1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-21 12:02:58 +02:00
llvm-mirror/tools/llvm-mca/Instruction.cpp
Andrea Di Biagio 45f0e5261e [llvm-mca] LLVM Machine Code Analyzer.
llvm-mca is an LLVM based performance analysis tool that can be used to
statically measure the performance of code, and to help triage potential
problems with target scheduling models.

llvm-mca uses information which is already available in LLVM (e.g. scheduling
models) to statically measure the performance of machine code in a specific cpu.
Performance is measured in terms of throughput as well as processor resource
consumption. The tool currently works for processors with an out-of-order
backend, for which there is a scheduling model available in LLVM.

The main goal of this tool is not just to predict the performance of the code
when run on the target, but also help with diagnosing potential performance
issues.

Given an assembly code sequence, llvm-mca estimates the IPC (instructions per
cycle), as well as hardware resources pressure. The analysis and reporting style
were mostly inspired by the IACA tool from Intel.

This patch is related to the RFC on llvm-dev visible at this link:
http://lists.llvm.org/pipermail/llvm-dev/2018-March/121490.html

Differential Revision: https://reviews.llvm.org/D43951

llvm-svn: 326998
2018-03-08 13:05:02 +00:00

135 lines
3.7 KiB
C++

//===--------------------- Instruction.cpp ----------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines abstractions used by the Backend to model register reads,
// register writes and instructions.
//
//===----------------------------------------------------------------------===//
#include "Instruction.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
namespace mca {
using namespace llvm;
void ReadState::writeStartEvent(unsigned Cycles) {
assert(DependentWrites);
assert(CyclesLeft == UNKNOWN_CYCLES);
// This read may be dependent on more than one write. This typically occurs
// when a definition is the result of multiple writes where at least one
// write does a partial register update.
// The HW is forced to do some extra bookkeeping to track of all the
// dependent writes, and implement a merging scheme for the partial writes.
--DependentWrites;
TotalCycles = std::max(TotalCycles, Cycles);
if (!DependentWrites)
CyclesLeft = TotalCycles;
}
void WriteState::onInstructionIssued() {
assert(CyclesLeft == UNKNOWN_CYCLES);
// Update the number of cycles left based on the WriteDescriptor info.
CyclesLeft = WD.Latency;
// Now that the time left before write-back is know, notify
// all the users.
for (const std::pair<ReadState *, int> &User : Users) {
ReadState *RS = User.first;
unsigned ReadCycles = std::max(0, CyclesLeft - User.second);
RS->writeStartEvent(ReadCycles);
}
}
void WriteState::addUser(ReadState *User, int ReadAdvance) {
// If CyclesLeft is different than -1, then we don't need to
// update the list of users. We can just notify the user with
// the actual number of cycles left (which may be zero).
if (CyclesLeft != UNKNOWN_CYCLES) {
unsigned ReadCycles = std::max(0, CyclesLeft - ReadAdvance);
User->writeStartEvent(ReadCycles);
return;
}
std::pair<ReadState *, int> NewPair(User, ReadAdvance);
Users.insert(NewPair);
}
void WriteState::cycleEvent() {
// Note: CyclesLeft can be a negative number. It is an error to
// make it an unsigned quantity because users of this write may
// specify a negative ReadAdvance.
if (CyclesLeft != UNKNOWN_CYCLES)
CyclesLeft--;
}
void ReadState::cycleEvent() {
// If CyclesLeft is unknown, then bail out immediately.
if (CyclesLeft == UNKNOWN_CYCLES)
return;
// If there are still dependent writes, or we reached cycle zero,
// then just exit.
if (DependentWrites || CyclesLeft == 0)
return;
CyclesLeft--;
}
#ifndef NDEBUG
void WriteState::dump() const {
dbgs() << "{ OpIdx=" << WD.OpIndex << ", Lat=" << WD.Latency << ", RegID "
<< getRegisterID() << ", Cycles Left=" << getCyclesLeft() << " }\n";
}
#endif
bool Instruction::isReady() {
if (Stage == IS_READY)
return true;
assert(Stage == IS_AVAILABLE);
for (const UniqueUse &Use : Uses)
if (!Use.get()->isReady())
return false;
setReady();
return true;
}
void Instruction::execute() {
assert(Stage == IS_READY);
Stage = IS_EXECUTING;
for (UniqueDef &Def : Defs)
Def->onInstructionIssued();
}
bool Instruction::isZeroLatency() const {
return Desc.MaxLatency == 0 && Defs.size() == 0 && Uses.size() == 0;
}
void Instruction::cycleEvent() {
if (isDispatched()) {
for (UniqueUse &Use : Uses)
Use->cycleEvent();
return;
}
if (isExecuting()) {
for (UniqueDef &Def : Defs)
Def->cycleEvent();
CyclesLeft--;
}
if (!CyclesLeft)
Stage = IS_EXECUTED;
}
} // namespace mca