RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity

AMDGPU: Process SDWA block at a time

Browse Source 
Right now this loops over the entire function every time there
is a change, which is not very efficient. There's no practical
reason to track this so globally, since the code motion optimization
passes should be sinking instructions with single uses and
the pass currently will not fold with multiple uses.

llvm-svn: 324667
This commit is contained in:
Matt Arsenault 2018-02-08 22:46:41 +00:00
parent 8c56b6e356
commit 7aa4cb8630
1 changed files with 30 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
lib/Target/AMDGPU/SIPeepholeSDWA.cpp
View File

@ -86,7 +86,7 @@ public:
}
bool runOnMachineFunction(MachineFunction &MF) override;
void matchSDWAOperands(MachineFunction &MF);
void matchSDWAOperands(MachineBasicBlock &MBB);
std::unique_ptr<SDWAOperand> matchSDWAOperand(MachineInstr &MI);
bool isConvertibleToSDWA(const MachineInstr &MI, const SISubtarget &ST) const;
bool convertToSDWA(MachineInstr &MI, const SDWAOperandsVector &SDWAOperands);
@ -804,14 +804,12 @@ SIPeepholeSDWA::matchSDWAOperand(MachineInstr &MI) {
return std::unique_ptr<SDWAOperand>(nullptr);
}
void SIPeepholeSDWA::matchSDWAOperands(MachineFunction &MF) {
for (MachineBasicBlock &MBB : MF) {
for (MachineInstr &MI : MBB) {
if (auto Operand = matchSDWAOperand(MI)) {
DEBUG(dbgs() << "Match: " << MI << "To: " << *Operand << '\n');
SDWAOperands[&MI] = std::move(Operand);
++NumSDWAPatternsFound;
}
void SIPeepholeSDWA::matchSDWAOperands(MachineBasicBlock &MBB) {
for (MachineInstr &MI : MBB) {
if (auto Operand = matchSDWAOperand(MI)) {
DEBUG(dbgs() << "Match: " << MI << "To: " << *Operand << '\n');
SDWAOperands[&MI] = std::move(Operand);
++NumSDWAPatternsFound;
}
}
}
@ -1059,35 +1057,36 @@ bool SIPeepholeSDWA::runOnMachineFunction(MachineFunction &MF) {
TII = ST.getInstrInfo();
// Find all SDWA operands in MF.
bool Changed = false;
bool Ret = false;
do {
matchSDWAOperands(MF);
for (MachineBasicBlock &MBB : MF) {
bool Changed = false;
do {
matchSDWAOperands(MBB);
for (const auto &OperandPair : SDWAOperands) {
const auto &Operand = OperandPair.second;
MachineInstr *PotentialMI = Operand->potentialToConvert(TII);
if (PotentialMI && isConvertibleToSDWA(*PotentialMI, ST)) {
PotentialMatches[PotentialMI].push_back(Operand.get());
for (const auto &OperandPair : SDWAOperands) {
const auto &Operand = OperandPair.second;
MachineInstr *PotentialMI = Operand->potentialToConvert(TII);
if (PotentialMI && isConvertibleToSDWA(*PotentialMI, ST)) {
PotentialMatches[PotentialMI].push_back(Operand.get());
}
}
}
for (auto &PotentialPair : PotentialMatches) {
MachineInstr &PotentialMI = *PotentialPair.first;
convertToSDWA(PotentialMI, PotentialPair.second);
}
for (auto &PotentialPair : PotentialMatches) {
MachineInstr &PotentialMI = *PotentialPair.first;
convertToSDWA(PotentialMI, PotentialPair.second);
}
PotentialMatches.clear();
SDWAOperands.clear();
PotentialMatches.clear();
SDWAOperands.clear();
Changed = !ConvertedInstructions.empty();
Changed = !ConvertedInstructions.empty();
if (Changed)
Ret = true;
while (!ConvertedInstructions.empty())
legalizeScalarOperands(*ConvertedInstructions.pop_back_val(), ST);
} while (Changed);
if (Changed)
Ret = true;
while (!ConvertedInstructions.empty())
legalizeScalarOperands(*ConvertedInstructions.pop_back_val(), ST);
} while (Changed);
}
return Ret;
}