maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Inline initOffsetMap. 

In the lld perf builder r328686 had a negative impact in
stalled-cycles-frontend. Somehow that stat is not showing on my
machine, but the attached patch shows an improvement on cache-misses,
which is probably a reasonable proxy.

My working theory is that given a large input the pieces vector is out
of cache by the time initOffsetMap runs.

Both finalizeContents implementation have a convenient location for
initializing the OffsetMap, so this seems the best solution.

llvm-svn: 329117
This commit is contained in:
Rafael Espindola 2018-04-03 21:38:18 +00:00
parent d506bf8e3d
commit 6cd7af51e1
3 changed files with 18 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lld/ELF/InputSection.cpp
View File

@ -985,12 +985,6 @@ uint64_t MergeInputSection::getOffset(uint64_t Offset) const {
return Piece.OutputOff + Addend;
}
void MergeInputSection::initOffsetMap() {
OffsetMap.reserve(Pieces.size());
for (size_t I = 0; I < Pieces.size(); ++I)
OffsetMap[Pieces[I].InputOff] = I;
}
template InputSection::InputSection(ObjFile<ELF32LE> &, const ELF32LE::Shdr &,
StringRef);
template InputSection::InputSection(ObjFile<ELF32BE> &, const ELF32BE::Shdr &,

4
lld/ELF/InputSection.h
View File

@ -236,6 +236,7 @@ public:
// Splittable sections are handled as a sequence of data
// rather than a single large blob of data.
std::vector<SectionPiece> Pieces;
llvm::DenseMap<uint32_t, uint32_t> OffsetMap;
// Returns I'th piece's data. This function is very hot when
// string merging is enabled, so we want to inline.
@ -254,14 +255,11 @@ public:
}
SyntheticSection *getParent() const;
void initOffsetMap();
private:
void splitStrings(ArrayRef<uint8_t> A, size_t Size);
void splitNonStrings(ArrayRef<uint8_t> A, size_t Size);
llvm::DenseMap<uint32_t, uint32_t> OffsetMap;
llvm::DenseSet<uint32_t> LiveOffsets;
};

29
lld/ELF/SyntheticSections.cpp
View File

@ -2438,10 +2438,15 @@ void MergeTailSection::finalizeContents() {
// finalize() fixed tail-optimized strings, so we can now get
// offsets of strings. Get an offset for each string and save it
// to a corresponding StringPiece for easy access.
for (MergeInputSection *Sec : Sections)
for (size_t I = 0, E = Sec->Pieces.size(); I != E; ++I)
if (Sec->Pieces[I].Live)
Sec->Pieces[I].OutputOff = Builder.getOffset(Sec->getData(I));
for (MergeInputSection *Sec : Sections) {
Sec->OffsetMap.reserve(Sec->Pieces.size());
for (size_t I = 0, E = Sec->Pieces.size(); I != E; ++I) {
SectionPiece &P = Sec->Pieces[I];
Sec->OffsetMap[P.InputOff] = I;
if (P.Live)
P.OutputOff = Builder.getOffset(Sec->getData(I));
}
}
}
void MergeNoTailSection::writeTo(uint8_t *Buf) {
@ -2494,10 +2499,13 @@ void MergeNoTailSection::finalizeContents() {
// So far, section pieces have offsets from beginning of shards, but
// we want offsets from beginning of the whole section. Fix them.
parallelForEach(Sections, [&](MergeInputSection *Sec) {
for (size_t I = 0, E = Sec->Pieces.size(); I != E; ++I)
if (Sec->Pieces[I].Live)
Sec->Pieces[I].OutputOff +=
ShardOffsets[getShardId(Sec->Pieces[I].Hash)];
Sec->OffsetMap.reserve(Sec->Pieces.size());
for (size_t I = 0, E = Sec->Pieces.size(); I != E; ++I) {
SectionPiece &P = Sec->Pieces[I];
Sec->OffsetMap[P.InputOff] = I;
if (P.Live)
P.OutputOff += ShardOffsets[getShardId(P.Hash)];
}
});
}
@ -2573,11 +2581,8 @@ void elf::mergeSections() {
}
(*I)->addSection(MS);
}
for (auto *MS : MergeSections) {
for (auto *MS : MergeSections)
MS->finalizeContents();
parallelForEach(MS->Sections,
[](MergeInputSection *Sec) { Sec->initOffsetMap(); });
}
std::vector<InputSectionBase *> &V = InputSections;
V.erase(std::remove(V.begin(), V.end(), nullptr), V.end());