Remove a fast lookup table from MergeInputSection.

We used to have a map from section piece offsets to section pieces
as a cache for binary search. But I found that the map took quite a
large amount of memory and didn't make linking faster. So, in this
patch, I removed the map.

This patch saves 566 MiB of RAM (2.019 GiB -> 1.453 GiB) when linking
clang with debug info, and the link time is 4% faster in that test case.

Thanks for Sean Silva for pointing this out.

llvm-svn: 316305
This commit is contained in:
Rui Ueyama 2017-10-22 23:02:07 +00:00
parent 39ff401026
commit d96724db42
2 changed files with 2 additions and 20 deletions

View File

@ -963,27 +963,12 @@ const SectionPiece *MergeInputSection::getSectionPiece(uint64_t Offset) const {
// Because contents of a mergeable section is not contiguous in output,
// it is not just an addition to a base output offset.
uint64_t MergeInputSection::getOffset(uint64_t Offset) const {
if (!this->Live)
if (!Live)
return 0;
// Initialize OffsetMap lazily.
llvm::call_once(InitOffsetMap, [&] {
OffsetMap.reserve(Pieces.size());
for (size_t I = 0; I < Pieces.size(); ++I)
OffsetMap[Pieces[I].InputOff] = I;
});
// Find a string starting at a given offset.
auto It = OffsetMap.find(Offset);
if (It != OffsetMap.end())
return Pieces[It->second].OutputOff;
// If Offset is not at beginning of a section piece, it is not in the map.
// In that case we need to search from the original section piece vector.
const SectionPiece &Piece = *this->getSectionPiece(Offset);
const SectionPiece &Piece = *getSectionPiece(Offset);
if (!Piece.Live)
return 0;
uint64_t Addend = Offset - Piece.InputOff;
return Piece.OutputOff + Addend;
}

View File

@ -269,9 +269,6 @@ private:
void splitStrings(ArrayRef<uint8_t> A, size_t Size);
void splitNonStrings(ArrayRef<uint8_t> A, size_t Size);
mutable llvm::DenseMap<uint32_t, uint32_t> OffsetMap;
mutable llvm::once_flag InitOffsetMap;
llvm::DenseSet<uint64_t> LiveOffsets;
};