, i16 7)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I16 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'constant_funnel_i16'
|
||||
|
|
@ -816,7 +816,7 @@ define void @constant_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <3
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshl.i16(i16 %a16, i16 %b16, i16 7)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I16 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'constant_funnel_i16'
|
||||
|
|
@ -880,7 +880,7 @@ define void @constant_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshl.i8(i8 %a8, i8 %b8, i8 7)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I8 = call <32 x i8> @llvm.fshl.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'constant_funnel_i8'
|
||||
|
|
@ -894,7 +894,7 @@ define void @constant_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshl.i8(i8 %a8, i8 %b8, i8 7)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I8 = call <32 x i8> @llvm.fshl.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'constant_funnel_i8'
|
||||
|
|
@ -1076,7 +1076,7 @@ define void @splatconstant_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a25
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshl.i16(i16 %a16, i16 %b16, i16 3)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I16 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'splatconstant_funnel_i16'
|
||||
|
|
@ -1090,7 +1090,7 @@ define void @splatconstant_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a25
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshl.i16(i16 %a16, i16 %b16, i16 3)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I16 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I16 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'splatconstant_funnel_i16'
|
||||
|
|
@ -1147,7 +1147,7 @@ define void @splatconstant_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshl.i8(i8 %a8, i8 %b8, i8 3)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I8 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.fshl.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'splatconstant_funnel_i8'
|
||||
|
|
@ -1161,7 +1161,7 @@ define void @splatconstant_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshl.i8(i8 %a8, i8 %b8, i8 3)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I8 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.fshl.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'splatconstant_funnel_i8'
|
||||
|
|
|
|||
|
|
@ -180,7 +180,7 @@ define void @var_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <32 x i
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshr.i16(i16 %a16, i16 %b16, i16 %c16)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8I16 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> %c128)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> %c256)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %c512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %c512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'var_funnel_i16'
|
||||
|
|
@ -194,7 +194,7 @@ define void @var_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <32 x i
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshr.i16(i16 %a16, i16 %b16, i16 %c16)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8I16 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> %c128)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> %c256)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %c512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %c512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'var_funnel_i16'
|
||||
|
|
@ -258,7 +258,7 @@ define void @var_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x i8> %
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshr.i8(i8 %a8, i8 %b8, i8 %c8)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> %c128)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I8 = call <32 x i8> @llvm.fshr.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> %c256)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %c512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %c512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'var_funnel_i8'
|
||||
|
|
@ -272,7 +272,7 @@ define void @var_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x i8> %
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshr.i8(i8 %a8, i8 %b8, i8 %c8)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> %c128)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I8 = call <32 x i8> @llvm.fshr.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> %c256)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %c512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %c512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'var_funnel_i8'
|
||||
|
|
@ -496,7 +496,7 @@ define void @splatvar_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <3
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %u512 = shufflevector <32 x i16> %c512, <32 x i16> undef, <32 x i32> zeroinitializer
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> %u128)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> %u256)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %u512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %u512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'splatvar_funnel_i16'
|
||||
|
|
@ -514,7 +514,7 @@ define void @splatvar_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <3
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %u512 = shufflevector <32 x i16> %c512, <32 x i16> undef, <32 x i32> zeroinitializer
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> %u128)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> %u256)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %u512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> %u512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'splatvar_funnel_i16'
|
||||
|
|
@ -587,7 +587,7 @@ define void @splatvar_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %u512 = shufflevector <64 x i8> %c512, <64 x i8> undef, <64 x i32> zeroinitializer
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16I8 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> %u128)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32I8 = call <32 x i8> @llvm.fshr.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> %u256)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %u512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %u512)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'splatvar_funnel_i8'
|
||||
|
|
@ -605,7 +605,7 @@ define void @splatvar_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %u512 = shufflevector <64 x i8> %c512, <64 x i8> undef, <64 x i32> zeroinitializer
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16I8 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> %u128)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32I8 = call <32 x i8> @llvm.fshr.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> %u256)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %u512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> %u512)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'splatvar_funnel_i8'
|
||||
|
|
@ -802,7 +802,7 @@ define void @constant_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <3
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshr.i16(i16 %a16, i16 %b16, i16 7)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I16 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'constant_funnel_i16'
|
||||
|
|
@ -816,7 +816,7 @@ define void @constant_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a256, <3
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshr.i16(i16 %a16, i16 %b16, i16 7)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I16 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'constant_funnel_i16'
|
||||
|
|
@ -880,7 +880,7 @@ define void @constant_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshr.i8(i8 %a8, i8 %b8, i8 7)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I8 = call <32 x i8> @llvm.fshr.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'constant_funnel_i8'
|
||||
|
|
@ -894,7 +894,7 @@ define void @constant_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <64 x
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshr.i8(i8 %a8, i8 %b8, i8 7)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I8 = call <32 x i8> @llvm.fshr.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'constant_funnel_i8'
|
||||
|
|
@ -1076,7 +1076,7 @@ define void @splatconstant_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a25
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshr.i16(i16 %a16, i16 %b16, i16 3)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I16 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'splatconstant_funnel_i16'
|
||||
|
|
@ -1090,7 +1090,7 @@ define void @splatconstant_funnel_i16(i16 %a16, <8 x i16> %a128, <16 x i16> %a25
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.fshr.i16(i16 %a16, i16 %b16, i16 3)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I16 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %a128, <8 x i16> %b128, <8 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %a256, <16 x i16> %b256, <16 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32I16 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %a512, <32 x i16> %b512, <32 x i16> <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'splatconstant_funnel_i16'
|
||||
|
|
@ -1147,7 +1147,7 @@ define void @splatconstant_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshr.i8(i8 %a8, i8 %b8, i8 3)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I8 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.fshr.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; AVX512BW-LABEL: 'splatconstant_funnel_i8'
|
||||
|
|
@ -1161,7 +1161,7 @@ define void @splatconstant_funnel_i8(i8 %a8, <16 x i8> %a128, <32 x i8> %a256, <
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.fshr.i8(i8 %a8, i8 %b8, i8 3)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I8 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> %a128, <16 x i8> %b128, <16 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.fshr.v32i8(<32 x i8> %a256, <32 x i8> %b256, <32 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %a512, <64 x i8> %b512, <64 x i8> <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; SLM-LABEL: 'splatconstant_funnel_i8'
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -181,13 +181,13 @@ define i32 @cmp_int_eq(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp eq i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = icmp eq <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = icmp eq <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = icmp eq <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V128I8 = icmp eq <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = icmp eq <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V128I8 = icmp eq <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp eq i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = icmp eq <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = icmp eq <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = icmp eq <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I16 = icmp eq <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = icmp eq <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I16 = icmp eq <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp eq i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp eq <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp eq <8 x i32> undef, undef
|
||||
|
|
@ -485,13 +485,13 @@ define i32 @cmp_int_ne(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp ne i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = icmp ne <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = icmp ne <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = icmp ne <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V128I8 = icmp ne <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = icmp ne <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128I8 = icmp ne <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp ne i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = icmp ne <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = icmp ne <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = icmp ne <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I16 = icmp ne <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = icmp ne <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I16 = icmp ne <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp ne i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp ne <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp ne <8 x i32> undef, undef
|
||||
|
|
@ -789,13 +789,13 @@ define i32 @cmp_int_sge(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp sge i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = icmp sge <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = icmp sge <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = icmp sge <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V128I8 = icmp sge <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = icmp sge <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128I8 = icmp sge <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp sge i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = icmp sge <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = icmp sge <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = icmp sge <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I16 = icmp sge <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = icmp sge <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I16 = icmp sge <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp sge i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp sge <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp sge <8 x i32> undef, undef
|
||||
|
|
@ -1093,13 +1093,13 @@ define i32 @cmp_int_uge(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp uge i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = icmp uge <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = icmp uge <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = icmp uge <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V128I8 = icmp uge <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = icmp uge <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128I8 = icmp uge <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp uge i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = icmp uge <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = icmp uge <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = icmp uge <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I16 = icmp uge <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = icmp uge <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I16 = icmp uge <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp uge i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp uge <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp uge <8 x i32> undef, undef
|
||||
|
|
@ -1397,13 +1397,13 @@ define i32 @cmp_int_sgt(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp sgt i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = icmp sgt <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = icmp sgt <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = icmp sgt <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V128I8 = icmp sgt <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = icmp sgt <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V128I8 = icmp sgt <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp sgt i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = icmp sgt <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = icmp sgt <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = icmp sgt <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I16 = icmp sgt <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = icmp sgt <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I16 = icmp sgt <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp sgt i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp sgt <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp sgt <8 x i32> undef, undef
|
||||
|
|
@ -1701,13 +1701,13 @@ define i32 @cmp_int_ugt(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp ugt i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I8 = icmp ugt <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I8 = icmp ugt <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = icmp ugt <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128I8 = icmp ugt <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = icmp ugt <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V128I8 = icmp ugt <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp ugt i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = icmp ugt <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I16 = icmp ugt <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = icmp ugt <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I16 = icmp ugt <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = icmp ugt <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V64I16 = icmp ugt <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp ugt i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp ugt <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp ugt <8 x i32> undef, undef
|
||||
|
|
@ -2005,13 +2005,13 @@ define i32 @cmp_int_sle(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp sle i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = icmp sle <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = icmp sle <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = icmp sle <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V128I8 = icmp sle <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = icmp sle <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128I8 = icmp sle <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp sle i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = icmp sle <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = icmp sle <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = icmp sle <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I16 = icmp sle <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = icmp sle <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I16 = icmp sle <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp sle i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp sle <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp sle <8 x i32> undef, undef
|
||||
|
|
@ -2309,13 +2309,13 @@ define i32 @cmp_int_ule(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp ule i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = icmp ule <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = icmp ule <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = icmp ule <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V128I8 = icmp ule <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = icmp ule <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128I8 = icmp ule <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp ule i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = icmp ule <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = icmp ule <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = icmp ule <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I16 = icmp ule <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = icmp ule <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I16 = icmp ule <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp ule i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp ule <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp ule <8 x i32> undef, undef
|
||||
|
|
@ -2613,13 +2613,13 @@ define i32 @cmp_int_slt(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp slt i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = icmp slt <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = icmp slt <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = icmp slt <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V128I8 = icmp slt <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = icmp slt <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V128I8 = icmp slt <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp slt i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = icmp slt <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = icmp slt <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = icmp slt <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I16 = icmp slt <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = icmp slt <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I16 = icmp slt <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp slt i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp slt <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp slt <8 x i32> undef, undef
|
||||
|
|
@ -2917,13 +2917,13 @@ define i32 @cmp_int_ult(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = icmp ult i8 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I8 = icmp ult <16 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32I8 = icmp ult <32 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = icmp ult <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128I8 = icmp ult <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = icmp ult <64 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V128I8 = icmp ult <128 x i8> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = icmp ult i16 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = icmp ult <8 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I16 = icmp ult <16 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = icmp ult <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I16 = icmp ult <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = icmp ult <32 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V64I16 = icmp ult <64 x i16> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = icmp ult i32 undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = icmp ult <4 x i32> undef, undef
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = icmp ult <8 x i32> undef, undef
|
||||
|
|
|
|||
|
|
@ -56,17 +56,17 @@ define void @umul(i32 %a, i32 %b, <16 x i32> %va, <16 x i32> %vb) {
|
|||
;
|
||||
; LATE-LABEL: 'umul'
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %s = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 93 for instruction: %v = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %v = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
; SIZE-LABEL: 'umul'
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %s = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %v = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %v = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
; SIZE_LATE-LABEL: 'umul'
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %s = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %v = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %v = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
%s = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
|
||||
|
|
@ -82,17 +82,17 @@ define void @smax(i32 %a, i32 %b, <16 x i32> %va, <16 x i32> %vb) {
|
|||
;
|
||||
; LATE-LABEL: 'smax'
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %s = call i32 @llvm.smax.i32(i32 %a, i32 %b)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
; SIZE-LABEL: 'smax'
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %s = call i32 @llvm.smax.i32(i32 %a, i32 %b)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
; SIZE_LATE-LABEL: 'smax'
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %s = call i32 @llvm.smax.i32(i32 %a, i32 %b)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
%s = call i32 @llvm.smax.i32(i32 %a, i32 %b)
|
||||
|
|
@ -290,17 +290,17 @@ define void @fshl(i32 %a, i32 %b, i32 %c, <16 x i32> %va, <16 x i32> %vb, <16 x
|
|||
;
|
||||
; LATE-LABEL: 'fshl'
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 142 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 145 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
|
||||
; LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
; SIZE-LABEL: 'fshl'
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 122 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
|
||||
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
; SIZE_LATE-LABEL: 'fshl'
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 146 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 149 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
|
||||
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
||||
;
|
||||
%s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
|
||||
|
|
|
|||
|
|
@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.vector.reduce.smax.v32i16(<32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i16'
|
||||
|
|
@ -201,7 +201,7 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.vector.reduce.smax.v32i16(<32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef)
|
||||
|
|
@ -271,7 +271,7 @@ define i32 @reduce_i8(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i8'
|
||||
|
|
@ -291,7 +291,7 @@ define i32 @reduce_i8(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i8 @llvm.vector.reduce.smax.v2i8(<2 x i8> undef)
|
||||
|
|
|
|||
|
|
@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.smin.v16i16(<16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.vector.reduce.smin.v32i16(<32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64 = call i16 @llvm.vector.reduce.smin.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V64 = call i16 @llvm.vector.reduce.smin.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i16'
|
||||
|
|
@ -201,7 +201,7 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.smin.v16i16(<16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.vector.reduce.smin.v32i16(<32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64 = call i16 @llvm.vector.reduce.smin.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V64 = call i16 @llvm.vector.reduce.smin.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i16 @llvm.vector.reduce.smin.v2i16(<2 x i16> undef)
|
||||
|
|
@ -271,7 +271,7 @@ define i32 @reduce_i8(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i8 @llvm.vector.reduce.smin.v32i8(<32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.vector.reduce.smin.v64i8(<64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V128 = call i8 @llvm.vector.reduce.smin.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i8 @llvm.vector.reduce.smin.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i8'
|
||||
|
|
@ -291,7 +291,7 @@ define i32 @reduce_i8(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i8 @llvm.vector.reduce.smin.v32i8(<32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.vector.reduce.smin.v64i8(<64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V128 = call i8 @llvm.vector.reduce.smin.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i8 @llvm.vector.reduce.smin.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i8 @llvm.vector.reduce.smin.v2i8(<2 x i8> undef)
|
||||
|
|
|
|||
|
|
@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.vector.reduce.umax.v32i16(<32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i16'
|
||||
|
|
@ -201,7 +201,7 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.vector.reduce.umax.v32i16(<32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef)
|
||||
|
|
@ -271,7 +271,7 @@ define i32 @reduce_i8(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i8'
|
||||
|
|
@ -291,7 +291,7 @@ define i32 @reduce_i8(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i8 @llvm.vector.reduce.umax.v2i8(<2 x i8> undef)
|
||||
|
|
|
|||
|
|
@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.umin.v16i16(<16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.vector.reduce.umin.v32i16(<32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64 = call i16 @llvm.vector.reduce.umin.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V64 = call i16 @llvm.vector.reduce.umin.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i16'
|
||||
|
|
@ -201,7 +201,7 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.umin.v16i16(<16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.vector.reduce.umin.v32i16(<32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64 = call i16 @llvm.vector.reduce.umin.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V64 = call i16 @llvm.vector.reduce.umin.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i16 @llvm.vector.reduce.umin.v2i16(<2 x i16> undef)
|
||||
|
|
@ -271,7 +271,7 @@ define i32 @reduce_i8(i32 %arg) {
|
|||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i8 @llvm.vector.reduce.umin.v32i8(<32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.vector.reduce.umin.v64i8(<64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V128 = call i8 @llvm.vector.reduce.umin.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i8 @llvm.vector.reduce.umin.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i8'
|
||||
|
|
@ -291,7 +291,7 @@ define i32 @reduce_i8(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i8 @llvm.vector.reduce.umin.v32i8(<32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.vector.reduce.umin.v64i8(<64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V128 = call i8 @llvm.vector.reduce.umin.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i8 @llvm.vector.reduce.umin.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i8 @llvm.vector.reduce.umin.v2i8(<2 x i8> undef)
|
||||
|
|
|
|||
Loading…
Reference in New Issue