1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-20 11:33:24 +02:00
llvm-mirror/lib/Target/AMDGPU/SIPreAllocateWWMRegs.cpp
Reid Kleckner 68092989f3 Sink all InitializePasses.h includes
This file lists every pass in LLVM, and is included by Pass.h, which is
very popular. Every time we add, remove, or rename a pass in LLVM, it
caused lots of recompilation.

I found this fact by looking at this table, which is sorted by the
number of times a file was changed over the last 100,000 git commits
multiplied by the number of object files that depend on it in the
current checkout:
  recompiles    touches affected_files  header
  342380        95      3604    llvm/include/llvm/ADT/STLExtras.h
  314730        234     1345    llvm/include/llvm/InitializePasses.h
  307036        118     2602    llvm/include/llvm/ADT/APInt.h
  213049        59      3611    llvm/include/llvm/Support/MathExtras.h
  170422        47      3626    llvm/include/llvm/Support/Compiler.h
  162225        45      3605    llvm/include/llvm/ADT/Optional.h
  158319        63      2513    llvm/include/llvm/ADT/Triple.h
  140322        39      3598    llvm/include/llvm/ADT/StringRef.h
  137647        59      2333    llvm/include/llvm/Support/Error.h
  131619        73      1803    llvm/include/llvm/Support/FileSystem.h

Before this change, touching InitializePasses.h would cause 1345 files
to recompile. After this change, touching it only causes 550 compiles in
an incremental rebuild.

Reviewers: bkramer, asbirlea, bollu, jdoerfert

Differential Revision: https://reviews.llvm.org/D70211
2019-11-13 16:34:37 -08:00

223 lines
6.1 KiB
C++

//===- SIPreAllocateWWMRegs.cpp - WWM Register Pre-allocation -------------===//
//
// 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
/// Pass to pre-allocated WWM registers
//
//===----------------------------------------------------------------------===//
#include "AMDGPU.h"
#include "AMDGPUSubtarget.h"
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
#include "SIInstrInfo.h"
#include "SIMachineFunctionInfo.h"
#include "SIRegisterInfo.h"
#include "llvm/ADT/PostOrderIterator.h"
#include "llvm/CodeGen/LiveInterval.h"
#include "llvm/CodeGen/LiveIntervals.h"
#include "llvm/CodeGen/LiveRegMatrix.h"
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/RegisterClassInfo.h"
#include "llvm/CodeGen/VirtRegMap.h"
#include "llvm/InitializePasses.h"
using namespace llvm;
#define DEBUG_TYPE "si-pre-allocate-wwm-regs"
namespace {
class SIPreAllocateWWMRegs : public MachineFunctionPass {
private:
const SIInstrInfo *TII;
const SIRegisterInfo *TRI;
MachineRegisterInfo *MRI;
LiveIntervals *LIS;
LiveRegMatrix *Matrix;
VirtRegMap *VRM;
RegisterClassInfo RegClassInfo;
std::vector<unsigned> RegsToRewrite;
public:
static char ID;
SIPreAllocateWWMRegs() : MachineFunctionPass(ID) {
initializeSIPreAllocateWWMRegsPass(*PassRegistry::getPassRegistry());
}
bool runOnMachineFunction(MachineFunction &MF) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<LiveIntervals>();
AU.addPreserved<LiveIntervals>();
AU.addRequired<VirtRegMap>();
AU.addRequired<LiveRegMatrix>();
AU.addPreserved<SlotIndexes>();
AU.setPreservesCFG();
MachineFunctionPass::getAnalysisUsage(AU);
}
private:
bool processDef(MachineOperand &MO);
void rewriteRegs(MachineFunction &MF);
};
} // End anonymous namespace.
INITIALIZE_PASS_BEGIN(SIPreAllocateWWMRegs, DEBUG_TYPE,
"SI Pre-allocate WWM Registers", false, false)
INITIALIZE_PASS_DEPENDENCY(LiveIntervals)
INITIALIZE_PASS_DEPENDENCY(VirtRegMap)
INITIALIZE_PASS_DEPENDENCY(LiveRegMatrix)
INITIALIZE_PASS_END(SIPreAllocateWWMRegs, DEBUG_TYPE,
"SI Pre-allocate WWM Registers", false, false)
char SIPreAllocateWWMRegs::ID = 0;
char &llvm::SIPreAllocateWWMRegsID = SIPreAllocateWWMRegs::ID;
FunctionPass *llvm::createSIPreAllocateWWMRegsPass() {
return new SIPreAllocateWWMRegs();
}
bool SIPreAllocateWWMRegs::processDef(MachineOperand &MO) {
if (!MO.isReg())
return false;
Register Reg = MO.getReg();
if (!TRI->isVGPR(*MRI, Reg))
return false;
if (Register::isPhysicalRegister(Reg))
return false;
if (VRM->hasPhys(Reg))
return false;
LiveInterval &LI = LIS->getInterval(Reg);
for (unsigned PhysReg : RegClassInfo.getOrder(MRI->getRegClass(Reg))) {
if (!MRI->isPhysRegUsed(PhysReg) &&
Matrix->checkInterference(LI, PhysReg) == LiveRegMatrix::IK_Free) {
Matrix->assign(LI, PhysReg);
assert(PhysReg != 0);
RegsToRewrite.push_back(Reg);
return true;
}
}
llvm_unreachable("physreg not found for WWM expression");
return false;
}
void SIPreAllocateWWMRegs::rewriteRegs(MachineFunction &MF) {
for (MachineBasicBlock &MBB : MF) {
for (MachineInstr &MI : MBB) {
for (MachineOperand &MO : MI.operands()) {
if (!MO.isReg())
continue;
const Register VirtReg = MO.getReg();
if (Register::isPhysicalRegister(VirtReg))
continue;
if (!VRM->hasPhys(VirtReg))
continue;
Register PhysReg = VRM->getPhys(VirtReg);
const unsigned SubReg = MO.getSubReg();
if (SubReg != 0) {
PhysReg = TRI->getSubReg(PhysReg, SubReg);
MO.setSubReg(0);
}
MO.setReg(PhysReg);
MO.setIsRenamable(false);
}
}
}
SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
for (unsigned Reg : RegsToRewrite) {
LIS->removeInterval(Reg);
const Register PhysReg = VRM->getPhys(Reg);
assert(PhysReg != 0);
MFI->ReserveWWMRegister(PhysReg);
}
RegsToRewrite.clear();
// Update the set of reserved registers to include WWM ones.
MRI->freezeReservedRegs(MF);
}
bool SIPreAllocateWWMRegs::runOnMachineFunction(MachineFunction &MF) {
LLVM_DEBUG(dbgs() << "SIPreAllocateWWMRegs: function " << MF.getName() << "\n");
const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
TII = ST.getInstrInfo();
TRI = &TII->getRegisterInfo();
MRI = &MF.getRegInfo();
LIS = &getAnalysis<LiveIntervals>();
Matrix = &getAnalysis<LiveRegMatrix>();
VRM = &getAnalysis<VirtRegMap>();
RegClassInfo.runOnMachineFunction(MF);
bool RegsAssigned = false;
// We use a reverse post-order traversal of the control-flow graph to
// guarantee that we visit definitions in dominance order. Since WWM
// expressions are guaranteed to never involve phi nodes, and we can only
// escape WWM through the special WWM instruction, this means that this is a
// perfect elimination order, so we can never do any better.
ReversePostOrderTraversal<MachineFunction*> RPOT(&MF);
for (MachineBasicBlock *MBB : RPOT) {
bool InWWM = false;
for (MachineInstr &MI : *MBB) {
if (MI.getOpcode() == AMDGPU::V_SET_INACTIVE_B32 ||
MI.getOpcode() == AMDGPU::V_SET_INACTIVE_B64)
RegsAssigned |= processDef(MI.getOperand(0));
if (MI.getOpcode() == AMDGPU::ENTER_WWM) {
LLVM_DEBUG(dbgs() << "entering WWM region: " << MI << "\n");
InWWM = true;
continue;
}
if (MI.getOpcode() == AMDGPU::EXIT_WWM) {
LLVM_DEBUG(dbgs() << "exiting WWM region: " << MI << "\n");
InWWM = false;
}
if (!InWWM)
continue;
LLVM_DEBUG(dbgs() << "processing " << MI << "\n");
for (MachineOperand &DefOpnd : MI.defs()) {
RegsAssigned |= processDef(DefOpnd);
}
}
}
if (!RegsAssigned)
return false;
rewriteRegs(MF);
return true;
}