Speed up GC by prefetching during marking by stedolan · Pull Request #10195 · ocaml/ocaml
This PR rewrites the core marking loop of the major GC, using prefetching to make better use of the processor's memory parallelism. This removes essentially all of the cache misses that occur d...
5bf2820278 Merge OCaml 4.14 (#55) 34432bedff Set VERSION to 4.14.0+jst 4e1d21c0cb Re-enable probes (amd64 only, as yet untested) 70840805f7 Regenerate .depend for upstream build system 16cb75b6c2 Fix upstream build system after merge (+Bootstrap) b635e3c4f9 Enable debug runtime in CI 5029967055 Apply ocaml-flambda/flambda-backend#916 7640f4bcd5 Ensure that tail recursion modulo cons is not used with local allocations d3b6161b03 Resolve merge conflicts in asmcomp/i386 09ac6e11cc Testsuite fix for Fortran tests 9f04dc41da Avoid having scope side-effects in loosen_ret_modes c32a0b754e Bugfix…
saved by
related reading
- abseil / Performance Hintsabseil.io
- Devlog ⚡ Zig Programming Languageziglang.org
- feat: algorithm abstraction — named algorithm classes + inline frozen-model references (grpo, opd, sft_distill, self_distill, echo) by hallerite · Pull Request #2746 · PrimeIntellect-ai/prime-rl · GitHubgithub.com
- How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklogsiboehm.com
- Blake2b F precompile by pdyraga · Pull Request #4 · keep-network/go-ethereumgithub.com
- [dev-overlay] Make badge draggable by raunofreiberg · Pull Request #78716 · vercel/next.jsgithub.com
- abseil / Performance Hintsabseil.io
- ⭐️ Fast LLM Inference From Scratchandrewkchan.dev
- Keep a Changelogkeepachangelog.com
- Lobsterslobste.rs
- Reading Listpliutau.com
- Idea Listjzhao.xyz