mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 12:41:49 +01:00
60f657acba
Summary: Support for profile-driven cache prefetching (X86) This change is part of a larger system, consisting of a cache prefetches recommender, create_llvm_prof (https://github.com/google/autofdo), and LLVM. A proof of concept recommender is DynamoRIO's cache miss analyzer. It processes memory access traces obtained from a running binary and identifies patterns in cache misses. Based on them, it produces a csv file with recommendations. The expectation is that, by leveraging such recommendations, we can reduce the amount of clock cycles spent waiting for data from memory. A microbenchmark based on the DynamoRIO analyzer is available as a proof of concept: https://goo.gl/6TM2Xp. The recommender makes prefetch recommendations in terms of: * the binary offset of an instruction with a memory operand; * a delta; * and a type (nta, t0, t1, t2) meaning: a prefetch of that type should be inserted right before the instrution at that binary offset, and the prefetch should be for an address delta away from the memory address the instruction will access. For example: 0x400ab2,64,nta and assuming the instruction at 0x400ab2 is: movzbl (%rbx,%rdx,1),%edx means that the recommender determined it would be beneficial for a prefetchnta instruction to be inserted right before this instruction, as such: prefetchnta 0x40(%rbx,%rdx,1) movzbl (%rbx, %rdx, 1), %edx The workflow for prefetch cache instrumentation is as follows (the proof of concept script details these steps as well): 1. build binary, making sure -gmlt -fdebug-info-for-profiling is passed. The latter option will enable the X86DiscriminateMemOps pass, which ensures instructions with memory operands are uniquely identifiable (this causes ~2% size increase in total binary size due to the additional debug information). 2. collect memory traces, run analysis to obtain recommendations (see above-referenced DynamoRIO demo as a proof of concept). 3. use create_llvm_prof to convert recommendations to reference insertion locations in terms of debug info locations. 4. rebuild binary, using the exact same set of arguments used initially, to which -mllvm -prefetch-hints-file=<file> needs to be added, using the afdo file obtained at step 3. Note that if sample profiling feedback-driven optimization is also desired, that happens before step 1 above. In this case, the sample profile afdo file that was used to produce the binary at step 1 must also be included in step 4. The data needed by the compiler in order to identify prefetch insertion points is very similar to what is needed for sample profiles. For this reason, and given that the overall approach (memory tracing-based cache recommendation mechanisms) is under active development, we use the afdo format as a syntax for capturing this information. We avoid confusing semantics with sample profile afdo data by feeding the two types of information to the compiler through separate files and compiler flags. Should the approach prove successful, we can investigate improvements to this encoding mechanism. Reviewers: davidxl, wmi, craig.topper Reviewed By: davidxl, wmi, craig.topper Subscribers: davide, danielcdh, mgorny, aprantl, eraman, JDevlieghere, llvm-commits Differential Revision: https://reviews.llvm.org/D54052 llvm-svn: 347596
235 lines
8.7 KiB
C++
235 lines
8.7 KiB
C++
//===------- X86InsertPrefetch.cpp - Insert cache prefetch hints ----------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This pass applies cache prefetch instructions based on a profile. The pass
|
|
// assumes DiscriminateMemOps ran immediately before, to ensure debug info
|
|
// matches the one used at profile generation time. The profile is encoded in
|
|
// afdo format (text or binary). It contains prefetch hints recommendations.
|
|
// Each recommendation is made in terms of debug info locations, a type (i.e.
|
|
// nta, t{0|1|2}) and a delta. The debug info identifies an instruction with a
|
|
// memory operand (see X86DiscriminateMemOps). The prefetch will be made for
|
|
// a location at that memory operand + the delta specified in the
|
|
// recommendation.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "X86.h"
|
|
#include "X86InstrBuilder.h"
|
|
#include "X86InstrInfo.h"
|
|
#include "X86MachineFunctionInfo.h"
|
|
#include "X86Subtarget.h"
|
|
#include "llvm/CodeGen/MachineModuleInfo.h"
|
|
#include "llvm/IR/DebugInfoMetadata.h"
|
|
#include "llvm/ProfileData/SampleProf.h"
|
|
#include "llvm/ProfileData/SampleProfReader.h"
|
|
#include "llvm/Transforms/IPO/SampleProfile.h"
|
|
using namespace llvm;
|
|
using namespace sampleprof;
|
|
|
|
static cl::opt<std::string>
|
|
PrefetchHintsFile("prefetch-hints-file",
|
|
cl::desc("Path to the prefetch hints profile."),
|
|
cl::Hidden);
|
|
namespace {
|
|
|
|
class X86InsertPrefetch : public MachineFunctionPass {
|
|
void getAnalysisUsage(AnalysisUsage &AU) const override;
|
|
bool doInitialization(Module &) override;
|
|
|
|
bool runOnMachineFunction(MachineFunction &MF) override;
|
|
struct PrefetchInfo {
|
|
unsigned InstructionID;
|
|
int64_t Delta;
|
|
};
|
|
typedef SmallVectorImpl<PrefetchInfo> Prefetches;
|
|
bool findPrefetchInfo(const FunctionSamples *Samples, const MachineInstr &MI,
|
|
Prefetches &prefetches) const;
|
|
|
|
public:
|
|
static char ID;
|
|
X86InsertPrefetch(const std::string &PrefetchHintsFilename);
|
|
|
|
private:
|
|
std::string Filename;
|
|
std::unique_ptr<SampleProfileReader> Reader;
|
|
};
|
|
|
|
using PrefetchHints = SampleRecord::CallTargetMap;
|
|
|
|
// Return any prefetching hints for the specified MachineInstruction. The hints
|
|
// are returned as pairs (name, delta).
|
|
ErrorOr<PrefetchHints> getPrefetchHints(const FunctionSamples *TopSamples,
|
|
const MachineInstr &MI) {
|
|
if (const auto &Loc = MI.getDebugLoc())
|
|
if (const auto *Samples = TopSamples->findFunctionSamples(Loc))
|
|
return Samples->findCallTargetMapAt(FunctionSamples::getOffset(Loc),
|
|
Loc->getBaseDiscriminator());
|
|
return std::error_code();
|
|
}
|
|
|
|
} // end anonymous namespace
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Implementation
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
char X86InsertPrefetch::ID = 0;
|
|
|
|
X86InsertPrefetch::X86InsertPrefetch(const std::string &PrefetchHintsFilename)
|
|
: MachineFunctionPass(ID), Filename(PrefetchHintsFilename) {}
|
|
|
|
/// Return true if the provided MachineInstruction has cache prefetch hints. In
|
|
/// that case, the prefetch hints are stored, in order, in the Prefetches
|
|
/// vector.
|
|
bool X86InsertPrefetch::findPrefetchInfo(const FunctionSamples *TopSamples,
|
|
const MachineInstr &MI,
|
|
Prefetches &Prefetches) const {
|
|
assert(Prefetches.empty() &&
|
|
"Expected caller passed empty PrefetchInfo vector.");
|
|
static const std::pair<const StringRef, unsigned> HintTypes[] = {
|
|
{"_nta_", X86::PREFETCHNTA},
|
|
{"_t0_", X86::PREFETCHT0},
|
|
{"_t1_", X86::PREFETCHT1},
|
|
{"_t2_", X86::PREFETCHT2},
|
|
};
|
|
static const char *SerializedPrefetchPrefix = "__prefetch";
|
|
|
|
const ErrorOr<PrefetchHints> T = getPrefetchHints(TopSamples, MI);
|
|
if (!T)
|
|
return false;
|
|
int16_t max_index = -1;
|
|
// Convert serialized prefetch hints into PrefetchInfo objects, and populate
|
|
// the Prefetches vector.
|
|
for (const auto &S_V : *T) {
|
|
StringRef Name = S_V.getKey();
|
|
if (Name.consume_front(SerializedPrefetchPrefix)) {
|
|
int64_t D = static_cast<int64_t>(S_V.second);
|
|
unsigned IID = 0;
|
|
for (const auto &HintType : HintTypes) {
|
|
if (Name.startswith(HintType.first)) {
|
|
Name = Name.drop_front(HintType.first.size());
|
|
IID = HintType.second;
|
|
break;
|
|
}
|
|
}
|
|
if (IID == 0)
|
|
return false;
|
|
uint8_t index = 0;
|
|
Name.consumeInteger(10, index);
|
|
|
|
if (index >= Prefetches.size())
|
|
Prefetches.resize(index + 1);
|
|
Prefetches[index] = {IID, D};
|
|
max_index = std::max(max_index, static_cast<int16_t>(index));
|
|
}
|
|
}
|
|
assert(max_index + 1 >= 0 &&
|
|
"Possible overflow: max_index + 1 should be positive.");
|
|
assert(static_cast<size_t>(max_index + 1) == Prefetches.size() &&
|
|
"The number of prefetch hints received should match the number of "
|
|
"PrefetchInfo objects returned");
|
|
return !Prefetches.empty();
|
|
}
|
|
|
|
bool X86InsertPrefetch::doInitialization(Module &M) {
|
|
if (Filename.empty())
|
|
return false;
|
|
|
|
LLVMContext &Ctx = M.getContext();
|
|
ErrorOr<std::unique_ptr<SampleProfileReader>> ReaderOrErr =
|
|
SampleProfileReader::create(Filename, Ctx);
|
|
if (std::error_code EC = ReaderOrErr.getError()) {
|
|
std::string Msg = "Could not open profile: " + EC.message();
|
|
Ctx.diagnose(DiagnosticInfoSampleProfile(Filename, Msg,
|
|
DiagnosticSeverity::DS_Warning));
|
|
return false;
|
|
}
|
|
Reader = std::move(ReaderOrErr.get());
|
|
Reader->read();
|
|
return true;
|
|
}
|
|
|
|
void X86InsertPrefetch::getAnalysisUsage(AnalysisUsage &AU) const {
|
|
AU.setPreservesAll();
|
|
AU.addRequired<MachineModuleInfo>();
|
|
}
|
|
|
|
bool X86InsertPrefetch::runOnMachineFunction(MachineFunction &MF) {
|
|
if (!Reader)
|
|
return false;
|
|
const FunctionSamples *Samples = Reader->getSamplesFor(MF.getFunction());
|
|
if (!Samples)
|
|
return false;
|
|
|
|
bool Changed = false;
|
|
|
|
const TargetInstrInfo *TII = MF.getSubtarget().getInstrInfo();
|
|
SmallVector<PrefetchInfo, 4> Prefetches;
|
|
for (auto &MBB : MF) {
|
|
for (auto MI = MBB.instr_begin(); MI != MBB.instr_end();) {
|
|
auto Current = MI;
|
|
++MI;
|
|
|
|
int Offset = X86II::getMemoryOperandNo(Current->getDesc().TSFlags);
|
|
if (Offset < 0)
|
|
continue;
|
|
Prefetches.clear();
|
|
if (!findPrefetchInfo(Samples, *Current, Prefetches))
|
|
continue;
|
|
assert(!Prefetches.empty() &&
|
|
"The Prefetches vector should contain at least a value if "
|
|
"findPrefetchInfo returned true.");
|
|
for (auto &PrefInfo : Prefetches) {
|
|
unsigned PFetchInstrID = PrefInfo.InstructionID;
|
|
int64_t Delta = PrefInfo.Delta;
|
|
const MCInstrDesc &Desc = TII->get(PFetchInstrID);
|
|
MachineInstr *PFetch =
|
|
MF.CreateMachineInstr(Desc, Current->getDebugLoc(), true);
|
|
MachineInstrBuilder MIB(MF, PFetch);
|
|
unsigned Bias = X86II::getOperandBias(Current->getDesc());
|
|
int MemOpOffset = Offset + Bias;
|
|
|
|
assert(X86::AddrBaseReg == 0 && X86::AddrScaleAmt == 1 &&
|
|
X86::AddrIndexReg == 2 && X86::AddrDisp == 3 &&
|
|
X86::AddrSegmentReg == 4 &&
|
|
"Unexpected change in X86 operand offset order.");
|
|
|
|
// This assumes X86::AddBaseReg = 0, {...}ScaleAmt = 1, etc.
|
|
// FIXME(mtrofin): consider adding a:
|
|
// MachineInstrBuilder::set(unsigned offset, op).
|
|
MIB.addReg(Current->getOperand(MemOpOffset + X86::AddrBaseReg).getReg())
|
|
.addImm(
|
|
Current->getOperand(MemOpOffset + X86::AddrScaleAmt).getImm())
|
|
.addReg(
|
|
Current->getOperand(MemOpOffset + X86::AddrIndexReg).getReg())
|
|
.addImm(Current->getOperand(MemOpOffset + X86::AddrDisp).getImm() +
|
|
Delta)
|
|
.addReg(Current->getOperand(MemOpOffset + X86::AddrSegmentReg)
|
|
.getReg());
|
|
|
|
if (!Current->memoperands_empty()) {
|
|
MachineMemOperand *CurrentOp = *(Current->memoperands_begin());
|
|
MIB.addMemOperand(MF.getMachineMemOperand(
|
|
CurrentOp, CurrentOp->getOffset() + Delta, CurrentOp->getSize()));
|
|
}
|
|
|
|
// Insert before Current. This is because Current may clobber some of
|
|
// the registers used to describe the input memory operand.
|
|
MBB.insert(Current, PFetch);
|
|
Changed = true;
|
|
}
|
|
}
|
|
}
|
|
return Changed;
|
|
}
|
|
|
|
FunctionPass *llvm::createX86InsertPrefetchPass() {
|
|
return new X86InsertPrefetch(PrefetchHintsFile);
|
|
}
|