2015-01-31 19:17:59 +08:00
|
|
|
//===-- ARMTargetTransformInfo.h - ARM specific TTI -------------*- C++ -*-===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/// \file
|
|
|
|
/// This file a TargetTransformInfo::Concept conforming object specific to the
|
|
|
|
/// ARM target machine. It uses the target's detailed information to
|
|
|
|
/// provide more precise answers to certain TTI queries, while letting the
|
|
|
|
/// target independent and default TTI implementations handle the rest.
|
|
|
|
///
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#ifndef LLVM_LIB_TARGET_ARM_ARMTARGETTRANSFORMINFO_H
|
|
|
|
#define LLVM_LIB_TARGET_ARM_ARMTARGETTRANSFORMINFO_H
|
|
|
|
|
|
|
|
#include "ARM.h"
|
|
|
|
#include "ARMTargetMachine.h"
|
|
|
|
#include "llvm/Analysis/TargetTransformInfo.h"
|
|
|
|
#include "llvm/CodeGen/BasicTTIImpl.h"
|
|
|
|
#include "llvm/Target/TargetLowering.h"
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
|
|
|
|
class ARMTTIImpl : public BasicTTIImplBase<ARMTTIImpl> {
|
|
|
|
typedef BasicTTIImplBase<ARMTTIImpl> BaseT;
|
|
|
|
typedef TargetTransformInfo TTI;
|
2015-02-01 22:01:15 +08:00
|
|
|
friend BaseT;
|
2015-01-31 19:17:59 +08:00
|
|
|
|
|
|
|
const ARMSubtarget *ST;
|
|
|
|
const ARMTargetLowering *TLI;
|
|
|
|
|
|
|
|
/// Estimate the overhead of scalarizing an instruction. Insert and Extract
|
|
|
|
/// are set if the result needs to be inserted and/or extracted from vectors.
|
|
|
|
unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract);
|
|
|
|
|
2015-02-01 22:22:17 +08:00
|
|
|
const ARMSubtarget *getST() const { return ST; }
|
2015-02-01 22:01:15 +08:00
|
|
|
const ARMTargetLowering *getTLI() const { return TLI; }
|
|
|
|
|
2015-01-31 19:17:59 +08:00
|
|
|
public:
|
2015-02-01 21:20:00 +08:00
|
|
|
explicit ARMTTIImpl(const ARMBaseTargetMachine *TM, Function &F)
|
2015-07-09 10:08:42 +08:00
|
|
|
: BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
|
|
|
|
TLI(ST->getTargetLowering()) {}
|
2015-01-31 19:17:59 +08:00
|
|
|
|
|
|
|
// Provide value semantics. MSVC requires that we spell all of these out.
|
|
|
|
ARMTTIImpl(const ARMTTIImpl &Arg)
|
2015-02-01 22:22:17 +08:00
|
|
|
: BaseT(static_cast<const BaseT &>(Arg)), ST(Arg.ST), TLI(Arg.TLI) {}
|
2015-01-31 19:17:59 +08:00
|
|
|
ARMTTIImpl(ARMTTIImpl &&Arg)
|
2015-02-01 22:22:17 +08:00
|
|
|
: BaseT(std::move(static_cast<BaseT &>(Arg))), ST(std::move(Arg.ST)),
|
|
|
|
TLI(std::move(Arg.TLI)) {}
|
2015-01-31 19:17:59 +08:00
|
|
|
|
|
|
|
/// \name Scalar TTI Implementations
|
|
|
|
/// @{
|
|
|
|
|
|
|
|
using BaseT::getIntImmCost;
|
|
|
|
unsigned getIntImmCost(const APInt &Imm, Type *Ty);
|
|
|
|
|
|
|
|
/// @}
|
|
|
|
|
|
|
|
/// \name Vector TTI Implementations
|
|
|
|
/// @{
|
|
|
|
|
|
|
|
unsigned getNumberOfRegisters(bool Vector) {
|
|
|
|
if (Vector) {
|
|
|
|
if (ST->hasNEON())
|
|
|
|
return 16;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ST->isThumb1Only())
|
|
|
|
return 8;
|
|
|
|
return 13;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getRegisterBitWidth(bool Vector) {
|
|
|
|
if (Vector) {
|
|
|
|
if (ST->hasNEON())
|
|
|
|
return 128;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 32;
|
|
|
|
}
|
|
|
|
|
2015-05-07 01:12:25 +08:00
|
|
|
unsigned getMaxInterleaveFactor(unsigned VF) {
|
2015-01-31 19:17:59 +08:00
|
|
|
// These are out of order CPUs:
|
|
|
|
if (ST->isCortexA15() || ST->isSwift())
|
|
|
|
return 2;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index,
|
|
|
|
Type *SubTp);
|
|
|
|
|
|
|
|
unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src);
|
|
|
|
|
|
|
|
unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy);
|
|
|
|
|
|
|
|
unsigned getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
|
|
|
|
|
|
|
|
unsigned getAddressComputationCost(Type *Val, bool IsComplex);
|
|
|
|
|
2015-02-05 10:09:33 +08:00
|
|
|
unsigned getFPOpCost(Type *Ty);
|
|
|
|
|
2015-01-31 19:17:59 +08:00
|
|
|
unsigned getArithmeticInstrCost(
|
|
|
|
unsigned Opcode, Type *Ty,
|
|
|
|
TTI::OperandValueKind Op1Info = TTI::OK_AnyValue,
|
|
|
|
TTI::OperandValueKind Op2Info = TTI::OK_AnyValue,
|
|
|
|
TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
|
|
|
|
TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None);
|
|
|
|
|
|
|
|
unsigned getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
|
|
|
|
unsigned AddressSpace);
|
|
|
|
|
[ARM] Lower interleaved memory accesses to vldN/vstN intrinsics.
This patch also adds a function to calculate the cost of interleaved memory accesses.
E.g. Lower an interleaved load:
%wide.vec = load <8 x i32>, <8 x i32>* %ptr, align 4
%v0 = shuffle %wide.vec, undef, <0, 2, 4, 6>
%v1 = shuffle %wide.vec, undef, <1, 3, 5, 7>
into:
%vld2 = { <4 x i32>, <4 x i32> } call llvm.arm.neon.vld2(%ptr, 4)
%vec0 = extractelement { <4 x i32>, <4 x i32> } %vld2, i32 0
%vec1 = extractelement { <4 x i32>, <4 x i32> } %vld2, i32 1
E.g. Lower an interleaved store:
%i.vec = shuffle <8 x i32> %v0, <8 x i32> %v1, <0, 4, 8, 1, 5, 9, 2, 6, 10, 3, 7, 11>
store <12 x i32> %i.vec, <12 x i32>* %ptr, align 4
into:
%sub.v0 = shuffle <8 x i32> %v0, <8 x i32> v1, <0, 1, 2, 3>
%sub.v1 = shuffle <8 x i32> %v0, <8 x i32> v1, <4, 5, 6, 7>
%sub.v2 = shuffle <8 x i32> %v0, <8 x i32> v1, <8, 9, 10, 11>
call void llvm.arm.neon.vst3(%ptr, %sub.v0, %sub.v1, %sub.v2, 4)
Differential Revision: http://reviews.llvm.org/D10533
llvm-svn: 240755
2015-06-26 10:45:36 +08:00
|
|
|
unsigned getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
|
|
|
|
unsigned Factor,
|
|
|
|
ArrayRef<unsigned> Indices,
|
|
|
|
unsigned Alignment,
|
|
|
|
unsigned AddressSpace);
|
2015-01-31 19:17:59 +08:00
|
|
|
/// @}
|
|
|
|
};
|
|
|
|
|
|
|
|
} // end namespace llvm
|
|
|
|
|
|
|
|
#endif
|