-
Notifications
You must be signed in to change notification settings - Fork 13.8k
Add self-profile events for target-machine creation #146845
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
These code paths are surprisingly hot in the `large-workspace` benchmark; it would be handy to see some detailed timings and execution counts.
This PR won't have a perf impact on its own, but I would like to see a preview of the measurements it produces. @bors try @rust-timer queue |
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
Add self-profile events for target-machine creation
This comment has been minimized.
This comment has been minimized.
Finished benchmarking commit (532db74): comparison URL. Overall result: ❌ regressions - no action neededBenchmarking this pull request means it may be perf-sensitive – we'll automatically label it not fit for rolling up. You can override this, but we strongly advise not to, due to possible changes in compiler perf. @bors rollup=never Instruction countOur most reliable metric. Used to determine the overall result above. However, even this metric can be noisy.
Max RSS (memory usage)Results (primary 3.5%)A less reliable metric. May be of interest, but not used to determine the overall result above.
CyclesResults (primary 5.0%, secondary -0.2%)A less reliable metric. May be of interest, but not used to determine the overall result above.
Binary sizeThis benchmark run did not return any relevant results for this metric. Bootstrap: 470.725s -> 470.112s (-0.13%) |
No reason not to roll this up, if/when it's approved: @bors rollup=always |
Seems reasonable, thanks! @bors r+ |
Rollup of 9 pull requests Successful merges: - #145411 (regression test for Cow<[u8]> layout) - #146397 (std_detect on Darwin AArch64: update features) - #146791 (emit attribute for readonly non-pure inline assembly) - #146831 (Support ctr and lr as clobber-only registers in PowerPC inline assembly) - #146838 (Introduce "wrapper" helpers to rustdoc) - #146845 (Add self-profile events for target-machine creation) - #146846 (btree InternalNode::new safety comments) - #146858 (Make mips64el-unknown-linux-muslabi64 link dynamically) - #146878 (assert_unsafe_precondition: fix some incorrect check_language_ub) r? `@ghost` `@rustbot` modify labels: rollup
Rollup merge of #146845 - Zalathar:prof-target-machine, r=Kobzol Add self-profile events for target-machine creation These code paths are surprisingly hot in the `large-workspace` benchmark (e.g. see perf changes from #146700), suggesting room for more improvement. It would be handy to see some detailed timings and execution counts.
…bzol Add self-profile events for target-machine creation These code paths are surprisingly hot in the `large-workspace` benchmark (e.g. see perf changes from rust-lang#146700), suggesting room for more improvement. It would be handy to see some detailed timings and execution counts.
Rollup of 9 pull requests Successful merges: - rust-lang#145411 (regression test for Cow<[u8]> layout) - rust-lang#146397 (std_detect on Darwin AArch64: update features) - rust-lang#146791 (emit attribute for readonly non-pure inline assembly) - rust-lang#146831 (Support ctr and lr as clobber-only registers in PowerPC inline assembly) - rust-lang#146838 (Introduce "wrapper" helpers to rustdoc) - rust-lang#146845 (Add self-profile events for target-machine creation) - rust-lang#146846 (btree InternalNode::new safety comments) - rust-lang#146858 (Make mips64el-unknown-linux-muslabi64 link dynamically) - rust-lang#146878 (assert_unsafe_precondition: fix some incorrect check_language_ub) r? `@ghost` `@rustbot` modify labels: rollup
These code paths are surprisingly hot in the
large-workspace
benchmark (e.g. see perf changes from #146700), suggesting room for more improvement. It would be handy to see some detailed timings and execution counts.