forked from OSchip/llvm-project
[CostModel][X86] Improve sum reduction costs.
I can't see any notable differences in costs between SSE2 and SSE42 arches for FADD/ADD reduction, so I've lowered the target to just SSE2. I've also added vXi8 sum reduction costs in line with the PSADBW codegen and discussions on PR42674. llvm-svn: 374655
This commit is contained in:
Simon Pilgrim
parent
ba229557dd
commit
1b59a16c0b
|
|
@ -2488,7 +2488,7 @@ int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
|
|||
// We use the Intel Architecture Code Analyzer(IACA) to measure the throughput
|
||||
// and make it as the cost.
|
||||
|
||||
static const CostTblEntry SSE42CostTblPairWise[] = {
|
||||
static const CostTblEntry SSE2CostTblPairWise[] = {
|
||||
{ ISD::FADD, MVT::v2f64, 2 },
|
||||
{ ISD::FADD, MVT::v4f32, 4 },
|
||||
{ ISD::ADD, MVT::v2i64, 2 }, // The data reported by the IACA tool is "1.6".
|
||||
|
|
@ -2497,23 +2497,23 @@ int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
|
|||
{ ISD::ADD, MVT::v2i16, 3 }, // FIXME: chosen to be less than v4i16
|
||||
{ ISD::ADD, MVT::v4i16, 4 }, // FIXME: chosen to be less than v8i16
|
||||
{ ISD::ADD, MVT::v8i16, 5 },
|
||||
{ ISD::ADD, MVT::v2i8, 2 },
|
||||
{ ISD::ADD, MVT::v4i8, 2 },
|
||||
{ ISD::ADD, MVT::v8i8, 2 },
|
||||
{ ISD::ADD, MVT::v16i8, 3 },
|
||||
};
|
||||
|
||||
static const CostTblEntry AVX1CostTblPairWise[] = {
|
||||
{ ISD::FADD, MVT::v4f32, 4 },
|
||||
{ ISD::FADD, MVT::v4f64, 5 },
|
||||
{ ISD::FADD, MVT::v8f32, 7 },
|
||||
{ ISD::ADD, MVT::v2i64, 1 }, // The data reported by the IACA tool is "1.5".
|
||||
{ ISD::ADD, MVT::v2i32, 2 }, // FIXME: chosen to be less than v4i32
|
||||
{ ISD::ADD, MVT::v4i32, 3 }, // The data reported by the IACA tool is "3.5".
|
||||
{ ISD::ADD, MVT::v4i64, 5 }, // The data reported by the IACA tool is "4.8".
|
||||
{ ISD::ADD, MVT::v2i16, 3 }, // FIXME: chosen to be less than v4i16
|
||||
{ ISD::ADD, MVT::v4i16, 4 }, // FIXME: chosen to be less than v8i16
|
||||
{ ISD::ADD, MVT::v8i16, 5 },
|
||||
{ ISD::ADD, MVT::v8i32, 5 },
|
||||
{ ISD::ADD, MVT::v16i16, 6 },
|
||||
{ ISD::ADD, MVT::v32i8, 4 },
|
||||
};
|
||||
|
||||
static const CostTblEntry SSE42CostTblNoPairWise[] = {
|
||||
static const CostTblEntry SSE2CostTblNoPairWise[] = {
|
||||
{ ISD::FADD, MVT::v2f64, 2 },
|
||||
{ ISD::FADD, MVT::v4f32, 4 },
|
||||
{ ISD::ADD, MVT::v2i64, 2 }, // The data reported by the IACA tool is "1.6".
|
||||
|
|
@ -2522,20 +2522,21 @@ int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
|
|||
{ ISD::ADD, MVT::v2i16, 2 }, // The data reported by the IACA tool is "4.3".
|
||||
{ ISD::ADD, MVT::v4i16, 3 }, // The data reported by the IACA tool is "4.3".
|
||||
{ ISD::ADD, MVT::v8i16, 4 }, // The data reported by the IACA tool is "4.3".
|
||||
{ ISD::ADD, MVT::v2i8, 2 },
|
||||
{ ISD::ADD, MVT::v4i8, 2 },
|
||||
{ ISD::ADD, MVT::v8i8, 2 },
|
||||
{ ISD::ADD, MVT::v16i8, 3 },
|
||||
};
|
||||
|
||||
static const CostTblEntry AVX1CostTblNoPairWise[] = {
|
||||
{ ISD::FADD, MVT::v4f32, 3 },
|
||||
{ ISD::FADD, MVT::v4f64, 3 },
|
||||
{ ISD::FADD, MVT::v4f32, 3 },
|
||||
{ ISD::FADD, MVT::v8f32, 4 },
|
||||
{ ISD::ADD, MVT::v2i64, 1 }, // The data reported by the IACA tool is "1.5".
|
||||
{ ISD::ADD, MVT::v2i32, 2 }, // FIXME: chosen to be less than v4i32
|
||||
{ ISD::ADD, MVT::v4i32, 3 }, // The data reported by the IACA tool is "2.8".
|
||||
{ ISD::ADD, MVT::v4i64, 3 },
|
||||
{ ISD::ADD, MVT::v2i16, 2 }, // The data reported by the IACA tool is "4.3".
|
||||
{ ISD::ADD, MVT::v4i16, 3 }, // The data reported by the IACA tool is "4.3".
|
||||
{ ISD::ADD, MVT::v8i16, 4 },
|
||||
{ ISD::ADD, MVT::v8i32, 5 },
|
||||
{ ISD::ADD, MVT::v16i16, 5 },
|
||||
{ ISD::ADD, MVT::v32i8, 4 },
|
||||
};
|
||||
|
||||
int ISD = TLI->InstructionOpcodeToISD(Opcode);
|
||||
|
|
@ -2552,16 +2553,16 @@ int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
|
|||
if (const auto *Entry = CostTableLookup(AVX1CostTblPairWise, ISD, MTy))
|
||||
return Entry->Cost;
|
||||
|
||||
if (ST->hasSSE42())
|
||||
if (const auto *Entry = CostTableLookup(SSE42CostTblPairWise, ISD, MTy))
|
||||
if (ST->hasSSE2())
|
||||
if (const auto *Entry = CostTableLookup(SSE2CostTblPairWise, ISD, MTy))
|
||||
return Entry->Cost;
|
||||
} else {
|
||||
if (ST->hasAVX())
|
||||
if (const auto *Entry = CostTableLookup(AVX1CostTblNoPairWise, ISD, MTy))
|
||||
return Entry->Cost;
|
||||
|
||||
if (ST->hasSSE42())
|
||||
if (const auto *Entry = CostTableLookup(SSE42CostTblNoPairWise, ISD, MTy))
|
||||
if (ST->hasSSE2())
|
||||
if (const auto *Entry = CostTableLookup(SSE2CostTblNoPairWise, ISD, MTy))
|
||||
return Entry->Cost;
|
||||
}
|
||||
}
|
||||
|
|
@ -2575,16 +2576,16 @@ int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
|
|||
if (const auto *Entry = CostTableLookup(AVX1CostTblPairWise, ISD, MTy))
|
||||
return LT.first * Entry->Cost;
|
||||
|
||||
if (ST->hasSSE42())
|
||||
if (const auto *Entry = CostTableLookup(SSE42CostTblPairWise, ISD, MTy))
|
||||
if (ST->hasSSE2())
|
||||
if (const auto *Entry = CostTableLookup(SSE2CostTblPairWise, ISD, MTy))
|
||||
return LT.first * Entry->Cost;
|
||||
} else {
|
||||
if (ST->hasAVX())
|
||||
if (const auto *Entry = CostTableLookup(AVX1CostTblNoPairWise, ISD, MTy))
|
||||
return LT.first * Entry->Cost;
|
||||
|
||||
if (ST->hasSSE42())
|
||||
if (const auto *Entry = CostTableLookup(SSE42CostTblNoPairWise, ISD, MTy))
|
||||
if (ST->hasSSE2())
|
||||
if (const auto *Entry = CostTableLookup(SSE2CostTblNoPairWise, ISD, MTy))
|
||||
return LT.first * Entry->Cost;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -9,29 +9,13 @@
|
|||
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
|
||||
|
||||
define i32 @reduce_i64(i32 %arg) {
|
||||
; SSE2-LABEL: 'reduce_i64'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SSSE3-LABEL: 'reduce_i64'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SSE42-LABEL: 'reduce_i64'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
; SSE-LABEL: 'reduce_i64'
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX-LABEL: 'reduce_i64'
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
|
||||
|
|
@ -58,29 +42,13 @@ define i32 @reduce_i64(i32 %arg) {
|
|||
}
|
||||
|
||||
define i32 @reduce_i32(i32 %arg) {
|
||||
; SSE2-LABEL: 'reduce_i32'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SSSE3-LABEL: 'reduce_i32'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SSE42-LABEL: 'reduce_i32'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
; SSE-LABEL: 'reduce_i32'
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX-LABEL: 'reduce_i32'
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
|
||||
|
|
@ -107,65 +75,38 @@ define i32 @reduce_i32(i32 %arg) {
|
|||
}
|
||||
|
||||
define i32 @reduce_i16(i32 %arg) {
|
||||
; SSE2-LABEL: 'reduce_i16'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
; SSE-LABEL: 'reduce_i16'
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SSSE3-LABEL: 'reduce_i16'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SSE42-LABEL: 'reduce_i16'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX1-LABEL: 'reduce_i16'
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX2-LABEL: 'reduce_i16'
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
; AVX-LABEL: 'reduce_i16'
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512F-LABEL: 'reduce_i16'
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i16'
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
|
|
@ -174,9 +115,9 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
|
||||
|
|
@ -189,84 +130,54 @@ define i32 @reduce_i16(i32 %arg) {
|
|||
}
|
||||
|
||||
define i32 @reduce_i8(i32 %arg) {
|
||||
; SSE2-LABEL: 'reduce_i8'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
; SSE-LABEL: 'reduce_i8'
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SSSE3-LABEL: 'reduce_i8'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; SSE42-LABEL: 'reduce_i8'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX1-LABEL: 'reduce_i8'
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 73 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX2-LABEL: 'reduce_i8'
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
; AVX-LABEL: 'reduce_i8'
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512F-LABEL: 'reduce_i8'
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512BW-LABEL: 'reduce_i8'
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; AVX512DQ-LABEL: 'reduce_i8'
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
|
||||
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ define fastcc float @reduction_cost_float(<4 x float> %rdx) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
|
||||
;
|
||||
; SSSE3-LABEL: 'reduction_cost_float'
|
||||
|
|
@ -23,7 +23,7 @@ define fastcc float @reduction_cost_float(<4 x float> %rdx) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
|
||||
;
|
||||
; SSE42-LABEL: 'reduction_cost_float'
|
||||
|
|
@ -107,7 +107,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r2 = fadd float %r, %f1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
|
||||
;
|
||||
|
|
@ -118,7 +118,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r2 = fadd float %r, %f1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
|
||||
;
|
||||
|
|
@ -168,7 +168,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r2 = fadd float %r, %f1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
|
||||
;
|
||||
|
|
@ -179,7 +179,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r2 = fadd float %r, %f1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
|
||||
;
|
||||
|
|
@ -228,7 +228,7 @@ define fastcc float @pairwise_hadd_skip_first(<4 x float> %rdx, float %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.1 = fadd <4 x float> %bin.rdx.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r2 = fadd float %r, %f1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
|
||||
;
|
||||
|
|
@ -238,7 +238,7 @@ define fastcc float @pairwise_hadd_skip_first(<4 x float> %rdx, float %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.1 = fadd <4 x float> %bin.rdx.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r2 = fadd float %r, %f1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
|
||||
;
|
||||
|
|
@ -280,13 +280,13 @@ define fastcc double @no_pairwise_reduction2double(<2 x double> %rdx, double %f1
|
|||
; SSE2-LABEL: 'no_pairwise_reduction2double'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <2 x double> %rdx, %rdx.shuf
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x double> %bin.rdx, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
|
||||
;
|
||||
; SSSE3-LABEL: 'no_pairwise_reduction2double'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <2 x double> %rdx, %rdx.shuf
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x double> %bin.rdx, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
|
||||
;
|
||||
; SSE42-LABEL: 'no_pairwise_reduction2double'
|
||||
|
|
@ -314,7 +314,7 @@ define fastcc float @no_pairwise_reduction4float(<4 x float> %rdx, float %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
|
||||
;
|
||||
; SSSE3-LABEL: 'no_pairwise_reduction4float'
|
||||
|
|
@ -322,7 +322,7 @@ define fastcc float @no_pairwise_reduction4float(<4 x float> %rdx, float %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
|
||||
;
|
||||
; SSE42-LABEL: 'no_pairwise_reduction4float'
|
||||
|
|
@ -356,7 +356,7 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
|
||||
;
|
||||
; SSSE3-LABEL: 'no_pairwise_reduction4double'
|
||||
|
|
@ -364,7 +364,7 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
|
||||
;
|
||||
; SSE42-LABEL: 'no_pairwise_reduction4double'
|
||||
|
|
@ -463,23 +463,11 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) {
|
|||
}
|
||||
|
||||
define fastcc i64 @no_pairwise_reduction2i64(<2 x i64> %rdx, i64 %f1) {
|
||||
; SSE2-LABEL: 'no_pairwise_reduction2i64'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <2 x i64> %rdx, %rdx.shuf
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x i64> %bin.rdx, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
|
||||
;
|
||||
; SSSE3-LABEL: 'no_pairwise_reduction2i64'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <2 x i64> %rdx, %rdx.shuf
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x i64> %bin.rdx, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
|
||||
;
|
||||
; SSE42-LABEL: 'no_pairwise_reduction2i64'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <2 x i64> %rdx, %rdx.shuf
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x i64> %bin.rdx, i32 0
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
|
||||
; SSE-LABEL: 'no_pairwise_reduction2i64'
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <2 x i64> %rdx, %rdx.shuf
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x i64> %bin.rdx, i32 0
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
|
||||
;
|
||||
; AVX-LABEL: 'no_pairwise_reduction2i64'
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
|
|
@ -495,37 +483,13 @@ define fastcc i64 @no_pairwise_reduction2i64(<2 x i64> %rdx, i64 %f1) {
|
|||
}
|
||||
|
||||
define fastcc i32 @no_pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) {
|
||||
; SSE2-LABEL: 'no_pairwise_reduction4i32'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx, %rdx.shuf
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %bin.rdx, %rdx.shuf7
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; SSSE3-LABEL: 'no_pairwise_reduction4i32'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx, %rdx.shuf
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %bin.rdx, %rdx.shuf7
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; SSE42-LABEL: 'no_pairwise_reduction4i32'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx, %rdx.shuf
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %bin.rdx, %rdx.shuf7
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; AVX-LABEL: 'no_pairwise_reduction4i32'
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx, %rdx.shuf
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %bin.rdx, %rdx.shuf7
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
; CHECK-LABEL: 'no_pairwise_reduction4i32'
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx, %rdx.shuf
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %bin.rdx, %rdx.shuf7
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
%rdx.shuf = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
||||
%bin.rdx = add <4 x i32> %rdx, %rdx.shuf
|
||||
|
|
@ -578,7 +542,7 @@ define fastcc i16 @no_pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <8 x i16> %bin.rdx4, %rdx.shuf
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %rdx.shuf7 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <8 x i16> %bin.rdx, %rdx.shuf7
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %r = extractelement <8 x i16> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x i16> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
|
||||
;
|
||||
; SSSE3-LABEL: 'no_pairwise_reduction8i16'
|
||||
|
|
@ -588,7 +552,7 @@ define fastcc i16 @no_pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <8 x i16> %bin.rdx4, %rdx.shuf
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <8 x i16> %bin.rdx, %rdx.shuf7
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i16> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x i16> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
|
||||
;
|
||||
; SSE42-LABEL: 'no_pairwise_reduction8i16'
|
||||
|
|
@ -669,14 +633,14 @@ define fastcc double @pairwise_reduction2double(<2 x double> %rdx, double %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <2 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
|
||||
;
|
||||
; SSSE3-LABEL: 'pairwise_reduction2double'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <2 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
|
||||
;
|
||||
; SSE42-LABEL: 'pairwise_reduction2double'
|
||||
|
|
@ -709,7 +673,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
|
||||
;
|
||||
; SSSE3-LABEL: 'pairwise_reduction4float'
|
||||
|
|
@ -719,7 +683,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
|
||||
;
|
||||
; SSE42-LABEL: 'pairwise_reduction4float'
|
||||
|
|
@ -761,7 +725,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
|
||||
;
|
||||
; SSSE3-LABEL: 'pairwise_reduction4double'
|
||||
|
|
@ -771,7 +735,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
|
||||
;
|
||||
; SSE42-LABEL: 'pairwise_reduction4double'
|
||||
|
|
@ -826,7 +790,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
|
||||
;
|
||||
; SSSE3-LABEL: 'pairwise_reduction8float'
|
||||
|
|
@ -839,7 +803,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
|
||||
;
|
||||
; SSE42-LABEL: 'pairwise_reduction8float'
|
||||
|
|
@ -896,26 +860,12 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
|
|||
}
|
||||
|
||||
define fastcc i64 @pairwise_reduction2i64(<2 x i64> %rdx, i64 %f1) {
|
||||
; SSE2-LABEL: 'pairwise_reduction2i64'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
|
||||
;
|
||||
; SSSE3-LABEL: 'pairwise_reduction2i64'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
|
||||
;
|
||||
; SSE42-LABEL: 'pairwise_reduction2i64'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
|
||||
; SSE-LABEL: 'pairwise_reduction2i64'
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
|
||||
;
|
||||
; AVX-LABEL: 'pairwise_reduction2i64'
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
|
||||
|
|
@ -933,45 +883,15 @@ define fastcc i64 @pairwise_reduction2i64(<2 x i64> %rdx, i64 %f1) {
|
|||
}
|
||||
|
||||
define fastcc i32 @pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) {
|
||||
; SSE2-LABEL: 'pairwise_reduction4i32'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; SSSE3-LABEL: 'pairwise_reduction4i32'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; SSE42-LABEL: 'pairwise_reduction4i32'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; AVX-LABEL: 'pairwise_reduction4i32'
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
; CHECK-LABEL: 'pairwise_reduction4i32'
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
%rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
|
||||
%rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
|
||||
|
|
@ -1037,7 +957,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
|
|||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx9 = add <8 x i16> %rdx.shuf.2.0, %rdx.shuf.2.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
|
||||
;
|
||||
; SSSE3-LABEL: 'pairwise_reduction8i16'
|
||||
|
|
@ -1050,7 +970,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
|
|||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx9 = add <8 x i16> %rdx.shuf.2.0, %rdx.shuf.2.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
|
||||
;
|
||||
; SSE42-LABEL: 'pairwise_reduction8i16'
|
||||
|
|
@ -1094,44 +1014,18 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
|
|||
}
|
||||
|
||||
define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
|
||||
; SSE2-LABEL: 'pairwise_reduction8i32'
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
|
||||
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; SSSE3-LABEL: 'pairwise_reduction8i32'
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
|
||||
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; SSE42-LABEL: 'pairwise_reduction8i32'
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
|
||||
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
; SSE-LABEL: 'pairwise_reduction8i32'
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
|
||||
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
|
||||
;
|
||||
; AVX1-LABEL: 'pairwise_reduction8i32'
|
||||
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
|
|
|
|||
|
|
@ -120,7 +120,7 @@ for.body: ; preds = %for.body, %entry
|
|||
; YAML-NEXT: Function: foo
|
||||
; YAML-NEXT: Args:
|
||||
; YAML-NEXT: - String: 'Vectorized horizontal reduction with cost '
|
||||
; YAML-NEXT: - Cost: '-2'
|
||||
; YAML-NEXT: - Cost: '-4'
|
||||
; YAML-NEXT: - String: ' and with tree size '
|
||||
; YAML-NEXT: - TreeSize: '1'
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue