8daaa26efd
Nested TaskGroups run serially to prevent deadlock, as documented by https://reviews.llvm.org/D61115 and refined by https://reviews.llvm.org/D148984 to use threadIndex. Enable nested parallelism by having worker threads actively execute tasks from the work queue while waiting (work-stealing), instead of just blocking. Root-level TaskGroups (main thread) keep the efficient blocking Latch::sync(), so there is no overhead for the common non-nested case. In lld, https://reviews.llvm.org/D131247 worked around the limitation by passing a single root TaskGroup into OutputSection::writeTo and spawning 4MB-chunked tasks into it. However, SyntheticSection::writeTo calls with internal parallelism (e.g. GdbIndexSection, MergeNoTailSection) still ran serially on worker threads. With this change, their internal parallelFor/parallelForEach calls parallelize automatically via helpSync work-stealing. The increased parallelism can reorder error messages from parallel phases (e.g. relocation processing during section writes), so one lld test is updated to use --threads=1 for deterministic output.
LLVM Linker (lld)
This directory and its subdirectories contain source code for the LLVM Linker, a modular cross platform linker which is built as part of the LLVM compiler infrastructure project.
lld is open source software. You may freely distribute it under the terms of the license agreement found in LICENSE.txt.
Benchmarking
In order to make sure various developers can evaluate patches over the same tests, we create a collection of self contained programs.
It is hosted at https://s3-us-west-2.amazonaws.com/linker-tests/lld-speed-test.tar.xz
The current sha256 is 10eec685463d5a8bbf08d77f4ca96282161d396c65bd97dc99dbde644a31610f.