Benchmark in Milliseconds(matklad.github.io)

143 points by surprisetalk 21 days ago | 47 comments

A blog post by matklad arguing that micro benchmarks should be sized to run around 300 milliseconds, explaining the reasons for this rule of thumb.

Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses(quesma.com)

271 points by stared 1 month ago | 128 comments

Building Linux kernel on macOS natively(seiya.me)

21 points by ingve 1 year ago | 3 comments

Cuckoo hashing improves SIMD hash tables (and other hash table tradeoffs)(reiner.org)

54 points by ibraheemdev 1 year ago | 0 comments

Microbenchmarks Are Experiments(mrale.ph)

48 points by zdw 1 year ago | 6 comments

Adding runtime benchmarks to the Rust compiler benchmark suite(kobzol.github.io)

107 points by lukastyrychtr 3 years ago | 26 comments