934f802731
This patch includes: 1. fma_mix inst takes fp16 type as input, but place the operand in vgpr32. Update selector to insert vgpr32 for true16 mode if necessary. 2. fma_mix inst returns fp16 type as output, but place the vdst in vgpr32. Create a fma_mix_t16 pesudo inst for isel pattern, and lower it to mix_lo/hi in the mc lowering pass. These stop isel from emitting illegal `vgpr32 = COPY vgpr16` and improve code quality
71 lines
2.5 KiB
C++
71 lines
2.5 KiB
C++
//===- AMDGPUMCInstLower.h - Lower MachineInstr to MCInst ------*- C++ -*--===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
/// \file
|
|
/// Header of lower AMDGPU MachineInstrs to their corresponding MCInst.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
|
|
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUMCINSTLOWER_H
|
|
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUMCINSTLOWER_H
|
|
|
|
#include "AMDGPUTargetMachine.h"
|
|
#include "llvm/IR/Constants.h"
|
|
#include "llvm/Support/Casting.h"
|
|
|
|
namespace llvm {
|
|
class AsmPrinter;
|
|
class MCContext;
|
|
|
|
class AMDGPUMCInstLower {
|
|
MCContext &Ctx;
|
|
const TargetSubtargetInfo &ST;
|
|
const AsmPrinter ≈
|
|
|
|
public:
|
|
AMDGPUMCInstLower(MCContext &ctx, const TargetSubtargetInfo &ST,
|
|
const AsmPrinter &AP);
|
|
|
|
bool lowerOperand(const MachineOperand &MO, MCOperand &MCOp) const;
|
|
|
|
/// Lower a MachineInstr to an MCInst
|
|
void lower(const MachineInstr *MI, MCInst &OutMI) const;
|
|
|
|
void lowerT16D16Helper(const MachineInstr *MI, MCInst &OutMI) const;
|
|
void lowerT16FmaMixFP16(const MachineInstr *MI, MCInst &OutMI) const;
|
|
};
|
|
|
|
namespace {
|
|
static inline const MCExpr *lowerAddrSpaceCast(const TargetMachine &TM,
|
|
const Constant *CV,
|
|
MCContext &OutContext) {
|
|
// TargetMachine does not support llvm-style cast. Use C++-style cast.
|
|
// This is safe since TM is always of type AMDGPUTargetMachine or its
|
|
// derived class.
|
|
auto &AT = static_cast<const AMDGPUTargetMachine &>(TM);
|
|
auto *CE = dyn_cast<ConstantExpr>(CV);
|
|
|
|
// Lower null pointers in private and local address space.
|
|
// Clang generates addrspacecast for null pointers in private and local
|
|
// address space, which needs to be lowered.
|
|
if (CE && CE->getOpcode() == Instruction::AddrSpaceCast) {
|
|
auto *Op = CE->getOperand(0);
|
|
auto SrcAddr = Op->getType()->getPointerAddressSpace();
|
|
if (Op->isNullValue() && AT.getNullPointerValue(SrcAddr) == 0) {
|
|
auto DstAddr = CE->getType()->getPointerAddressSpace();
|
|
return MCConstantExpr::create(AT.getNullPointerValue(DstAddr),
|
|
OutContext);
|
|
}
|
|
}
|
|
return nullptr;
|
|
}
|
|
} // namespace
|
|
} // namespace llvm
|
|
#endif // LLVM_LIB_TARGET_AMDGPU_AMDGPUMCINSTLOWER_H
|