mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-21 02:29:22 +00:00
83c8e732dd
Summary: Reapply r221772. The old patch breaks the bot because the @indvar_32_bit test was run whether NVPTX was enabled or not. IndVarSimplify should not widen an indvar if arithmetics on the wider indvar are more expensive than those on the narrower indvar. For instance, although NVPTX64 treats i64 as a legal type, an ADD on i64 is twice as expensive as that on i32, because the hardware needs to simulate a 64-bit integer using two 32-bit integers. Split from D6188, and based on D6195 which adds NVPTXTargetTransformInfo. Fixes PR21148. Test Plan: Added @indvar_32_bit that verifies we do not widen an indvar if the arithmetics on the wider type are more expensive. This test is run only when NVPTX is enabled. Reviewers: jholewinski, eliben, meheff, atrick Reviewed By: atrick Subscribers: jholewinski, llvm-commits Differential Revision: http://reviews.llvm.org/D6196 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221799 91177308-0d34-0410-b5e6-96231b3b80d8
118 lines
3.9 KiB
C++
118 lines
3.9 KiB
C++
//===-- NVPTXTargetTransformInfo.cpp - NVPTX specific TTI pass ---------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// \file
|
|
// This file implements a TargetTransformInfo analysis pass specific to the
|
|
// NVPTX 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.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "NVPTXTargetMachine.h"
|
|
#include "llvm/Analysis/LoopInfo.h"
|
|
#include "llvm/Analysis/TargetTransformInfo.h"
|
|
#include "llvm/Analysis/ValueTracking.h"
|
|
#include "llvm/Support/Debug.h"
|
|
#include "llvm/Target/CostTable.h"
|
|
#include "llvm/Target/TargetLowering.h"
|
|
using namespace llvm;
|
|
|
|
#define DEBUG_TYPE "NVPTXtti"
|
|
|
|
// Declare the pass initialization routine locally as target-specific passes
|
|
// don't have a target-wide initialization entry point, and so we rely on the
|
|
// pass constructor initialization.
|
|
namespace llvm {
|
|
void initializeNVPTXTTIPass(PassRegistry &);
|
|
}
|
|
|
|
namespace {
|
|
|
|
class NVPTXTTI final : public ImmutablePass, public TargetTransformInfo {
|
|
const NVPTXTargetLowering *TLI;
|
|
public:
|
|
NVPTXTTI() : ImmutablePass(ID), TLI(nullptr) {
|
|
llvm_unreachable("This pass cannot be directly constructed");
|
|
}
|
|
|
|
NVPTXTTI(const NVPTXTargetMachine *TM)
|
|
: ImmutablePass(ID), TLI(TM->getSubtargetImpl()->getTargetLowering()) {
|
|
initializeNVPTXTTIPass(*PassRegistry::getPassRegistry());
|
|
}
|
|
|
|
void initializePass() override { pushTTIStack(this); }
|
|
|
|
void getAnalysisUsage(AnalysisUsage &AU) const override {
|
|
TargetTransformInfo::getAnalysisUsage(AU);
|
|
}
|
|
|
|
/// Pass identification.
|
|
static char ID;
|
|
|
|
/// Provide necessary pointer adjustments for the two base classes.
|
|
void *getAdjustedAnalysisPointer(const void *ID) override {
|
|
if (ID == &TargetTransformInfo::ID)
|
|
return (TargetTransformInfo *)this;
|
|
return this;
|
|
}
|
|
|
|
bool hasBranchDivergence() const override;
|
|
|
|
unsigned getArithmeticInstrCost(
|
|
unsigned Opcode, Type *Ty, OperandValueKind Opd1Info = OK_AnyValue,
|
|
OperandValueKind Opd2Info = OK_AnyValue,
|
|
OperandValueProperties Opd1PropInfo = OP_None,
|
|
OperandValueProperties Opd2PropInfo = OP_None) const override;
|
|
|
|
/// @}
|
|
};
|
|
|
|
} // end anonymous namespace
|
|
|
|
INITIALIZE_AG_PASS(NVPTXTTI, TargetTransformInfo, "NVPTXtti",
|
|
"NVPTX Target Transform Info", true, true, false)
|
|
char NVPTXTTI::ID = 0;
|
|
|
|
ImmutablePass *
|
|
llvm::createNVPTXTargetTransformInfoPass(const NVPTXTargetMachine *TM) {
|
|
return new NVPTXTTI(TM);
|
|
}
|
|
|
|
bool NVPTXTTI::hasBranchDivergence() const { return true; }
|
|
|
|
unsigned NVPTXTTI::getArithmeticInstrCost(
|
|
unsigned Opcode, Type *Ty, OperandValueKind Opd1Info,
|
|
OperandValueKind Opd2Info, OperandValueProperties Opd1PropInfo,
|
|
OperandValueProperties Opd2PropInfo) const {
|
|
// Legalize the type.
|
|
std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Ty);
|
|
|
|
int ISD = TLI->InstructionOpcodeToISD(Opcode);
|
|
|
|
switch (ISD) {
|
|
default:
|
|
return TargetTransformInfo::getArithmeticInstrCost(
|
|
Opcode, Ty, Opd1Info, Opd2Info, Opd1PropInfo, Opd2PropInfo);
|
|
case ISD::ADD:
|
|
case ISD::MUL:
|
|
case ISD::XOR:
|
|
case ISD::OR:
|
|
case ISD::AND:
|
|
// The machine code (SASS) simulates an i64 with two i32. Therefore, we
|
|
// estimate that arithmetic operations on i64 are twice as expensive as
|
|
// those on types that can fit into one machine register.
|
|
if (LT.second.SimpleTy == MVT::i64)
|
|
return 2 * LT.first;
|
|
// Delegate other cases to the basic TTI.
|
|
return TargetTransformInfo::getArithmeticInstrCost(
|
|
Opcode, Ty, Opd1Info, Opd2Info, Opd1PropInfo, Opd2PropInfo);
|
|
}
|
|
}
|