[llvm] [AArch64][CostModel] Improve cost estimate of scalarizing a vector di… (PR #118055)
Sushant Gokhale via llvm-commits
llvm-commits at lists.llvm.org
Thu Nov 28 22:37:18 PST 2024
https://github.com/sushgokh created https://github.com/llvm/llvm-project/pull/118055
…vision
In the backend, last resort of finding the vector division cost is to use its scalar cost. However, without knowledge about the division operands, the cost can be off in certain cases.
For SLP, this patch tries to pass scalars for better scalar cost estimation in the backend.
>From 37a5288fe3d122486806192dd5f4fba3d024e5d2 Mon Sep 17 00:00:00 2001
From: sgokhale <sgokhale at nvidia.com>
Date: Fri, 29 Nov 2024 11:59:18 +0530
Subject: [PATCH] [AArch64][CostModel] Improve cost estimate of scalarizing a
vector division
In the backend, last resort of finding the vector division cost is to use its scalar cost. However, without knowledge about the division operands, the cost can be off in certain cases.
For SLP, this patch tries to pass scalars for better scalar cost estimation in the backend.
---
.../llvm/Analysis/TargetTransformInfo.h | 14 +-
.../llvm/Analysis/TargetTransformInfoImpl.h | 12 +-
llvm/include/llvm/CodeGen/BasicTTIImpl.h | 3 +-
llvm/lib/Analysis/TargetTransformInfo.cpp | 8 +-
.../AArch64/AArch64TargetTransformInfo.cpp | 56 ++--
.../AArch64/AArch64TargetTransformInfo.h | 3 +-
.../AMDGPU/AMDGPUTargetTransformInfo.cpp | 4 +-
.../Target/AMDGPU/AMDGPUTargetTransformInfo.h | 3 +-
.../lib/Target/ARM/ARMTargetTransformInfo.cpp | 5 +-
llvm/lib/Target/ARM/ARMTargetTransformInfo.h | 3 +-
llvm/lib/Target/BPF/BPFTargetTransformInfo.h | 4 +-
.../Hexagon/HexagonTargetTransformInfo.cpp | 4 +-
.../Hexagon/HexagonTargetTransformInfo.h | 3 +-
.../Target/Lanai/LanaiTargetTransformInfo.h | 3 +-
.../Target/NVPTX/NVPTXTargetTransformInfo.cpp | 4 +-
.../Target/NVPTX/NVPTXTargetTransformInfo.h | 3 +-
.../Target/PowerPC/PPCTargetTransformInfo.cpp | 4 +-
.../Target/PowerPC/PPCTargetTransformInfo.h | 3 +-
.../Target/RISCV/RISCVTargetTransformInfo.cpp | 3 +-
.../Target/RISCV/RISCVTargetTransformInfo.h | 3 +-
.../SystemZ/SystemZTargetTransformInfo.cpp | 4 +-
.../SystemZ/SystemZTargetTransformInfo.h | 3 +-
.../WebAssemblyTargetTransformInfo.cpp | 4 +-
.../WebAssemblyTargetTransformInfo.h | 3 +-
.../lib/Target/X86/X86TargetTransformInfo.cpp | 4 +-
llvm/lib/Target/X86/X86TargetTransformInfo.h | 3 +-
.../Transforms/Vectorize/SLPVectorizer.cpp | 6 +-
llvm/test/Analysis/CostModel/AArch64/div.ll | 282 +++++++++---------
.../Transforms/SLPVectorizer/AArch64/div.ll | 36 +--
29 files changed, 250 insertions(+), 240 deletions(-)
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index 985ca1532e0149..50f1210e82f1e2 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -1297,13 +1297,16 @@ class TargetTransformInfo {
/// provide even more information.
/// \p TLibInfo is used to search for platform specific vector library
/// functions for instructions that might be converted to calls (e.g. frem).
+ /// \p Scalars refers to individual scalars/instructions being used for
+ /// vectorization.
InstructionCost getArithmeticInstrCost(
unsigned Opcode, Type *Ty,
TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput,
TTI::OperandValueInfo Opd1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Opd2Info = {TTI::OK_AnyValue, TTI::OP_None},
ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
- const TargetLibraryInfo *TLibInfo = nullptr) const;
+ const TargetLibraryInfo *TLibInfo = nullptr,
+ ArrayRef<Value *> Scalars = {}) const;
/// Returns the cost estimation for alternating opcode pattern that can be
/// lowered to a single instruction on the target. In X86 this is for the
@@ -2099,7 +2102,8 @@ class TargetTransformInfo::Concept {
virtual InstructionCost getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
OperandValueInfo Opd1Info, OperandValueInfo Opd2Info,
- ArrayRef<const Value *> Args, const Instruction *CxtI = nullptr) = 0;
+ ArrayRef<const Value *> Args, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {}) = 0;
virtual InstructionCost getAltInstrCost(
VectorType *VecTy, unsigned Opcode0, unsigned Opcode1,
const SmallBitVector &OpcodeMask,
@@ -2780,10 +2784,10 @@ class TargetTransformInfo::Model final : public TargetTransformInfo::Concept {
InstructionCost getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
OperandValueInfo Opd1Info, OperandValueInfo Opd2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI = nullptr) override {
+ ArrayRef<const Value *> Args, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {}) override {
return Impl.getArithmeticInstrCost(Opcode, Ty, CostKind, Opd1Info, Opd2Info,
- Args, CxtI);
+ Args, CxtI, Scalars);
}
InstructionCost getAltInstrCost(VectorType *VecTy, unsigned Opcode0,
unsigned Opcode1,
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
index 38aba183f6a173..4aa255a909edbf 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -581,11 +581,13 @@ class TargetTransformInfoImplBase {
unsigned getMaxInterleaveFactor(ElementCount VF) const { return 1; }
- InstructionCost getArithmeticInstrCost(
- unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
- TTI::OperandValueInfo Opd1Info, TTI::OperandValueInfo Opd2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI = nullptr) const {
+ InstructionCost getArithmeticInstrCost(unsigned Opcode, Type *Ty,
+ TTI::TargetCostKind CostKind,
+ TTI::OperandValueInfo Opd1Info,
+ TTI::OperandValueInfo Opd2Info,
+ ArrayRef<const Value *> Args,
+ const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {}) const {
// Widenable conditions will eventually lower into constants, so some
// operations with them will be trivially optimized away.
auto IsWidenableCondition = [](const Value *V) {
diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 98cbb4886642bf..4a27470763db83 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -924,7 +924,8 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Opd1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Opd2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr) {
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {}) {
// Check if any of the operands are vector operands.
const TargetLoweringBase *TLI = getTLI();
int ISD = TLI->InstructionOpcodeToISD(Opcode);
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index 1fb2b9836de0cc..3f8745b1e06ecc 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -927,7 +927,7 @@ InstructionCost TargetTransformInfo::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
OperandValueInfo Op1Info, OperandValueInfo Op2Info,
ArrayRef<const Value *> Args, const Instruction *CxtI,
- const TargetLibraryInfo *TLibInfo) const {
+ const TargetLibraryInfo *TLibInfo, ArrayRef<Value *> Scalars) const {
// Use call cost for frem intructions that have platform specific vector math
// functions, as those will be replaced with calls later by SelectionDAG or
@@ -942,10 +942,8 @@ InstructionCost TargetTransformInfo::getArithmeticInstrCost(
return getCallInstrCost(nullptr, VecTy, {VecTy, VecTy}, CostKind);
}
- InstructionCost Cost =
- TTIImpl->getArithmeticInstrCost(Opcode, Ty, CostKind,
- Op1Info, Op2Info,
- Args, CxtI);
+ InstructionCost Cost = TTIImpl->getArithmeticInstrCost(
+ Opcode, Ty, CostKind, Op1Info, Op2Info, Args, CxtI, Scalars);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index d1536a276a9040..f9434b1691d746 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3376,8 +3376,8 @@ InstructionCost AArch64TTIImpl::getScalarizationOverhead(
InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
// The code-generator is currently not able to handle scalable vectors
// of <vscale x 1 x eltty> yet, so return an invalid cost to avoid selecting
@@ -3442,8 +3442,8 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
if (!VT.isVector() && VT.getSizeInBits() > 64)
return getCallInstrCost(/*Function*/ nullptr, Ty, {Ty, Ty}, CostKind);
- InstructionCost Cost = BaseT::getArithmeticInstrCost(
- Opcode, Ty, CostKind, Op1Info, Op2Info);
+ InstructionCost Cost =
+ BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info, Op2Info);
if (Ty->isVectorTy()) {
if (TLI->isOperationLegalOrCustom(ISD, LT.second) && ST->hasSVE()) {
// SDIV/UDIV operations are lowered using SVE, then we can have less
@@ -3472,29 +3472,41 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
Cost *= 4;
return Cost;
} else {
- // If one of the operands is a uniform constant then the cost for each
- // element is Cost for insertion, extraction and division.
- // Insertion cost = 2, Extraction Cost = 2, Division = cost for the
- // operation with scalar type
- if ((Op1Info.isConstant() && Op1Info.isUniform()) ||
- (Op2Info.isConstant() && Op2Info.isUniform())) {
- if (auto *VTy = dyn_cast<FixedVectorType>(Ty)) {
+ if (auto *VTy = dyn_cast<FixedVectorType>(Ty)) {
+ if ((Op1Info.isConstant() && Op1Info.isUniform()) ||
+ (Op2Info.isConstant() && Op2Info.isUniform())) {
InstructionCost DivCost = BaseT::getArithmeticInstrCost(
Opcode, Ty->getScalarType(), CostKind, Op1Info, Op2Info);
- return (4 + DivCost) * VTy->getNumElements();
+ // If #vector_elements = n then we need
+ // n inserts + 2n extracts + n divisions.
+ InstructionCost InsertExtractCost =
+ ST->getVectorInsertExtractBaseCost();
+ Cost = (3 * InsertExtractCost + DivCost) * VTy->getNumElements();
+ } else if (!Scalars.empty()) {
+ // If #vector_elements = n then we need
+ // n inserts + 2n extracts + n divisions.
+ InstructionCost InsertExtractCost =
+ ST->getVectorInsertExtractBaseCost();
+ Cost = (3 * InsertExtractCost) * VTy->getNumElements();
+ for (auto *V : Scalars) {
+ auto *I = cast<Instruction>(V);
+ Cost +=
+ getArithmeticInstrCost(I->getOpcode(), I->getType(), CostKind,
+ TTI::getOperandInfo(I->getOperand(0)),
+ TTI::getOperandInfo(I->getOperand(1)));
+ }
+ } else {
+ // FIXME: The initial cost calculated should have considered extract
+ // cost twice. For now, we just add additional cost to avoid
+ // underestimating the total cost.
+ Cost += Cost;
}
+ } else {
+ // We can't predict the cost of div/extract/insert without knowing the
+ // vector width.
+ Cost.setInvalid();
}
- // On AArch64, without SVE, vector divisions are expanded
- // into scalar divisions of each pair of elements.
- Cost += getArithmeticInstrCost(Instruction::ExtractElement, Ty,
- CostKind, Op1Info, Op2Info);
- Cost += getArithmeticInstrCost(Instruction::InsertElement, Ty, CostKind,
- Op1Info, Op2Info);
}
-
- // TODO: if one of the arguments is scalar, then it's not necessary to
- // double the cost of handling the vector elements.
- Cost += Cost;
}
return Cost;
}
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
index 201bc831b816b3..8845efd241f8f0 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -218,7 +218,8 @@ class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
InstructionCost getAddressComputationCost(Type *Ty, ScalarEvolution *SE,
const SCEV *Ptr);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
index 5160851f8c4424..e1d718aa8a3509 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -546,8 +546,8 @@ bool GCNTTIImpl::getTgtMemIntrinsic(IntrinsicInst *Inst,
InstructionCost GCNTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
// Legalize the type.
std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(Ty);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
index 10956861650ab3..414e4b8f7284a7 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
@@ -157,7 +157,8 @@ class GCNTTIImpl final : public BasicTTIImplBase<GCNTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
InstructionCost getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 0e29648a7a284f..9bf37d8457b02f 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -10,6 +10,7 @@
#include "ARMSubtarget.h"
#include "MCTargetDesc/ARMAddressingModes.h"
#include "llvm/ADT/APInt.h"
+#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/CodeGen/CostTable.h"
@@ -1349,8 +1350,8 @@ InstructionCost ARMTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
InstructionCost ARMTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
int ISDOpcode = TLI->InstructionOpcodeToISD(Opcode);
if (ST->isThumb() && CostKind == TTI::TCK_CodeSize && Ty->isIntegerTy(1)) {
// Make operations on i1 relatively expensive as this often involves
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
index 3a4f940088b2e3..bef278e211a418 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
@@ -258,7 +258,8 @@ class ARMTTIImpl : public BasicTTIImplBase<ARMTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
InstructionCost
getMemoryOpCost(unsigned Opcode, Type *Src, MaybeAlign Alignment,
diff --git a/llvm/lib/Target/BPF/BPFTargetTransformInfo.h b/llvm/lib/Target/BPF/BPFTargetTransformInfo.h
index bf0bef3a2b2f98..ca52bd375021c2 100644
--- a/llvm/lib/Target/BPF/BPFTargetTransformInfo.h
+++ b/llvm/lib/Target/BPF/BPFTargetTransformInfo.h
@@ -16,6 +16,7 @@
#define LLVM_LIB_TARGET_BPF_BPFTARGETTRANSFORMINFO_H
#include "BPFTargetMachine.h"
+#include "llvm/ADT/ArrayRef.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/Transforms/Utils/ScalarEvolutionExpander.h"
@@ -61,7 +62,8 @@ class BPFTTIImpl : public BasicTTIImplBase<BPFTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr) {
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {}) {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
if (ISD == ISD::ADD && CostKind == TTI::TCK_RecipThroughput)
return SCEVCheapExpansionBudget.getValue() + 1;
diff --git a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp
index bbb9d065b62435..53572321ecec62 100644
--- a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp
+++ b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp
@@ -273,8 +273,8 @@ InstructionCost HexagonTTIImpl::getCmpSelInstrCost(
InstructionCost HexagonTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
// TODO: Handle more cost kinds.
if (CostKind != TTI::TCK_RecipThroughput)
return BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info,
diff --git a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h
index 826644d08d1ac0..abaa25136574ae 100644
--- a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h
+++ b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h
@@ -142,7 +142,8 @@ class HexagonTTIImpl : public BasicTTIImplBase<HexagonTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
TTI::CastContextHint CCH,
TTI::TargetCostKind CostKind,
diff --git a/llvm/lib/Target/Lanai/LanaiTargetTransformInfo.h b/llvm/lib/Target/Lanai/LanaiTargetTransformInfo.h
index 5fe63e4a2e0312..5000a93a818b0a 100644
--- a/llvm/lib/Target/Lanai/LanaiTargetTransformInfo.h
+++ b/llvm/lib/Target/Lanai/LanaiTargetTransformInfo.h
@@ -94,7 +94,8 @@ class LanaiTTIImpl : public BasicTTIImplBase<LanaiTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr) {
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {}) {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
switch (ISD) {
diff --git a/llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.cpp b/llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.cpp
index 4ec2ec100ab08d..2c194d9fff1ad4 100644
--- a/llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.cpp
@@ -485,8 +485,8 @@ NVPTXTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
InstructionCost NVPTXTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
// Legalize the type.
std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(Ty);
diff --git a/llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.h b/llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.h
index 0f4fb280b2d996..3d34f8d97ddc47 100644
--- a/llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.h
+++ b/llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.h
@@ -98,7 +98,8 @@ class NVPTXTTIImpl : public BasicTTIImplBase<NVPTXTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP,
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index c308ec332e8443..b8cc52e51f3c11 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -582,8 +582,8 @@ InstructionCost PPCTTIImpl::vectorCostAdjustmentFactor(unsigned Opcode,
InstructionCost PPCTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
assert(TLI->InstructionOpcodeToISD(Opcode) && "Invalid opcode");
InstructionCost CostFactor = vectorCostAdjustmentFactor(Opcode, Ty, nullptr);
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
index 3cb60d7a1785ae..344c16084d4089 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
@@ -106,7 +106,8 @@ class PPCTTIImpl : public BasicTTIImplBase<PPCTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
InstructionCost getShuffleCost(TTI::ShuffleKind Kind, Type *Tp,
ArrayRef<int> Mask,
TTI::TargetCostKind CostKind, int Index,
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index bbded57bb92ab0..328fabdeef2b45 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1951,7 +1951,8 @@ InstructionCost RISCVTTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args, const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
// TODO: Handle more cost kinds.
if (CostKind != TTI::TCK_RecipThroughput)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
index 6fd36e90a02ddd..8c01a9ffdb233e 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
@@ -216,7 +216,8 @@ class RISCVTTIImpl : public BasicTTIImplBase<RISCVTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
bool isElementTypeLegalForScalableVector(Type *Ty) const {
return TLI->isLegalElementTypeForRVV(TLI->getValueType(DL, Ty));
diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
index a586eedd58b667..4f7d43ae576885 100644
--- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
@@ -490,8 +490,8 @@ static unsigned getNumVectorRegs(Type *Ty) {
InstructionCost SystemZTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
// TODO: Handle more cost kinds.
if (CostKind != TTI::TCK_RecipThroughput)
diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
index 8cc71a6c528f82..f9de7b81e67e26 100644
--- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
+++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
@@ -88,7 +88,8 @@ class SystemZTTIImpl : public BasicTTIImplBase<SystemZTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
InstructionCost getShuffleCost(TTI::ShuffleKind Kind, VectorType *Tp,
ArrayRef<int> Mask,
TTI::TargetCostKind CostKind, int Index,
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.cpp
index 3d678e53841664..4b765c64112a07 100644
--- a/llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.cpp
@@ -51,8 +51,8 @@ TypeSize WebAssemblyTTIImpl::getRegisterBitWidth(
InstructionCost WebAssemblyTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
InstructionCost Cost =
BasicTTIImplBase<WebAssemblyTTIImpl>::getArithmeticInstrCost(
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.h b/llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.h
index 9691120b2e531d..ecbe88d438cd39 100644
--- a/llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.h
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.h
@@ -63,7 +63,8 @@ class WebAssemblyTTIImpl final : public BasicTTIImplBase<WebAssemblyTTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
using BaseT::getVectorInstrCost;
InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
TTI::TargetCostKind CostKind,
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 179e29e40614e7..14befea05856b2 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -245,8 +245,8 @@ unsigned X86TTIImpl::getMaxInterleaveFactor(ElementCount VF) {
InstructionCost X86TTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info, TTI::OperandValueInfo Op2Info,
- ArrayRef<const Value *> Args,
- const Instruction *CxtI) {
+ ArrayRef<const Value *> Args, const Instruction *CxtI,
+ ArrayRef<Value *> Scalars) {
// vXi8 multiplications are always promoted to vXi16.
// Sub-128-bit types can be extended/packed more efficiently.
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.h b/llvm/lib/Target/X86/X86TargetTransformInfo.h
index 36d00cee0d18b5..3fc276bc86efca 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.h
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.h
@@ -140,7 +140,8 @@ class X86TTIImpl : public BasicTTIImplBase<X86TTIImpl> {
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
- ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
+ ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr,
+ ArrayRef<Value *> Scalars = {});
InstructionCost getAltInstrCost(VectorType *VecTy, unsigned Opcode0,
unsigned Opcode1,
const SmallBitVector &OpcodeMask,
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 48a8520a966fc7..f0be89147a27e8 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -11561,9 +11561,9 @@ BoUpSLP::getEntryCost(const TreeEntry *E, ArrayRef<Value *> VectorizedVals,
unsigned OpIdx = isa<UnaryOperator>(VL0) ? 0 : 1;
TTI::OperandValueInfo Op1Info = getOperandInfo(E->getOperand(0));
TTI::OperandValueInfo Op2Info = getOperandInfo(E->getOperand(OpIdx));
- return TTI->getArithmeticInstrCost(ShuffleOrOp, VecTy, CostKind, Op1Info,
- Op2Info, {}, nullptr, TLI) +
- CommonCost;
+ return CommonCost +
+ TTI->getArithmeticInstrCost(ShuffleOrOp, VecTy, CostKind, Op1Info,
+ Op2Info, {}, nullptr, TLI, E->Scalars);
};
return GetCostDiff(GetScalarCost, GetVectorCost);
}
diff --git a/llvm/test/Analysis/CostModel/AArch64/div.ll b/llvm/test/Analysis/CostModel/AArch64/div.ll
index ada0be66c27b5a..179efe58b328ed 100644
--- a/llvm/test/Analysis/CostModel/AArch64/div.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/div.ll
@@ -7,21 +7,21 @@ define i32 @sdiv() {
; CHECK-LABEL: 'sdiv'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = sdiv i128 undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2i64 = sdiv <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = sdiv <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = sdiv <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2i64 = sdiv <2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i64 = sdiv <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i64 = sdiv <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = sdiv <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = sdiv <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = sdiv <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i32 = sdiv <4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i32 = sdiv <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i32 = sdiv <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = sdiv <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = sdiv <16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = sdiv <32 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i16 = sdiv <8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i16 = sdiv <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i16 = sdiv <32 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = sdiv <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = sdiv <32 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = sdiv <64 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i8 = sdiv <16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i8 = sdiv <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 640 for instruction: %V64i8 = sdiv <64 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = sdiv i128 undef, undef
@@ -53,21 +53,21 @@ define i32 @udiv() {
; CHECK-LABEL: 'udiv'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2i64 = udiv <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = udiv <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = udiv <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2i64 = udiv <2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i64 = udiv <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i64 = udiv <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = udiv <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = udiv <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = udiv <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i32 = udiv <4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i32 = udiv <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i32 = udiv <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = udiv <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = udiv <16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = udiv <32 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i16 = udiv <8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i16 = udiv <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i16 = udiv <32 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = udiv <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = udiv <32 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = udiv <64 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i8 = udiv <16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i8 = udiv <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 640 for instruction: %V64i8 = udiv <64 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = udiv i128 undef, undef
@@ -99,21 +99,21 @@ define i32 @sdiv_const() {
; CHECK-LABEL: 'sdiv_const'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = sdiv i128 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = sdiv i64 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 6, i64 7>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 6, i64 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 640 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = sdiv i128 undef, 7
@@ -145,21 +145,21 @@ define i32 @udiv_const() {
; CHECK-LABEL: 'udiv_const'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 640 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
@@ -192,21 +192,21 @@ define i32 @sdiv_uniformconst() {
; CHECK-LABEL: 'sdiv_uniformconst'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = sdiv i128 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = sdiv i64 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = sdiv <2 x i64> undef, splat (i64 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = sdiv <4 x i64> undef, splat (i64 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = sdiv <8 x i64> undef, splat (i64 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = sdiv <2 x i64> undef, splat (i64 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = sdiv <4 x i64> undef, splat (i64 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = sdiv <8 x i64> undef, splat (i64 7)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = sdiv <4 x i32> undef, splat (i32 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = sdiv <8 x i32> undef, splat (i32 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = sdiv <16 x i32> undef, splat (i32 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = sdiv <8 x i32> undef, splat (i32 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = sdiv <16 x i32> undef, splat (i32 7)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = sdiv <8 x i16> undef, splat (i16 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = sdiv <16 x i16> undef, splat (i16 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = sdiv <32 x i16> undef, splat (i16 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = sdiv <16 x i16> undef, splat (i16 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = sdiv <32 x i16> undef, splat (i16 7)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = sdiv <16 x i8> undef, splat (i8 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = sdiv <32 x i8> undef, splat (i8 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = sdiv <64 x i8> undef, splat (i8 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = sdiv <32 x i8> undef, splat (i8 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = sdiv <64 x i8> undef, splat (i8 7)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = sdiv i128 undef, 7
@@ -238,21 +238,21 @@ define i32 @udiv_uniformconst() {
; CHECK-LABEL: 'udiv_uniformconst'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 7)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 7)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 7)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 7)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 7)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 7)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = udiv i128 undef, 7
@@ -284,21 +284,21 @@ define i32 @sdiv_constpow2() {
; CHECK-LABEL: 'sdiv_constpow2'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = sdiv i128 undef, 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = sdiv i64 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 8, i64 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 8, i64 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I32 = sdiv i32 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I16 = sdiv i16 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I8 = sdiv i8 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 640 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = sdiv i128 undef, 16
@@ -330,21 +330,21 @@ define i32 @udiv_constpow2() {
; CHECK-LABEL: 'udiv_constpow2'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 640 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = udiv i128 undef, 16
@@ -422,21 +422,21 @@ define i32 @udiv_uniformconstpow2() {
; CHECK-LABEL: 'udiv_uniformconstpow2'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = udiv i128 undef, 16
@@ -468,21 +468,21 @@ define i32 @sdiv_constnegpow2() {
; CHECK-LABEL: 'sdiv_constnegpow2'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = sdiv i128 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = sdiv i64 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -8, i64 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -8, i64 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 640 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = sdiv i128 undef, -16
@@ -514,21 +514,21 @@ define i32 @udiv_constnegpow2() {
; CHECK-LABEL: 'udiv_constnegpow2'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -8, i64 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -8, i64 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 640 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = udiv i128 undef, -16
@@ -560,21 +560,21 @@ define i32 @sdiv_uniformconstnegpow2() {
; CHECK-LABEL: 'sdiv_uniformconstnegpow2'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = sdiv i128 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = sdiv i64 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = sdiv <2 x i64> undef, splat (i64 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = sdiv <4 x i64> undef, splat (i64 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = sdiv <8 x i64> undef, splat (i64 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = sdiv <2 x i64> undef, splat (i64 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = sdiv <4 x i64> undef, splat (i64 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = sdiv <8 x i64> undef, splat (i64 -16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = sdiv <4 x i32> undef, splat (i32 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = sdiv <8 x i32> undef, splat (i32 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = sdiv <16 x i32> undef, splat (i32 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = sdiv <8 x i32> undef, splat (i32 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = sdiv <16 x i32> undef, splat (i32 -16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = sdiv <8 x i16> undef, splat (i16 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = sdiv <16 x i16> undef, splat (i16 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = sdiv <32 x i16> undef, splat (i16 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = sdiv <16 x i16> undef, splat (i16 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = sdiv <32 x i16> undef, splat (i16 -16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = sdiv <16 x i8> undef, splat (i8 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = sdiv <32 x i8> undef, splat (i8 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = sdiv <64 x i8> undef, splat (i8 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = sdiv <32 x i8> undef, splat (i8 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = sdiv <64 x i8> undef, splat (i8 -16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = sdiv i128 undef, -16
@@ -606,21 +606,21 @@ define i32 @udiv_uniformconstnegpow2() {
; CHECK-LABEL: 'udiv_uniformconstnegpow2'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 -16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 -16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 -16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 -16)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 -16)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 -16)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I128 = udiv i128 undef, -16
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/div.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/div.ll
index 57c877a58d5c0e..47630d9eb01fff 100644
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/div.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/div.ll
@@ -554,35 +554,13 @@ define <4 x i32> @slp_v4i32_Op1_unknown_Op2_const_pow2(<4 x i32> %a)
; computes (a/const + x - y) * z
define <2 x i32> @vectorize_sdiv_v2i32(<2 x i32> %a, <2 x i32> %x, <2 x i32> %y, <2 x i32> %z)
-; NO-SVE-LABEL: define <2 x i32> @vectorize_sdiv_v2i32(
-; NO-SVE-SAME: <2 x i32> [[A:%.*]], <2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <2 x i32> [[Z:%.*]]) #[[ATTR0]] {
-; NO-SVE-NEXT: [[A0:%.*]] = extractelement <2 x i32> [[A]], i64 0
-; NO-SVE-NEXT: [[A1:%.*]] = extractelement <2 x i32> [[A]], i64 1
-; NO-SVE-NEXT: [[TMP1:%.*]] = sdiv i32 [[A0]], 2
-; NO-SVE-NEXT: [[TMP2:%.*]] = sdiv i32 [[A1]], 4
-; NO-SVE-NEXT: [[X0:%.*]] = extractelement <2 x i32> [[X]], i64 0
-; NO-SVE-NEXT: [[X1:%.*]] = extractelement <2 x i32> [[X]], i64 1
-; NO-SVE-NEXT: [[TMP3:%.*]] = add i32 [[TMP1]], [[X0]]
-; NO-SVE-NEXT: [[TMP4:%.*]] = add i32 [[TMP2]], [[X1]]
-; NO-SVE-NEXT: [[Y0:%.*]] = extractelement <2 x i32> [[Y]], i64 0
-; NO-SVE-NEXT: [[Y1:%.*]] = extractelement <2 x i32> [[Y]], i64 1
-; NO-SVE-NEXT: [[TMP5:%.*]] = sub i32 [[TMP3]], [[Y0]]
-; NO-SVE-NEXT: [[TMP6:%.*]] = sub i32 [[TMP4]], [[Y1]]
-; NO-SVE-NEXT: [[Z0:%.*]] = extractelement <2 x i32> [[Z]], i64 0
-; NO-SVE-NEXT: [[Z1:%.*]] = extractelement <2 x i32> [[Z]], i64 1
-; NO-SVE-NEXT: [[TMP7:%.*]] = mul i32 [[TMP5]], [[Z0]]
-; NO-SVE-NEXT: [[TMP8:%.*]] = mul i32 [[TMP6]], [[Z1]]
-; NO-SVE-NEXT: [[RES0:%.*]] = insertelement <2 x i32> poison, i32 [[TMP7]], i32 0
-; NO-SVE-NEXT: [[RES1:%.*]] = insertelement <2 x i32> [[RES0]], i32 [[TMP8]], i32 1
-; NO-SVE-NEXT: ret <2 x i32> [[RES1]]
-;
-; SVE-LABEL: define <2 x i32> @vectorize_sdiv_v2i32(
-; SVE-SAME: <2 x i32> [[A:%.*]], <2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <2 x i32> [[Z:%.*]]) #[[ATTR0]] {
-; SVE-NEXT: [[TMP1:%.*]] = sdiv <2 x i32> [[A]], <i32 2, i32 4>
-; SVE-NEXT: [[TMP2:%.*]] = add <2 x i32> [[TMP1]], [[X]]
-; SVE-NEXT: [[TMP3:%.*]] = sub <2 x i32> [[TMP2]], [[Y]]
-; SVE-NEXT: [[TMP4:%.*]] = mul <2 x i32> [[TMP3]], [[Z]]
-; SVE-NEXT: ret <2 x i32> [[TMP4]]
+; CHECK-LABEL: define <2 x i32> @vectorize_sdiv_v2i32(
+; CHECK-SAME: <2 x i32> [[A:%.*]], <2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <2 x i32> [[Z:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = sdiv <2 x i32> [[A]], <i32 2, i32 4>
+; CHECK-NEXT: [[TMP2:%.*]] = add <2 x i32> [[TMP1]], [[X]]
+; CHECK-NEXT: [[TMP3:%.*]] = sub <2 x i32> [[TMP2]], [[Y]]
+; CHECK-NEXT: [[TMP4:%.*]] = mul <2 x i32> [[TMP3]], [[Z]]
+; CHECK-NEXT: ret <2 x i32> [[TMP4]]
;
{
%a0 = extractelement <2 x i32> %a, i64 0
More information about the llvm-commits
mailing list