2017-07-07 04:57:05 +08:00
|
|
|
//===--- AMDGPUMacroFusion.cpp - AMDGPU Macro Fusion ----------------------===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
/// \file This file contains the AMDGPU implementation of the DAG scheduling
|
|
|
|
/// mutation to pair instructions back to back.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "AMDGPUMacroFusion.h"
|
|
|
|
#include "AMDGPUSubtarget.h"
|
|
|
|
#include "SIInstrInfo.h"
|
AMDGPU: Remove #include "MCTargetDesc/AMDGPUMCTargetDesc.h" from common headers
Summary:
MCTargetDesc/AMDGPUMCTargetDesc.h contains enums for all the instuction
and register defintions, which are huge so we only want to include
them where needed.
This will also make it easier if we want to split the R600 and GCN
definitions into separate tablegenerated files.
I was unable to remove AMDGPUMCTargetDesc.h from SIMachineFunctionInfo.h
because it uses some enums from the header to initialize default values
for the SIMachineFunction class, so I ended up having to remove includes of
SIMachineFunctionInfo.h from headers too.
Reviewers: arsenm, nhaehnle
Reviewed By: nhaehnle
Subscribers: MatzeB, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D46272
llvm-svn: 332930
2018-05-22 10:03:23 +08:00
|
|
|
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
|
2017-07-07 04:57:05 +08:00
|
|
|
|
|
|
|
#include "llvm/CodeGen/MacroFusion.h"
|
|
|
|
|
|
|
|
using namespace llvm;
|
|
|
|
|
|
|
|
namespace {
|
|
|
|
|
2018-05-01 23:54:18 +08:00
|
|
|
/// Check if the instr pair, FirstMI and SecondMI, should be fused
|
2017-07-07 04:57:05 +08:00
|
|
|
/// together. Given SecondMI, when FirstMI is unspecified, then check if
|
|
|
|
/// SecondMI may be part of a fused pair at all.
|
|
|
|
static bool shouldScheduleAdjacent(const TargetInstrInfo &TII_,
|
|
|
|
const TargetSubtargetInfo &TSI,
|
|
|
|
const MachineInstr *FirstMI,
|
|
|
|
const MachineInstr &SecondMI) {
|
|
|
|
const SIInstrInfo &TII = static_cast<const SIInstrInfo&>(TII_);
|
|
|
|
|
|
|
|
switch (SecondMI.getOpcode()) {
|
|
|
|
case AMDGPU::V_ADDC_U32_e64:
|
|
|
|
case AMDGPU::V_SUBB_U32_e64:
|
|
|
|
case AMDGPU::V_CNDMASK_B32_e64: {
|
|
|
|
// Try to cluster defs of condition registers to their uses. This improves
|
|
|
|
// the chance VCC will be available which will allow shrinking to VOP2
|
|
|
|
// encodings.
|
|
|
|
if (!FirstMI)
|
|
|
|
return true;
|
|
|
|
|
2018-11-10 01:58:59 +08:00
|
|
|
const MachineBasicBlock &MBB = *FirstMI->getParent();
|
|
|
|
const MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
|
|
|
|
const TargetRegisterInfo *TRI = MRI.getTargetRegisterInfo();
|
2017-07-07 04:57:05 +08:00
|
|
|
const MachineOperand *Src2 = TII.getNamedOperand(SecondMI,
|
|
|
|
AMDGPU::OpName::src2);
|
2018-11-10 01:58:59 +08:00
|
|
|
return FirstMI->definesRegister(Src2->getReg(), TRI);
|
2017-07-07 04:57:05 +08:00
|
|
|
}
|
|
|
|
default:
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
} // end namespace
|
|
|
|
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
|
|
|
|
std::unique_ptr<ScheduleDAGMutation> createAMDGPUMacroFusionDAGMutation () {
|
|
|
|
return createMacroFusionDAGMutation(shouldScheduleAdjacent);
|
|
|
|
}
|
|
|
|
|
|
|
|
} // end namespace llvm
|