1. 31 Jul, 2023 1 commit
    • Jackson Gardner's avatar
      Reland --omit-type-checks for benchmarks. (#131493) · b928b3c1
      Jackson Gardner authored
      Because the cost of type checks dominate our dart2wasm benchmarks, we've
      decided to pass `--omit-type-checks` for now.
      
      This was previously reverted because the skwasm benchmarks were broken
      in general for a separate reason, and my getting rid of `bringup: true`
      broke the tree. I ended up fixing the benchmarks and getting rid of
      `bringup: true` in a separate commit, so this just adds the flag only.
      b928b3c1
  2. 26 Jul, 2023 2 commits
  3. 14 Jul, 2023 1 commit
  4. 07 Jul, 2023 1 commit
  5. 29 Jun, 2023 1 commit
    • Jackson Gardner's avatar
      Skwasm benchmarks. (#129681) · 1b887c72
      Jackson Gardner authored
      This enables benchmarks for the Skwasm renderer, compiled with
      dart2wasm.
      
      Platform views aren't supported in Skwasm yet, so we are skipping those
      benchmarks for now.
      1b887c72
  6. 24 Jun, 2023 1 commit
  7. 02 Jun, 2023 1 commit
  8. 31 May, 2023 1 commit
    • Jackson Gardner's avatar
      Improve web benchmarks measurements (#127900) · e8f4d803
      Jackson Gardner authored
      By default, the browser fuzzes the timer APIs such that they have a granularity of approximately 100 microseconds (this is due to Spectre mitigation techniques). However, many of the thing we are trying to measure actually have a much finer granularity than 100 microseconds. As a result, many of our benchmarks are extremely noisy and don't provide accurate data.
      
      By serving the initial script files with the `Cross-Origin-Opener-Policy: same-origin` and `Cross-Origin-Embedder-Policy: require-corp` HTTP headers, the browser runs the benchmarks in a `crossOriginIsolated` context, which restores the fine granularity of APIs such as `performance.now()` to microsecond precision.
      
      Also, we were considering anything an outlier that was more than one standard deviation away from the mean. In a normal distribution, that means we are only capturing 68% of the data and the rest are considered outliers. This is not ideal. Doing two standard deviations away captures 95% of the data, and the outliers are in the remaining 5%, which seems much more reasonable.
      e8f4d803
  9. 26 May, 2023 1 commit
  10. 23 May, 2023 1 commit
  11. 15 May, 2023 2 commits
  12. 10 May, 2023 1 commit
  13. 03 May, 2023 2 commits
  14. 28 Apr, 2023 1 commit
  15. 24 Apr, 2023 1 commit
  16. 07 Apr, 2023 2 commits
  17. 31 Mar, 2023 2 commits
  18. 22 Mar, 2023 1 commit
  19. 21 Mar, 2023 3 commits
  20. 20 Mar, 2023 1 commit
  21. 17 Mar, 2023 2 commits
  22. 15 Mar, 2023 2 commits
  23. 10 Mar, 2023 2 commits
  24. 09 Mar, 2023 1 commit
  25. 08 Mar, 2023 3 commits
  26. 28 Feb, 2023 1 commit
  27. 27 Feb, 2023 2 commits