blob: 9f63f7ef7befcae1be2512ca68c2c798bcd23136 [file] [log] [blame]
//===-- CSPreInliner.h - Profile guided preinliner ---------------- C++ -*-===//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#include "ProfiledBinary.h"
#include "llvm/ADT/PriorityQueue.h"
#include "llvm/ProfileData/ProfileCommon.h"
#include "llvm/ProfileData/SampleProf.h"
#include "llvm/Transforms/IPO/ProfiledCallGraph.h"
#include "llvm/Transforms/IPO/SampleContextTracker.h"
using namespace llvm;
using namespace sampleprof;
namespace llvm {
namespace sampleprof {
// Inline candidate seen from profile
struct ProfiledInlineCandidate {
ProfiledInlineCandidate(const FunctionSamples *Samples, uint64_t Count,
uint32_t Size)
: CalleeSamples(Samples), CallsiteCount(Count), SizeCost(Size) {}
// Context-sensitive function profile for inline candidate
const FunctionSamples *CalleeSamples;
// Call site count for an inline candidate
// TODO: make sure entry count for context profile and call site
// target count for corresponding call are consistent.
uint64_t CallsiteCount;
// Size proxy for function under particular call context.
uint64_t SizeCost;
// Inline candidate comparer using call site weight
struct ProfiledCandidateComparer {
bool operator()(const ProfiledInlineCandidate &LHS,
const ProfiledInlineCandidate &RHS) {
if (LHS.CallsiteCount != RHS.CallsiteCount)
return LHS.CallsiteCount < RHS.CallsiteCount;
if (LHS.SizeCost != RHS.SizeCost)
return LHS.SizeCost > RHS.SizeCost;
// Tie breaker using GUID so we have stable/deterministic inlining order
assert(LHS.CalleeSamples && RHS.CalleeSamples &&
"Expect non-null FunctionSamples");
return LHS.CalleeSamples->getGUID(LHS.CalleeSamples->getName()) <
using ProfiledCandidateQueue =
PriorityQueue<ProfiledInlineCandidate, std::vector<ProfiledInlineCandidate>,
// Pre-compilation inliner based on context-sensitive profile.
// The PreInliner estimates inline decision using hotness from profile
// and cost estimation from machine code size. It helps merges context
// profile globally and achieves better post-inine profile quality, which
// otherwise won't be possible for ThinLTO. It also reduce context profile
// size by only keep context that is estimated to be inlined.
class CSPreInliner {
CSPreInliner(SampleProfileMap &Profiles, ProfiledBinary &Binary,
uint64_t HotThreshold, uint64_t ColdThreshold);
void run();
bool getInlineCandidates(ProfiledCandidateQueue &CQueue,
const FunctionSamples *FCallerContextSamples);
std::vector<StringRef> buildTopDownOrder();
void processFunction(StringRef Name);
bool shouldInline(ProfiledInlineCandidate &Candidate);
uint32_t getFuncSize(const FunctionSamples &FSamples);
bool UseContextCost;
SampleContextTracker ContextTracker;
SampleProfileMap &ProfileMap;
ProfiledBinary &Binary;
// Count thresholds to answer isHotCount and isColdCount queries.
// Mirrors the threshold in ProfileSummaryInfo.
uint64_t HotCountThreshold;
uint64_t ColdCountThreshold;
} // end namespace sampleprof
} // end namespace llvm