The profile format has now a separate section called "Contexts" - there will be a corresponding one for flat profiles. The root has a separate tag because, in addition to not having a callsite ID as all the other context nodes have under it, it will have additional fields in subsequent patches. The rest of this patch amounts to a bit of refactorings in the reader/writer (for better reuse later) and tests fixups.
208 lines
8.3 KiB
C++
208 lines
8.3 KiB
C++
//===- PGOCtxProfWriter.cpp - Contextual Instrumentation profile writer ---===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Write a contextual profile to bitstream.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "llvm/ProfileData/PGOCtxProfWriter.h"
|
|
#include "llvm/Bitstream/BitCodeEnums.h"
|
|
#include "llvm/ProfileData/CtxInstrContextNode.h"
|
|
#include "llvm/Support/CommandLine.h"
|
|
#include "llvm/Support/Error.h"
|
|
#include "llvm/Support/YAMLTraits.h"
|
|
#include "llvm/Support/raw_ostream.h"
|
|
|
|
using namespace llvm;
|
|
using namespace llvm::ctx_profile;
|
|
|
|
static cl::opt<bool>
|
|
IncludeEmptyOpt("ctx-prof-include-empty", cl::init(false),
|
|
cl::desc("Also write profiles with all-zero counters. "
|
|
"Intended for testing/debugging."));
|
|
|
|
PGOCtxProfileWriter::PGOCtxProfileWriter(
|
|
raw_ostream &Out, std::optional<unsigned> VersionOverride,
|
|
bool IncludeEmpty)
|
|
: Writer(Out, 0),
|
|
IncludeEmpty(IncludeEmptyOpt.getNumOccurrences() > 0 ? IncludeEmptyOpt
|
|
: IncludeEmpty) {
|
|
static_assert(ContainerMagic.size() == 4);
|
|
Out.write(ContainerMagic.data(), ContainerMagic.size());
|
|
Writer.EnterBlockInfoBlock();
|
|
{
|
|
auto DescribeBlock = [&](unsigned ID, StringRef Name) {
|
|
Writer.EmitRecord(bitc::BLOCKINFO_CODE_SETBID,
|
|
SmallVector<unsigned, 1>{ID});
|
|
Writer.EmitRecord(bitc::BLOCKINFO_CODE_BLOCKNAME,
|
|
llvm::arrayRefFromStringRef(Name));
|
|
};
|
|
SmallVector<uint64_t, 16> Data;
|
|
auto DescribeRecord = [&](unsigned RecordID, StringRef Name) {
|
|
Data.clear();
|
|
Data.push_back(RecordID);
|
|
llvm::append_range(Data, Name);
|
|
Writer.EmitRecord(bitc::BLOCKINFO_CODE_SETRECORDNAME, Data);
|
|
};
|
|
DescribeBlock(PGOCtxProfileBlockIDs::ProfileMetadataBlockID, "Metadata");
|
|
DescribeRecord(PGOCtxProfileRecords::Version, "Version");
|
|
DescribeBlock(PGOCtxProfileBlockIDs::ContextsSectionBlockID, "Contexts");
|
|
DescribeBlock(PGOCtxProfileBlockIDs::ContextRootBlockID, "Root");
|
|
DescribeRecord(PGOCtxProfileRecords::Guid, "GUID");
|
|
DescribeRecord(PGOCtxProfileRecords::Counters, "Counters");
|
|
DescribeBlock(PGOCtxProfileBlockIDs::ContextNodeBlockID, "Context");
|
|
DescribeRecord(PGOCtxProfileRecords::Guid, "GUID");
|
|
DescribeRecord(PGOCtxProfileRecords::CalleeIndex, "CalleeIndex");
|
|
DescribeRecord(PGOCtxProfileRecords::Counters, "Counters");
|
|
}
|
|
Writer.ExitBlock();
|
|
Writer.EnterSubblock(PGOCtxProfileBlockIDs::ProfileMetadataBlockID, CodeLen);
|
|
const auto Version = VersionOverride.value_or(CurrentVersion);
|
|
Writer.EmitRecord(PGOCtxProfileRecords::Version,
|
|
SmallVector<unsigned, 1>({Version}));
|
|
}
|
|
|
|
void PGOCtxProfileWriter::writeCounters(ArrayRef<uint64_t> Counters) {
|
|
Writer.EmitCode(bitc::UNABBREV_RECORD);
|
|
Writer.EmitVBR(PGOCtxProfileRecords::Counters, VBREncodingBits);
|
|
Writer.EmitVBR(Counters.size(), VBREncodingBits);
|
|
for (uint64_t C : Counters)
|
|
Writer.EmitVBR64(C, VBREncodingBits);
|
|
}
|
|
|
|
void PGOCtxProfileWriter::writeGuid(ctx_profile::GUID Guid) {
|
|
Writer.EmitRecord(PGOCtxProfileRecords::Guid, SmallVector<uint64_t, 1>{Guid});
|
|
}
|
|
|
|
// recursively write all the subcontexts. We do need to traverse depth first to
|
|
// model the context->subcontext implicitly, and since this captures call
|
|
// stacks, we don't really need to be worried about stack overflow and we can
|
|
// keep the implementation simple.
|
|
void PGOCtxProfileWriter::writeImpl(std::optional<uint32_t> CallerIndex,
|
|
const ContextNode &Node) {
|
|
// A node with no counters is an error. We don't expect this to happen from
|
|
// the runtime, rather, this is interesting for testing the reader.
|
|
if (!IncludeEmpty && (Node.counters_size() > 0 && Node.entrycount() == 0))
|
|
return;
|
|
Writer.EnterSubblock(CallerIndex ? PGOCtxProfileBlockIDs::ContextNodeBlockID
|
|
: PGOCtxProfileBlockIDs::ContextRootBlockID,
|
|
CodeLen);
|
|
writeGuid(Node.guid());
|
|
if (CallerIndex)
|
|
Writer.EmitRecord(PGOCtxProfileRecords::CalleeIndex,
|
|
SmallVector<uint64_t, 1>{*CallerIndex});
|
|
writeCounters({Node.counters(), Node.counters_size()});
|
|
for (uint32_t I = 0U; I < Node.callsites_size(); ++I)
|
|
for (const auto *Subcontext = Node.subContexts()[I]; Subcontext;
|
|
Subcontext = Subcontext->next())
|
|
writeImpl(I, *Subcontext);
|
|
Writer.ExitBlock();
|
|
}
|
|
|
|
void PGOCtxProfileWriter::startContextSection() {
|
|
Writer.EnterSubblock(PGOCtxProfileBlockIDs::ContextsSectionBlockID, CodeLen);
|
|
}
|
|
|
|
void PGOCtxProfileWriter::endContextSection() { Writer.ExitBlock(); }
|
|
|
|
void PGOCtxProfileWriter::writeContextual(const ContextNode &RootNode) {
|
|
writeImpl(std::nullopt, RootNode);
|
|
}
|
|
|
|
namespace {
|
|
|
|
/// Representation of the context node suitable for yaml serialization /
|
|
/// deserialization.
|
|
struct SerializableCtxRepresentation {
|
|
ctx_profile::GUID Guid = 0;
|
|
std::vector<uint64_t> Counters;
|
|
std::vector<std::vector<SerializableCtxRepresentation>> Callsites;
|
|
};
|
|
struct SerializableProfileRepresentation {
|
|
std::vector<SerializableCtxRepresentation> Contexts;
|
|
};
|
|
|
|
ctx_profile::ContextNode *
|
|
createNode(std::vector<std::unique_ptr<char[]>> &Nodes,
|
|
const std::vector<SerializableCtxRepresentation> &DCList);
|
|
|
|
// Convert a DeserializableCtx into a ContextNode, potentially linking it to
|
|
// its sibling (e.g. callee at same callsite) "Next".
|
|
ctx_profile::ContextNode *
|
|
createNode(std::vector<std::unique_ptr<char[]>> &Nodes,
|
|
const SerializableCtxRepresentation &DC,
|
|
ctx_profile::ContextNode *Next = nullptr) {
|
|
auto AllocSize = ctx_profile::ContextNode::getAllocSize(DC.Counters.size(),
|
|
DC.Callsites.size());
|
|
auto *Mem = Nodes.emplace_back(std::make_unique<char[]>(AllocSize)).get();
|
|
std::memset(Mem, 0, AllocSize);
|
|
auto *Ret = new (Mem) ctx_profile::ContextNode(DC.Guid, DC.Counters.size(),
|
|
DC.Callsites.size(), Next);
|
|
std::memcpy(Ret->counters(), DC.Counters.data(),
|
|
sizeof(uint64_t) * DC.Counters.size());
|
|
for (const auto &[I, DCList] : llvm::enumerate(DC.Callsites))
|
|
Ret->subContexts()[I] = createNode(Nodes, DCList);
|
|
return Ret;
|
|
}
|
|
|
|
// Convert a list of SerializableCtxRepresentation into a linked list of
|
|
// ContextNodes.
|
|
ctx_profile::ContextNode *
|
|
createNode(std::vector<std::unique_ptr<char[]>> &Nodes,
|
|
const std::vector<SerializableCtxRepresentation> &DCList) {
|
|
ctx_profile::ContextNode *List = nullptr;
|
|
for (const auto &DC : DCList)
|
|
List = createNode(Nodes, DC, List);
|
|
return List;
|
|
}
|
|
} // namespace
|
|
|
|
LLVM_YAML_IS_SEQUENCE_VECTOR(SerializableCtxRepresentation)
|
|
LLVM_YAML_IS_SEQUENCE_VECTOR(std::vector<SerializableCtxRepresentation>)
|
|
template <> struct yaml::MappingTraits<SerializableCtxRepresentation> {
|
|
static void mapping(yaml::IO &IO, SerializableCtxRepresentation &SCR) {
|
|
IO.mapRequired("Guid", SCR.Guid);
|
|
IO.mapRequired("Counters", SCR.Counters);
|
|
IO.mapOptional("Callsites", SCR.Callsites);
|
|
}
|
|
};
|
|
|
|
template <> struct yaml::MappingTraits<SerializableProfileRepresentation> {
|
|
static void mapping(yaml::IO &IO, SerializableProfileRepresentation &SPR) {
|
|
IO.mapOptional("Contexts", SPR.Contexts);
|
|
}
|
|
};
|
|
|
|
Error llvm::createCtxProfFromYAML(StringRef Profile, raw_ostream &Out) {
|
|
yaml::Input In(Profile);
|
|
SerializableProfileRepresentation SPR;
|
|
In >> SPR;
|
|
if (In.error())
|
|
return createStringError(In.error(), "incorrect yaml content");
|
|
std::vector<std::unique_ptr<char[]>> Nodes;
|
|
std::error_code EC;
|
|
if (EC)
|
|
return createStringError(EC, "failed to open output");
|
|
PGOCtxProfileWriter Writer(Out);
|
|
|
|
if (!SPR.Contexts.empty()) {
|
|
Writer.startContextSection();
|
|
for (const auto &DC : SPR.Contexts) {
|
|
auto *TopList = createNode(Nodes, DC);
|
|
if (!TopList)
|
|
return createStringError(
|
|
"Unexpected error converting internal structure to ctx profile");
|
|
Writer.writeContextual(*TopList);
|
|
}
|
|
Writer.endContextSection();
|
|
}
|
|
if (EC)
|
|
return createStringError(EC, "failed to write output");
|
|
return Error::success();
|
|
}
|