[llvm] f4c67df - [X86] More accurately model the cost of horizontal reductions.
Craig Topper via llvm-commits
llvm-commits at lists.llvm.org
Sun Mar 22 14:20:33 PDT 2020
Author: Craig Topper
Date: 2020-03-22T14:20:15-07:00
New Revision: f4c67dfa925a6735fb31edf9d06f4a8e6e1cc812
URL: https://github.com/llvm/llvm-project/commit/f4c67dfa925a6735fb31edf9d06f4a8e6e1cc812
DIFF: https://github.com/llvm/llvm-project/commit/f4c67dfa925a6735fb31edf9d06f4a8e6e1cc812.diff
LOG: [X86] More accurately model the cost of horizontal reductions.
This patch attempts to more accurately model the reduction of
power of 2 vectors of types we natively support. This takes into
account the narrowing of vectors that occur as we go from 512
bits to 256 bits, to 128 bits. It also takes into account the use
of wider elements in the shuffles for the first 2 steps of a
reduction from 128 bits. And uses a v8i16 shift for the final step
of vXi8 reduction.
The default implementation uses the legalized type for the arithmetic
for all levels. And uses the single source permute cost of the
legalized type for all levels. This penalizes things like
lack of v16i8 pshufb on pre-sse3 targets and the splitting and
joining that needs to be done for integer types on AVX1. We never
need v16i8 shuffle for a reduction and we only need split AVX1 ops
when type the type wide and needs to be split. I think we're still
over costing splits and joins for AVX1, but we're closer now.
I've also removed all pairwise special casing because I don't
think we ever want to generate that on X86. I've also adjusted
the add handling to more accurately account for any type splitting
that occurs before we reach a legal type.
Differential Revision: https://reviews.llvm.org/D76478
Added:
Modified:
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/X86/reduce-add.ll
llvm/test/Analysis/CostModel/X86/reduce-and.ll
llvm/test/Analysis/CostModel/X86/reduce-mul.ll
llvm/test/Analysis/CostModel/X86/reduce-or.ll
llvm/test/Analysis/CostModel/X86/reduce-xor.ll
llvm/test/Analysis/CostModel/X86/reduction.ll
llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 8ae5749cd06c..3fc61541d511 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -2648,39 +2648,13 @@ int X86TTIImpl::getAddressComputationCost(Type *Ty, ScalarEvolution *SE,
int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
bool IsPairwise) {
+ // Just use the default implementation for pair reductions.
+ if (IsPairwise)
+ return BaseT::getArithmeticReductionCost(Opcode, ValTy, IsPairwise);
+
// We use the Intel Architecture Code Analyzer(IACA) to measure the throughput
// and make it as the cost.
- static const CostTblEntry SLMCostTblPairWise[] = {
- { ISD::FADD, MVT::v2f64, 3 },
- { ISD::ADD, MVT::v2i64, 5 },
- };
-
- 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".
- { 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::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::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::v4i64, 5 }, // The data reported by the IACA tool is "4.8".
- { ISD::ADD, MVT::v8i32, 5 },
- { ISD::ADD, MVT::v16i16, 6 },
- { ISD::ADD, MVT::v32i8, 4 },
- };
-
static const CostTblEntry SLMCostTblNoPairWise[] = {
{ ISD::FADD, MVT::v2f64, 3 },
{ ISD::ADD, MVT::v2i64, 5 },
@@ -2721,62 +2695,44 @@ int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
EVT VT = TLI->getValueType(DL, ValTy);
if (VT.isSimple()) {
MVT MTy = VT.getSimpleVT();
- if (IsPairwise) {
- if (ST->isSLM())
- if (const auto *Entry = CostTableLookup(SLMCostTblPairWise, ISD, MTy))
- return Entry->Cost;
-
- if (ST->hasAVX())
- if (const auto *Entry = CostTableLookup(AVX1CostTblPairWise, ISD, MTy))
- return Entry->Cost;
-
- if (ST->hasSSE2())
- if (const auto *Entry = CostTableLookup(SSE2CostTblPairWise, ISD, MTy))
- return Entry->Cost;
- } else {
- if (ST->isSLM())
- if (const auto *Entry = CostTableLookup(SLMCostTblNoPairWise, ISD, MTy))
- return Entry->Cost;
+ if (ST->isSLM())
+ if (const auto *Entry = CostTableLookup(SLMCostTblNoPairWise, ISD, MTy))
+ return Entry->Cost;
- if (ST->hasAVX())
- if (const auto *Entry = CostTableLookup(AVX1CostTblNoPairWise, ISD, MTy))
- return Entry->Cost;
+ if (ST->hasAVX())
+ if (const auto *Entry = CostTableLookup(AVX1CostTblNoPairWise, ISD, MTy))
+ return Entry->Cost;
- if (ST->hasSSE2())
- if (const auto *Entry = CostTableLookup(SSE2CostTblNoPairWise, ISD, MTy))
- return Entry->Cost;
- }
+ if (ST->hasSSE2())
+ if (const auto *Entry = CostTableLookup(SSE2CostTblNoPairWise, ISD, MTy))
+ return Entry->Cost;
}
std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, ValTy);
MVT MTy = LT.second;
- if (IsPairwise) {
- if (ST->isSLM())
- if (const auto *Entry = CostTableLookup(SLMCostTblPairWise, ISD, MTy))
- return LT.first * Entry->Cost;
-
- if (ST->hasAVX())
- if (const auto *Entry = CostTableLookup(AVX1CostTblPairWise, ISD, MTy))
- return LT.first * Entry->Cost;
+ unsigned ArithmeticCost = 0;
+ if (LT.first != 1 && MTy.isVector() &&
+ MTy.getVectorNumElements() < ValTy->getVectorNumElements()) {
+ // Type needs to be split. We need LT.first - 1 arithmetic ops.
+ Type *SingleOpTy = VectorType::get(ValTy->getVectorElementType(),
+ MTy.getVectorNumElements());
+ ArithmeticCost = getArithmeticInstrCost(Opcode, SingleOpTy);
+ ArithmeticCost *= LT.first - 1;
+ }
- if (ST->hasSSE2())
- if (const auto *Entry = CostTableLookup(SSE2CostTblPairWise, ISD, MTy))
- return LT.first * Entry->Cost;
- } else {
- if (ST->isSLM())
- if (const auto *Entry = CostTableLookup(SLMCostTblNoPairWise, ISD, MTy))
- return LT.first * Entry->Cost;
+ if (ST->isSLM())
+ if (const auto *Entry = CostTableLookup(SLMCostTblNoPairWise, ISD, MTy))
+ return ArithmeticCost + Entry->Cost;
- if (ST->hasAVX())
- if (const auto *Entry = CostTableLookup(AVX1CostTblNoPairWise, ISD, MTy))
- return LT.first * Entry->Cost;
+ if (ST->hasAVX())
+ if (const auto *Entry = CostTableLookup(AVX1CostTblNoPairWise, ISD, MTy))
+ return ArithmeticCost + Entry->Cost;
- if (ST->hasSSE2())
- if (const auto *Entry = CostTableLookup(SSE2CostTblNoPairWise, ISD, MTy))
- return LT.first * Entry->Cost;
- }
+ if (ST->hasSSE2())
+ if (const auto *Entry = CostTableLookup(SSE2CostTblNoPairWise, ISD, MTy))
+ return ArithmeticCost + Entry->Cost;
// FIXME: These assume a naive kshift+binop lowering, which is probably
// conservative in most cases.
@@ -2825,9 +2781,9 @@ int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
};
// Handle bool allof/anyof patterns.
- if (!IsPairwise && ValTy->getVectorElementType()->isIntegerTy(1)) {
+ if (ValTy->getVectorElementType()->isIntegerTy(1)) {
unsigned ArithmeticCost = 0;
- if (MTy.isVector() &&
+ if (LT.first != 1 && MTy.isVector() &&
MTy.getVectorNumElements() < ValTy->getVectorNumElements()) {
// Type needs to be split. We need LT.first - 1 arithmetic ops.
Type *SingleOpTy = VectorType::get(ValTy->getVectorElementType(),
@@ -2848,9 +2804,77 @@ int X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, Type *ValTy,
if (ST->hasSSE2())
if (const auto *Entry = CostTableLookup(SSE2BoolReduction, ISD, MTy))
return ArithmeticCost + Entry->Cost;
+
+ return BaseT::getArithmeticReductionCost(Opcode, ValTy, IsPairwise);
+ }
+
+ unsigned NumVecElts = ValTy->getVectorNumElements();
+ unsigned ScalarSize = ValTy->getScalarSizeInBits();
+
+ // Special case power of 2 reductions where the scalar type isn't changed
+ // by type legalization.
+ if (!isPowerOf2_32(NumVecElts) || ScalarSize != MTy.getScalarSizeInBits())
+ return BaseT::getArithmeticReductionCost(Opcode, ValTy, IsPairwise);
+
+ unsigned ReductionCost = 0;
+
+ Type *Ty = ValTy;
+ if (LT.first != 1 && MTy.isVector() &&
+ MTy.getVectorNumElements() < ValTy->getVectorNumElements()) {
+ // Type needs to be split. We need LT.first - 1 arithmetic ops.
+ Ty = VectorType::get(ValTy->getVectorElementType(),
+ MTy.getVectorNumElements());
+ ReductionCost = getArithmeticInstrCost(Opcode, Ty);
+ ReductionCost *= LT.first - 1;
+ NumVecElts = MTy.getVectorNumElements();
+ }
+
+ // Now handle reduction with the legal type, taking into account size changes
+ // at each level.
+ while (NumVecElts > 1) {
+ // Determine the size of the remaining vector we need to reduce.
+ unsigned Size = NumVecElts * ScalarSize;
+ NumVecElts /= 2;
+ // If we're reducing from 256/512 bits, use an extract_subvector.
+ if (Size > 128) {
+ Type *SubTy = VectorType::get(ValTy->getVectorElementType(), NumVecElts);
+ ReductionCost +=
+ getShuffleCost(TTI::SK_ExtractSubvector, Ty, NumVecElts, SubTy);
+ Ty = SubTy;
+ } else if (Size == 128) {
+ // Reducing from 128 bits is a permute of v2f64/v2i64.
+ Type *ShufTy;
+ if (ValTy->isFloatingPointTy())
+ ShufTy = VectorType::get(Type::getDoubleTy(ValTy->getContext()), 2);
+ else
+ ShufTy = VectorType::get(Type::getInt64Ty(ValTy->getContext()), 2);
+ ReductionCost +=
+ getShuffleCost(TTI::SK_PermuteSingleSrc, ShufTy, 0, nullptr);
+ } else if (Size == 64) {
+ // Reducing from 64 bits is a shuffle of v4f32/v4i32.
+ Type *ShufTy;
+ if (ValTy->isFloatingPointTy())
+ ShufTy = VectorType::get(Type::getFloatTy(ValTy->getContext()), 4);
+ else
+ ShufTy = VectorType::get(Type::getInt32Ty(ValTy->getContext()), 4);
+ ReductionCost +=
+ getShuffleCost(TTI::SK_PermuteSingleSrc, ShufTy, 0, nullptr);
+ } else {
+ // Reducing from smaller size is a shift by immediate.
+ Type *ShiftTy = VectorType::get(
+ Type::getIntNTy(ValTy->getContext(), Size), 128 / Size);
+ ReductionCost += getArithmeticInstrCost(
+ Instruction::LShr, ShiftTy, TargetTransformInfo::OK_AnyValue,
+ TargetTransformInfo::OK_UniformConstantValue,
+ TargetTransformInfo::OP_None, TargetTransformInfo::OP_None);
+ }
+
+ // Add the arithmetic op for this level.
+ ReductionCost += getArithmeticInstrCost(Opcode, Ty);
}
- return BaseT::getArithmeticReductionCost(Opcode, ValTy, IsPairwise);
+ // Add the final extract element to the cost.
+ return ReductionCost + getVectorInstrCost(Instruction::ExtractElement, Ty, 0);
}
int X86TTIImpl::getMinMaxReductionCost(Type *ValTy, Type *CondTy,
diff --git a/llvm/test/Analysis/CostModel/X86/reduce-add.ll b/llvm/test/Analysis/CostModel/X86/reduce-add.ll
index b5729eac4bc4..0b0e78059bc6 100644
--- a/llvm/test/Analysis/CostModel/X86/reduce-add.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduce-add.ll
@@ -14,18 +14,26 @@ define i32 @reduce_i64(i32 %arg) {
; 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 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 9 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)
-; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef)
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
-; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
-; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
-; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX1-LABEL: 'reduce_i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX2-LABEL: 'reduce_i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_i64'
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
@@ -38,9 +46,9 @@ define i32 @reduce_i64(i32 %arg) {
; SLM-LABEL: 'reduce_i64'
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef)
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef)
@@ -55,18 +63,26 @@ define i32 @reduce_i32(i32 %arg) {
; 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 4 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 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)
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef)
-; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
-; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
-; AVX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
-; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX1-LABEL: 'reduce_i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX2-LABEL: 'reduce_i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_i32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
@@ -79,9 +95,9 @@ define i32 @reduce_i32(i32 %arg) {
; SLM-LABEL: 'reduce_i32'
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef)
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef)
@@ -97,27 +113,36 @@ define i32 @reduce_i16(i32 %arg) {
; 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 5 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 11 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
;
-; 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
+; 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 5 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 17 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 5 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 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
;
; 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 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 6 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 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'
@@ -134,17 +159,17 @@ define i32 @reduce_i16(i32 %arg) {
; 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 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 6 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 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
;
; SLM-LABEL: 'reduce_i16'
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef)
; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef)
; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef)
; SLM-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)
@@ -162,20 +187,30 @@ define i32 @reduce_i8(i32 %arg) {
; 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 4 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 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
;
-; 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
+; AVX1-LABEL: 'reduce_i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 16 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 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 7 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
;
; AVX512F-LABEL: 'reduce_i8'
; 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)
@@ -183,8 +218,8 @@ define i32 @reduce_i8(i32 %arg) {
; 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 5 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 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'
@@ -193,8 +228,8 @@ define i32 @reduce_i8(i32 %arg) {
; 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 13 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 14 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'
@@ -203,8 +238,8 @@ define i32 @reduce_i8(i32 %arg) {
; 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 5 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 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
;
; SLM-LABEL: 'reduce_i8'
@@ -212,9 +247,9 @@ define i32 @reduce_i8(i32 %arg) {
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef)
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef)
; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
-; SLM-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef)
+; SLM-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef)
; SLM-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)
diff --git a/llvm/test/Analysis/CostModel/X86/reduce-and.ll b/llvm/test/Analysis/CostModel/X86/reduce-and.ll
index 9a558118e4ce..0943984167e1 100644
--- a/llvm/test/Analysis/CostModel/X86/reduce-and.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduce-and.ll
@@ -17,21 +17,13 @@ define i32 @reduce_i64(i32 %arg) {
; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.v16i64(<16 x i64> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
-; AVX1-LABEL: 'reduce_i64'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.v1i64(<1 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.v2i64(<2 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.v4i64(<4 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.v8i64(<8 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.v16i64(<16 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'reduce_i64'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.v1i64(<1 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.v2i64(<2 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.v4i64(<4 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.v8i64(<8 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.v16i64(<16 x i64> undef)
-; AVX2-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.and.v1i64(<1 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.v2i64(<2 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.v4i64(<4 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.v8i64(<8 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.v16i64(<16 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_i64'
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.v1i64(<1 x i64> undef)
@@ -58,21 +50,13 @@ define i32 @reduce_i32(i32 %arg) {
; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.v32i32(<32 x i32> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
-; AVX1-LABEL: 'reduce_i32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.v2i32(<2 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.v4i32(<4 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.v8i32(<8 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.v16i32(<16 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.v32i32(<32 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'reduce_i32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.v2i32(<2 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.v4i32(<4 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.v8i32(<8 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.v16i32(<16 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.v32i32(<32 x i32> undef)
-; AVX2-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 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.v2i32(<2 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.v4i32(<4 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.v8i32(<8 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.v16i32(<16 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.v32i32(<32 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_i32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.v2i32(<2 x i32> undef)
@@ -91,58 +75,31 @@ 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.and.v2i16(<2 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.v64i16(<64 x i16> undef)
-; SSE2-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.and.v2i16(<2 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.v2i16(<2 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.v2i16(<2 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.v64i16(<64 x i16> undef)
-; AVX1-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.v2i16(<2 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.v64i16(<64 x i16> undef)
+; SSE-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.v2i16(<2 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.v2i16(<2 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.v2i16(<2 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.v64i16(<64 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.v64i16(<64 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i16'
@@ -158,9 +115,9 @@ define i32 @reduce_i16(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.v2i16(<2 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.v4i16(<4 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.v8i16(<8 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.v16i16(<16 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.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.and.v2i16(<2 x i16> undef)
@@ -173,64 +130,34 @@ 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.and.v2i8(<2 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.v128i8(<128 x i8> undef)
-; SSE2-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.and.v2i8(<2 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.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.and.v2i8(<2 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.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.and.v2i8(<2 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.v128i8(<128 x i8> undef)
-; AVX1-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 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.v2i8(<2 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.v128i8(<128 x i8> undef)
+; SSE-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.and.v2i8(<2 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.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 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.v2i8(<2 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.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.and.v2i8(<2 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.v128i8(<128 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.v128i8(<128 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i8'
@@ -238,9 +165,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.v128i8(<128 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'reduce_i8'
@@ -248,9 +175,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.v4i8(<4 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.v8i8(<8 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.v16i8(<16 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.v32i8(<32 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.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.and.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/X86/reduce-mul.ll b/llvm/test/Analysis/CostModel/X86/reduce-mul.ll
index 42c9b5cedf4a..bbf57578e694 100644
--- a/llvm/test/Analysis/CostModel/X86/reduce-mul.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduce-mul.ll
@@ -20,9 +20,9 @@ define i32 @reduce_i64(i32 %arg) {
; AVX1-LABEL: 'reduce_i64'
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.v1i64(<1 x i64> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.v2i64(<2 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.v4i64(<4 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.v8i64(<8 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 95 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.v16i64(<16 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.v4i64(<4 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.v8i64(<8 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 73 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.v16i64(<16 x i64> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'reduce_i64'
@@ -93,9 +93,9 @@ define i32 @reduce_i32(i32 %arg) {
; AVX1-LABEL: 'reduce_i32'
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.v2i32(<2 x i32> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.v4i32(<4 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.v8i32(<8 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.v16i32(<16 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.v32i32(<32 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.v8i32(<8 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.v16i32(<16 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.v32i32(<32 x i32> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'reduce_i32'
@@ -123,58 +123,40 @@ 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.mul.v2i16(<2 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.v4i16(<4 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.v8i16(<8 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
-; SSE2-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.mul.v2i16(<2 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.v4i16(<4 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.v8i16(<8 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.v2i16(<2 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.v4i16(<4 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.v8i16(<8 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
-; SSE42-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.v2i16(<2 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.v4i16(<4 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.v8i16(<8 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
+; SSE-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.v2i16(<2 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.v4i16(<4 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.v8i16(<8 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.v2i16(<2 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.v4i16(<4 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.v8i16(<8 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
; AVX2-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.v2i16(<2 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.v4i16(<4 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.v8i16(<8 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i16'
@@ -190,9 +172,9 @@ define i32 @reduce_i16(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.v2i16(<2 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.v4i16(<4 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.v8i16(<8 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.v16i16(<16 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.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.mul.v2i16(<2 x i16> undef)
@@ -205,44 +187,24 @@ 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 23 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.v2i8(<2 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 101 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 173 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
-; SSE2-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 14 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.v2i8(<2 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.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 14 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.v2i8(<2 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
-; SSE42-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 14 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.v2i8(<2 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
+; SSE-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 14 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.v2i8(<2 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 171 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 197 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 249 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'reduce_i8'
@@ -250,9 +212,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 123 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 157 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'reduce_i8'
@@ -260,9 +222,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i8'
@@ -270,9 +232,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 115 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'reduce_i8'
@@ -280,9 +242,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.v4i8(<4 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.v8i8(<8 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.v16i8(<16 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.v32i8(<32 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.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.mul.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/X86/reduce-or.ll b/llvm/test/Analysis/CostModel/X86/reduce-or.ll
index 011a6cc1d051..8bdf419c13ba 100644
--- a/llvm/test/Analysis/CostModel/X86/reduce-or.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduce-or.ll
@@ -17,21 +17,13 @@ define i32 @reduce_i64(i32 %arg) {
; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.v16i64(<16 x i64> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
-; AVX1-LABEL: 'reduce_i64'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.v1i64(<1 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.v2i64(<2 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.v4i64(<4 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.v8i64(<8 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.v16i64(<16 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'reduce_i64'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.v1i64(<1 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.v2i64(<2 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.v4i64(<4 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.v8i64(<8 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.v16i64(<16 x i64> undef)
-; AVX2-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.or.v1i64(<1 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.v2i64(<2 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.v4i64(<4 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.v8i64(<8 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.v16i64(<16 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_i64'
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.v1i64(<1 x i64> undef)
@@ -58,21 +50,13 @@ define i32 @reduce_i32(i32 %arg) {
; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.v32i32(<32 x i32> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
-; AVX1-LABEL: 'reduce_i32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.v2i32(<2 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.v4i32(<4 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.v8i32(<8 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.v16i32(<16 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.v32i32(<32 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'reduce_i32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.v2i32(<2 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.v4i32(<4 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.v8i32(<8 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.v16i32(<16 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.v32i32(<32 x i32> undef)
-; AVX2-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 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.v2i32(<2 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.v4i32(<4 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.v8i32(<8 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.v16i32(<16 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.v32i32(<32 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_i32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.v2i32(<2 x i32> undef)
@@ -91,58 +75,31 @@ 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.or.v2i16(<2 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.v64i16(<64 x i16> undef)
-; SSE2-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.or.v2i16(<2 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.v2i16(<2 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.v2i16(<2 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.v64i16(<64 x i16> undef)
-; AVX1-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.v2i16(<2 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.v64i16(<64 x i16> undef)
+; SSE-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.v2i16(<2 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.v2i16(<2 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.v2i16(<2 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.v64i16(<64 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.v64i16(<64 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i16'
@@ -158,9 +115,9 @@ define i32 @reduce_i16(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.v2i16(<2 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.v4i16(<4 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.v8i16(<8 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.v16i16(<16 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.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.or.v2i16(<2 x i16> undef)
@@ -173,64 +130,34 @@ 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.or.v2i8(<2 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.v128i8(<128 x i8> undef)
-; SSE2-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.or.v2i8(<2 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.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.or.v2i8(<2 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.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.or.v2i8(<2 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.v128i8(<128 x i8> undef)
-; AVX1-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 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.v2i8(<2 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.v128i8(<128 x i8> undef)
+; SSE-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.or.v2i8(<2 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.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 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.v2i8(<2 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.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.or.v2i8(<2 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.v128i8(<128 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.v128i8(<128 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i8'
@@ -238,9 +165,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.v128i8(<128 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'reduce_i8'
@@ -248,9 +175,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.v4i8(<4 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.v8i8(<8 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.v16i8(<16 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.v32i8(<32 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.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.or.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/X86/reduce-xor.ll b/llvm/test/Analysis/CostModel/X86/reduce-xor.ll
index df927b436ac1..679cd3368b50 100644
--- a/llvm/test/Analysis/CostModel/X86/reduce-xor.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduce-xor.ll
@@ -17,21 +17,13 @@ define i32 @reduce_i64(i32 %arg) {
; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.v16i64(<16 x i64> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
-; AVX1-LABEL: 'reduce_i64'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.v1i64(<1 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.v2i64(<2 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.v4i64(<4 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.v8i64(<8 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.v16i64(<16 x i64> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'reduce_i64'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.v1i64(<1 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.v2i64(<2 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.v4i64(<4 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.v8i64(<8 x i64> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.v16i64(<16 x i64> undef)
-; AVX2-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.xor.v1i64(<1 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.v2i64(<2 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.v4i64(<4 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.v8i64(<8 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.v16i64(<16 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_i64'
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.v1i64(<1 x i64> undef)
@@ -58,21 +50,13 @@ define i32 @reduce_i32(i32 %arg) {
; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.v32i32(<32 x i32> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
-; AVX1-LABEL: 'reduce_i32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.v2i32(<2 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.v4i32(<4 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.v8i32(<8 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.v16i32(<16 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.v32i32(<32 x i32> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'reduce_i32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.v2i32(<2 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.v4i32(<4 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.v8i32(<8 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.v16i32(<16 x i32> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.v32i32(<32 x i32> undef)
-; AVX2-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 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.v2i32(<2 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.v4i32(<4 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.v8i32(<8 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.v16i32(<16 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.v32i32(<32 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_i32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.v2i32(<2 x i32> undef)
@@ -91,58 +75,31 @@ 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.xor.v2i16(<2 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.v64i16(<64 x i16> undef)
-; SSE2-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.xor.v2i16(<2 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.v2i16(<2 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.v2i16(<2 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.v64i16(<64 x i16> undef)
-; AVX1-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.v2i16(<2 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.v64i16(<64 x i16> undef)
+; SSE-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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.v2i16(<2 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.v2i16(<2 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.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 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.v2i16(<2 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.v64i16(<64 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.v64i16(<64 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i16'
@@ -158,9 +115,9 @@ define i32 @reduce_i16(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.v2i16(<2 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.v4i16(<4 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.v8i16(<8 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.v16i16(<16 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.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.xor.v2i16(<2 x i16> undef)
@@ -173,64 +130,34 @@ 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.xor.v2i8(<2 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.v128i8(<128 x i8> undef)
-; SSE2-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.xor.v2i8(<2 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.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.xor.v2i8(<2 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.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.xor.v2i8(<2 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.v128i8(<128 x i8> undef)
-; AVX1-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 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.v2i8(<2 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.v128i8(<128 x i8> undef)
+; SSE-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.xor.v2i8(<2 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.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 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.v2i8(<2 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.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.xor.v2i8(<2 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.v128i8(<128 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.v128i8(<128 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i8'
@@ -238,9 +165,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.v128i8(<128 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'reduce_i8'
@@ -248,9 +175,9 @@ define i32 @reduce_i8(i32 %arg) {
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.v4i8(<4 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.v8i8(<8 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.v16i8(<16 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.v32i8(<32 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.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.xor.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/X86/reduction.ll b/llvm/test/Analysis/CostModel/X86/reduction.ll
index ac373020532b..1812a074f86b 100644
--- a/llvm/test/Analysis/CostModel/X86/reduction.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduction.ll
@@ -69,7 +69,7 @@ define fastcc i32 @reduction_cost_int(<8 x i32> %rdx) {
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <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.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3
-; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
; AVX1-LABEL: 'reduction_cost_int'
@@ -99,7 +99,7 @@ define fastcc i32 @reduction_cost_int(<8 x i32> %rdx) {
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2
; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3
-; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
%rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef,
@@ -127,7 +127,7 @@ 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 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; 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 2 for instruction: %r2 = fadd float %r, %f1
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -138,7 +138,7 @@ 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 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; 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 2 for instruction: %r2 = fadd float %r, %f1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -149,7 +149,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
; SSE42-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>
; SSE42-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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -160,7 +160,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
; AVX-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>
; AVX-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>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -171,7 +171,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
; SLM-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>
; SLM-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>
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -199,7 +199,7 @@ 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 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; 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 2 for instruction: %r2 = fadd float %r, %f1
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -210,7 +210,7 @@ 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 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; 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 2 for instruction: %r2 = fadd float %r, %f1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -221,7 +221,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
; SSE42-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>
; SSE42-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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -232,7 +232,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
; AVX-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>
; AVX-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>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -243,7 +243,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
; SLM-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>
; SLM-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>
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -270,7 +270,7 @@ 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 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; 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 2 for instruction: %r2 = fadd float %r, %f1
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -280,7 +280,7 @@ 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 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; 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 2 for instruction: %r2 = fadd float %r, %f1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -290,7 +290,7 @@ define fastcc float @pairwise_hadd_skip_first(<4 x float> %rdx, float %f1) {
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSE42-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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %bin.rdx.0, %rdx.shuf.1.1
-; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -300,7 +300,7 @@ define fastcc float @pairwise_hadd_skip_first(<4 x float> %rdx, float %f1) {
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; AVX-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>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %bin.rdx.0, %rdx.shuf.1.1
-; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -310,7 +310,7 @@ define fastcc float @pairwise_hadd_skip_first(<4 x float> %rdx, float %f1) {
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; SLM-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>
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %bin.rdx.0, %rdx.shuf.1.1
-; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2
;
@@ -438,7 +438,7 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf
; SSE42-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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7
-; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
;
; AVX1-LABEL: 'no_pairwise_reduction4double'
@@ -462,7 +462,7 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1
; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf
; SLM-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>
; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7
-; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
;
%rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
@@ -482,7 +482,7 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <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.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7
-; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 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_reduction8float'
@@ -492,7 +492,7 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <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.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 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_reduction8float'
@@ -502,7 +502,7 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> 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.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7
-; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
; AVX1-LABEL: 'no_pairwise_reduction8float'
@@ -532,7 +532,7 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf
; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7
-; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
%rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7,i32 undef, i32 undef, i32 undef, i32 undef>
@@ -604,7 +604,7 @@ define fastcc i64 @no_pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7
-; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
; AVX1-LABEL: 'no_pairwise_reduction4i64'
@@ -628,7 +628,7 @@ define fastcc i64 @no_pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7
-; SLM-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
%rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
@@ -710,7 +710,7 @@ define fastcc i32 @no_pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <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.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7
-; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
; AVX1-LABEL: 'no_pairwise_reduction8i32'
@@ -740,7 +740,7 @@ define fastcc i32 @no_pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf
; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7
-; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
%rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7,i32 undef, i32 undef, i32 undef, i32 undef>
@@ -759,14 +759,14 @@ 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 2 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
+; 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 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 2 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
+; 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 0 for instruction: ret double %r
;
; SSE42-LABEL: 'pairwise_reduction2double'
@@ -806,7 +806,7 @@ 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 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
+; 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 0 for instruction: ret float %r
;
; SSSE3-LABEL: 'pairwise_reduction4float'
@@ -816,7 +816,7 @@ 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 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
+; 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 0 for instruction: ret float %r
;
; SSE42-LABEL: 'pairwise_reduction4float'
@@ -826,7 +826,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
; SSE42-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>
; SSE42-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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
; AVX-LABEL: 'pairwise_reduction4float'
@@ -836,7 +836,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
; AVX-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>
; AVX-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>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
; SLM-LABEL: 'pairwise_reduction4float'
@@ -846,7 +846,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
; SLM-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>
; SLM-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>
; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
%rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
@@ -868,7 +868,7 @@ 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 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; 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 0 for instruction: ret double %r
;
; SSSE3-LABEL: 'pairwise_reduction4double'
@@ -878,7 +878,7 @@ 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 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; 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 0 for instruction: ret double %r
;
; SSE42-LABEL: 'pairwise_reduction4double'
@@ -888,7 +888,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; SSE42-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>
; SSE42-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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
;
; AVX1-LABEL: 'pairwise_reduction4double'
@@ -898,7 +898,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; AVX1-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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
;
; AVX2-LABEL: 'pairwise_reduction4double'
@@ -918,7 +918,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; SLM-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>
; SLM-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>
; SLM-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
-; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
;
%rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
@@ -943,7 +943,7 @@ 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 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
+; 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 0 for instruction: ret float %r
;
; SSSE3-LABEL: 'pairwise_reduction8float'
@@ -956,7 +956,7 @@ 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 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
+; 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 0 for instruction: ret float %r
;
; SSE42-LABEL: 'pairwise_reduction8float'
@@ -969,7 +969,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; SSE42-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>
; SSE42-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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
-; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
; AVX1-LABEL: 'pairwise_reduction8float'
@@ -982,7 +982,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; AVX1-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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
-; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
; AVX2-LABEL: 'pairwise_reduction8float'
@@ -995,7 +995,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; AVX2-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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
; SLM-LABEL: 'pairwise_reduction8float'
@@ -1008,7 +1008,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; SLM-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>
; SLM-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>
; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
-; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
%rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6,i32 undef, i32 undef, i32 undef, i32 undef>
@@ -1026,25 +1026,18 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
}
define fastcc i64 @pairwise_reduction2i64(<2 x i64> %rdx, i64 %f1) {
-; 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>
-; AVX-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>
-; AVX-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
-; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
-; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
+; CHECK-LABEL: 'pairwise_reduction2i64'
+; CHECK-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>
+; CHECK-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>
+; CHECK-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
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
; SLM-LABEL: 'pairwise_reduction2i64'
; SLM-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>
; SLM-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>
; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
%rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
@@ -1063,7 +1056,7 @@ define fastcc i32 @pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) {
; 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 6 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
;
; SLM-LABEL: 'pairwise_reduction4i32'
@@ -1073,7 +1066,7 @@ define fastcc i32 @pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) {
; SLM-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>
; SLM-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>
; SLM-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
-; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
; SLM-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>
@@ -1105,7 +1098,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
; AVX2-LABEL: 'pairwise_reduction4i64'
@@ -1115,7 +1108,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
; SLM-LABEL: 'pairwise_reduction4i64'
@@ -1150,7 +1143,7 @@ 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 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
+; 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 0 for instruction: ret i16 %r
;
; SSSE3-LABEL: 'pairwise_reduction8i16'
@@ -1163,7 +1156,7 @@ 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 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
+; 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 0 for instruction: ret i16 %r
;
; SSE42-LABEL: 'pairwise_reduction8i16'
@@ -1176,7 +1169,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
; SSE42-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>
; SSE42-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>
; SSE42-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
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
;
; AVX-LABEL: 'pairwise_reduction8i16'
@@ -1189,7 +1182,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
; AVX-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>
; AVX-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>
; AVX-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
-; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
;
; SLM-LABEL: 'pairwise_reduction8i16'
@@ -1202,7 +1195,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
; SLM-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>
; SLM-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>
; SLM-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
-; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
;
%rdx.shuf.0.0 = shufflevector <8 x i16> %rdx, <8 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6,i32 undef, i32 undef, i32 undef, i32 undef>
@@ -1230,7 +1223,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; 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 7 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'
@@ -1243,7 +1236,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; AVX1-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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
; AVX2-LABEL: 'pairwise_reduction8i32'
@@ -1256,7 +1249,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; AVX2-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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
; SLM-LABEL: 'pairwise_reduction8i32'
@@ -1269,7 +1262,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; SLM-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>
; SLM-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>
; SLM-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
-; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
%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>
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll b/llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll
index 7fdc95392235..dd1a210824d5 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll
@@ -69,31 +69,51 @@ entry:
; }
define i32 @test_mul(i32* nocapture readonly %p) {
-; CHECK-LABEL: @test_mul(
-; CHECK-NEXT: entry:
-; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[P:%.*]], align 4
-; CHECK-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
-; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX_1]], align 4
-; CHECK-NEXT: [[MUL_18:%.*]] = mul i32 [[TMP1]], [[TMP0]]
-; CHECK-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 2
-; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX_2]], align 4
-; CHECK-NEXT: [[MUL_29:%.*]] = mul i32 [[TMP2]], [[MUL_18]]
-; CHECK-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 3
-; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[ARRAYIDX_3]], align 4
-; CHECK-NEXT: [[MUL_310:%.*]] = mul i32 [[TMP3]], [[MUL_29]]
-; CHECK-NEXT: [[ARRAYIDX_4:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 4
-; CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX_4]], align 4
-; CHECK-NEXT: [[MUL_411:%.*]] = mul i32 [[TMP4]], [[MUL_310]]
-; CHECK-NEXT: [[ARRAYIDX_5:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 5
-; CHECK-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX_5]], align 4
-; CHECK-NEXT: [[MUL_512:%.*]] = mul i32 [[TMP5]], [[MUL_411]]
-; CHECK-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 6
-; CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* [[ARRAYIDX_6]], align 4
-; CHECK-NEXT: [[MUL_613:%.*]] = mul i32 [[TMP6]], [[MUL_512]]
-; CHECK-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 7
-; CHECK-NEXT: [[TMP7:%.*]] = load i32, i32* [[ARRAYIDX_7]], align 4
-; CHECK-NEXT: [[MUL_714:%.*]] = mul i32 [[TMP7]], [[MUL_613]]
-; CHECK-NEXT: ret i32 [[MUL_714]]
+; AVX-LABEL: @test_mul(
+; AVX-NEXT: entry:
+; AVX-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
+; AVX-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 2
+; AVX-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 3
+; AVX-NEXT: [[ARRAYIDX_4:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 4
+; AVX-NEXT: [[ARRAYIDX_5:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 5
+; AVX-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 6
+; AVX-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 7
+; AVX-NEXT: [[TMP0:%.*]] = bitcast i32* [[P]] to <8 x i32>*
+; AVX-NEXT: [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* [[TMP0]], align 4
+; AVX-NEXT: [[RDX_SHUF:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
+; AVX-NEXT: [[BIN_RDX:%.*]] = mul <8 x i32> [[TMP1]], [[RDX_SHUF]]
+; AVX-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <8 x i32> [[BIN_RDX]], <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; AVX-NEXT: [[BIN_RDX2:%.*]] = mul <8 x i32> [[BIN_RDX]], [[RDX_SHUF1]]
+; AVX-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <8 x i32> [[BIN_RDX2]], <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; AVX-NEXT: [[BIN_RDX4:%.*]] = mul <8 x i32> [[BIN_RDX2]], [[RDX_SHUF3]]
+; AVX-NEXT: [[TMP2:%.*]] = extractelement <8 x i32> [[BIN_RDX4]], i32 0
+; AVX-NEXT: ret i32 [[TMP2]]
+;
+; SSE-LABEL: @test_mul(
+; SSE-NEXT: entry:
+; SSE-NEXT: [[TMP0:%.*]] = load i32, i32* [[P:%.*]], align 4
+; SSE-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
+; SSE-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX_1]], align 4
+; SSE-NEXT: [[MUL_18:%.*]] = mul i32 [[TMP1]], [[TMP0]]
+; SSE-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 2
+; SSE-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX_2]], align 4
+; SSE-NEXT: [[MUL_29:%.*]] = mul i32 [[TMP2]], [[MUL_18]]
+; SSE-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 3
+; SSE-NEXT: [[TMP3:%.*]] = load i32, i32* [[ARRAYIDX_3]], align 4
+; SSE-NEXT: [[MUL_310:%.*]] = mul i32 [[TMP3]], [[MUL_29]]
+; SSE-NEXT: [[ARRAYIDX_4:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 4
+; SSE-NEXT: [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX_4]], align 4
+; SSE-NEXT: [[MUL_411:%.*]] = mul i32 [[TMP4]], [[MUL_310]]
+; SSE-NEXT: [[ARRAYIDX_5:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 5
+; SSE-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX_5]], align 4
+; SSE-NEXT: [[MUL_512:%.*]] = mul i32 [[TMP5]], [[MUL_411]]
+; SSE-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 6
+; SSE-NEXT: [[TMP6:%.*]] = load i32, i32* [[ARRAYIDX_6]], align 4
+; SSE-NEXT: [[MUL_613:%.*]] = mul i32 [[TMP6]], [[MUL_512]]
+; SSE-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 7
+; SSE-NEXT: [[TMP7:%.*]] = load i32, i32* [[ARRAYIDX_7]], align 4
+; SSE-NEXT: [[MUL_714:%.*]] = mul i32 [[TMP7]], [[MUL_613]]
+; SSE-NEXT: ret i32 [[MUL_714]]
;
entry:
%0 = load i32, i32* %p, align 4
More information about the llvm-commits
mailing list