[PATCH] D115993: [ELF] Optimize RelocationSection<ELFT>::writeTo

[Fangrui Song via Phabricator via llvm-commits]

MaskRay created this revision.
MaskRay added reviewers: arichardson, ikudrin, peter.smith.
Herald added a subscriber: emaste.
MaskRay requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

When linking a 1.2G output (nearly no debug info, 2846621 dynamic relocations) using `--threads=8`, I measured

  9.131462 Total ExecuteLinker
  1.449913 Total Write output file
  1.445784 Total Write sections
  0.657152 Write sections {"detail":".rela.dyn"}

This change decreases the .rela.dyn time to 0.25, leading to 4% speed up in the total time.

- The parallelSort is slow because of expensive r_sym/r_offset computation. Cache the values.
- The iteration is slow. Move r_sym/r_addend computation ahead of time and parallelize it.

With the change, the new encodeDynamicReloc is cheap (0.05s). So don't parallelize it.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D115993

Files:
  lld/ELF/OutputSections.cpp
  lld/ELF/SyntheticSections.cpp
  lld/ELF/SyntheticSections.h

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D115993.395302.patch
Type: text/x-patch
Size: 6239 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211218/af9b3a08/attachment.bin>