yjit-bench

yjit-bench copied to clipboard

Don't print individual run timings

4

It's a lot of output you don't need most of the time but more importantly, when running the script from a TTY it can be relatively slow.

casperisfine

The ruby-lsp benchmark fails on ruby master

3

With a fresh `ruby-dev` I get this error: ``` $ ./run_benchmarks.rb ruby-lsp --once Running benchmark "ruby-lsp" (1/1) /Users/rwstauner/.rubies/ruby-dev/bin/ruby -I harness /Users/rwstauner/src/github.com/Shopify/yjit-bench/benchmarks/ruby-lsp/benchmark.rb ruby 3.4.0dev (2024-01-18T15:35:46Z master 00814fd672) [arm64-darwin23] Command: bundle check...

rwstauner

Bumps the npm_and_yarn group with 1 update in the /benchmarks/erubi-rails directory: [ws](https://github.com/websockets/ws). Updates `ws` from 6.2.2 to 6.2.3 Release notes Sourced from ws's releases. 6.2.3 Bug fixes Backported e55e5106 to...

dependabot[bot]

Enable protoboeuf-encode benchmark on TruffleRuby

10

The benchmark was disabled in #325. Now the issue is fixed (in https://github.com/oracle/truffleruby/pull/3674).

andrykonchin

Improve benchmark stability with cpusets, nice, and disabling of hyper threading

4

This adds to `run_benchmarks.rb` several additional linux features which can help to make the benchmark results more reliable: - set scheduler priority (niceness) high - setup two cpusets, one for...

rwstauner

We want to track the performance of common operations in the Addressable gem, such as parsing, normalization, component access, and modification. We heavily use the Addressable gem in our projects,...

rafaelfranca

I'm trying to add a few features to this script but the code is hard to modify and understand without knowing if I broke something else. In order to improve...

rafaelfranca

Idea: benchmark JITs against fast_blank

2

We're likely not going to get the full perf but I wonder how much closer we get by enabling a JIT https://github.com/SamSaffron/fast_blank

tekknolagi