Candidates

Source code of the benchmark is available at GitHub.

This benchmark ran on Chrome 91(Headless - Puppeteer) - iMac 2017 27" i7 4.2Ghz with 24GB RAM 2400MHz DDR4 & Built-in Apple SSD.

Benchmark Mechanism

• The benchmark is automated through Puppeteer and using devtools-timeline-model to parse raw trace data. (Equavalent of manually checking javascript execution time through Dev Tools Performance tab.)
• Each task is iterated times and mean execution duration is taken.
• Each iteration Steps:
  1. Open a new page ("empty_page.html")
  2. Slowdown CPU speed by X
  3. Load required libraries through a script tags.
  4. Load respective task through a script tag
  5. Start tracing (to capture Dev Tools' performance metrics)
  6. Run Task (Puppeteer's code injection execution time is excluded by scheduling the task using setTimeout before tracing is started.)
  7. Wait pre-defined seconds for all task operations to be completed.
  8. Stop tracing
  9. Assert whether the task is completed.
  10. Parse raw trace data using devtools-timeline-model to extract javascript, layout & painting execution times.
  11. Close Page
• The mean execution duration is in microseconds. (1000 Microseconds = 1 Millisecond)
• Coefficient of variation is shown below the execution duration.
  • This is how much iterations deviated from its mean execution duration. Lower deviation means the test is stable.
  • Variation for smaller operations can be high. If that's the case, repeat the task equally for all candidates to increase the execution time.
  • Refer _task_template.js for details.
• Factor of slowness is compared against the selected base candidate. Eg:
  • Vanilla JS execution duration = 400ms
  • Candidate 1 execution duration= 600ms
  • Candidate 1 is 1.5x slower than Vanilla JS

pFreak Config & Candidate Versions

Compiled results.json

Loading, please wait...

This report was produced by pFreak Benchmarking & Testing Framework.