forked from OSchip/llvm-project
[ELF] Use parallel_for_each for writing.
This changes improves performance of lld, when self-hosting lld, when compared with the bfd linker. BFD linker on average takes 8 seconds in elapsed time. lld takes 3 seconds elapased time average. Without this change, lld takes ~5 seconds average. The runtime comparisons were done on a release build and measured by running linking thrice. lld self-host without the change ---------------------------------- real 0m3.196s user 0m4.580s sys 0m0.832s lld self-host with lld ----------------------- user 0m3.024s user 0m3.252s sys 0m0.796s time taken to build lld with bfd -------------------------------- real 0m8.419s user 0m7.748s sys 0m0.632s llvm-svn: 232460
This commit is contained in:
parent
e0afb1fe6c
commit
baf1aaaf1f
|
@ -586,8 +586,10 @@ std::error_code OutputELFWriter<ELFT>::writeOutput(const File &file,
|
|||
_elfHeader->write(this, _layout, *buffer);
|
||||
_programHeader->write(this, _layout, *buffer);
|
||||
|
||||
for (auto section : _layout.sections())
|
||||
section->write(this, _layout, *buffer);
|
||||
auto sections = _layout.sections();
|
||||
parallel_for_each(
|
||||
sections.begin(), sections.end(),
|
||||
[&](Chunk<ELFT> *section) { section->write(this, _layout, *buffer); });
|
||||
writeTask.end();
|
||||
|
||||
ScopedTask commitTask(getDefaultDomain(), "ELF Writer commit to disk");
|
||||
|
|
|
@ -234,17 +234,17 @@ public:
|
|||
/// routine gets called after the linker fixes up the virtual address
|
||||
/// of the section
|
||||
virtual void assignVirtualAddress(uint64_t addr) override {
|
||||
for (auto &ai : _atoms) {
|
||||
parallel_for_each(_atoms.begin(), _atoms.end(), [&](AtomLayout *ai) {
|
||||
ai->_virtualAddr = addr + ai->_fileOffset;
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// \brief Set the file offset of each Atom in the section. This routine
|
||||
/// gets called after the linker fixes up the section offset
|
||||
void assignFileOffsets(uint64_t offset) override {
|
||||
for (auto &ai : _atoms) {
|
||||
parallel_for_each(_atoms.begin(), _atoms.end(), [&](AtomLayout *ai) {
|
||||
ai->_fileOffset = offset + ai->_fileOffset;
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// \brief Find the Atom address given a name, this is needed to properly
|
||||
|
|
Loading…
Reference in New Issue