x86 (32/64): go back to passing SIMD vectors by-ptr by RalfJung · Pull Request #141309 · rust-lang/rust (original) (raw)

What is this?This is an experimental post-merge analysis report that shows differences in test outcomes between the merged PR and its parent PR.

Comparing 4b27a04 (parent) -> ff223d3 (this PR)

Test differences

Show 13 test diffs

Stage 1

Stage 2

Job group index

Run

cargo run --manifest-path src/ci/citool/Cargo.toml --
test-dashboard ff223d35cd684f8c7c07ed4b7fd4475e482359ab --output-dir test-dashboard

And then open test-dashboard/index.html in your browser to see an overview of all executed tests.

Job duration changes

  1. dist-aarch64-linux: 8219.2s -> 5897.4s (-28.2%)
  2. mingw-check-1: 1602.1s -> 1912.3s (19.4%)
  3. x86_64-gnu-aux: 5266.5s -> 6091.7s (15.7%)
  4. i686-gnu-2: 5444.5s -> 6097.1s (12.0%)
  5. i686-gnu-1: 7187.9s -> 7972.8s (10.9%)
  6. i686-gnu-nopt-1: 7240.1s -> 8023.8s (10.8%)
  7. arm-android: 4815.9s -> 5302.6s (10.1%)
  8. x86_64-rust-for-linux: 2301.0s -> 2519.8s (9.5%)
  9. x86_64-gnu-llvm-20-2: 5550.0s -> 6034.0s (8.7%)
  10. armhf-gnu: 3879.3s -> 4205.3s (8.4%) How to interpret the job duration changes?

Job durations can vary a lot, based on the actual runner instance
that executed the job, system noise, invalidated caches, etc. The table above is provided
mostly for t-infra members, for simpler debugging of potential CI slow-downs.