rust - https://github.com/rust-lang/rust

Age	Commit message (Collapse)	Author	Lines
2023-03-02	Remove dead pgo.sh file	Nikita Popov	-230/+0
	This has been replaced by stage-build.py.
2022-10-09	Use BOLT in x64 dist CI to optimize LLVM	Jakub Beránek	-5/+34

2022-07-28	bump rustc-perf commit	Jane Losare-Lusby	-2/+2

2022-07-24	Revert "Revert "Use ICF (identical code folding) for building rustc""	Jubilee Young	-0/+4
	This reverts commit rust-lang/rust@45575d23f316af7476ccd0a895234ac59c47a6be, thereby enabling identical code folding again.
2022-07-18	Revert "Use ICF (identical code folding) for building rustc"	Jakub Beránek	-4/+0

2022-07-17	Use LLD linker for compiling rustc on Linux x64 and use ICF for binary size ↵	Jakub Beránek	-0/+4
	optimization
2022-07-11	introduce PGO on the `dist-x86_64-msvc` builder	Rémy Rakic	-12/+46
	This adds windows-specific behavior into the PGO script, and enables it on CI.
2022-07-11	make linux PGO script more generic	Rémy Rakic	-39/+70
	This extracts the linux-isms into variables, so that the script can be extended to do PGO on windows. These variables will be overriden in a few spots, in windows-specific blocks.
2022-05-28	Add PID to LLVM PGO profiles generated in CI and measure PGO statistics	Jakub Beránek	-10/+36

2022-05-23	Add bitmaps and diesel to `rustc` PGO benchmarks	Jakub Beránek	-1/+2

2022-05-17	Add PID to rustc PGO profiles generated in CI	Jakub Beránek	-1/+5

2022-04-11	CI: do not compile libcore twice when performing LLVM PGO	Jakub Beránek	-6/+0

2022-04-07	Update rustc-perf version used in CI and also the corresponding PGO benchmarks	Jakub Beránek	-7/+12

2022-03-08	Create a function for gathering profiles and run only Full benchmarks in ↵	Jakub Beránek	-39/+38
	LLVM PGO
2022-03-07	Gather more profile data for LLVM PGO	Jakub Beránek	-10/+28

2022-02-06	Build libcore as 2021 in a few more places	Scott McMurray	-8/+8
	The `Cargo.toml` has `edition = "2021"`, so that's what these command lines should use too.
2021-10-14	Move LLVM profiling to a separate phase of compilation	Mark Rousskov	-8/+30

2021-08-24	PGO for LLVM builds on x86_64-unknown-linux-gnu in CI	Mark Rousskov	-49/+47
	This shows up to 5% less instruction counts on multiple benchmarks, and up to 19% wins on the -j1 wall times for rustc self-compilation. We can afford to spend the extra cycles building LLVM essentially once more for the x86_64-unknown-linux-gnu CI build today. The builder finishes in around 50 minutes on average, and this adds just 10 more minutes. Given the sizeable improvements in compiler performance, this is definitely worth it.
2021-07-10	Use clang 12.0.1 on dist-x86_64/i686-linux	Nikita Popov	-1/+1
	The LLD + ThinLTO __morestack bug has been fixed in 12.0.1, so we can now update our clang version. This also means that we no longer need to build Python 2.
2021-06-28	Add inflate to pgo	jackh726	-3/+5

2021-05-10	update perf version used for PGO	Ralf Jung	-1/+1

2021-04-24	update rustc-perf version that is used for PGO	Ralf Jung	-1/+1

2021-02-09	ci: allow unstable features in some PGO benchmarks	Pietro Albini	-2/+4

2021-01-30	Revert "Auto merge of #81489 - nikic:x86-64-dist-update, r=Mark-Simulacrum"	Nikita Popov	-1/+1
	This reverts commit cb6787ae82d388045cdf6b5dc73787d828d91feb, reversing changes made to 0248c6f178ab3a4d2ec702b7d418ff8375ab0515.
2021-01-28	Update Python and Clang on x86 dist images	Nikita Popov	-1/+1
	LLVM 12 no longer builds with Python 2, so install Python 3 in preparatin. However, Clang 10 does not build with Python 3, so we need update to Clang 11 as well, which supports both. Unfortunately, doing so results in errors while linking the libLLVM.so into other binaries: > __morestack: invalid needed version 2 This is fixed by using LLD instead. Possibly this is due to a binutils linker bug, but updating to the latest binutils version does not fix it.
2021-01-25	ci: use the monorepo's lockfile when building cargo for pgo profiling	Pietro Albini	-0/+14

2020-12-22	Utilize PGO for rustc linux dist builds	Mark Rousskov	-0/+47
	This implements support for applying PGO to the rustc compilation step (not standard library or any tooling, including rustdoc). Expanding PGO to more tools is not terribly difficult but will involve more work and greater CI time commitment. For the same reason of avoiding greater time commitment, this currently avoids implementing for platforms outside of x86_64-unknown-linux-gnu, though in practice it should be quite simple to extend over time to more platforms. The initial implementation is intentionally minimal here to avoid too much work investment before we start seeing wins for a subset of Rust users. The choice of workloads to profile here is somewhat arbitrary, but the general rationale was to aim for a small set that largely avoided time regressions on perf.rust-lang.org's full suite of crates. The set chosen is libcore, cargo (and its dependencies), and a few ad-hoc stress tests from perf.rlo. The stress tests are arguably the most controversial, but they benefit those cases (avoiding regressions) and do not really remove wins from other benchmarks. The primary next step after this PR lands is to implement support for PGO in LLVM. It is unclear whether we can afford a full LLVM rebuild in CI, though, so the approach taken there may need to be more staggered. rustc-only PGO seems well affordable on linux at least, giving us up to 20% wall time wins on some crates for 15 minutes of extra CI time (1 hour up from 45 minutes). The PGO data is uploaded to allow others to reuse it if attempting to reproduce the CI build or potentially, in the future, on other platforms where an off-by-one strategy is used for dist builds at minimal performance cost.