‹ BackHN Continuity

Thread

Nvidia announces native GPU programming in Rust

970 points · 404 comments · nonmaskable

  1. calini · · focus · HN ↗
    Do it in Go and I’m interested
    1. jrhey · · focus · HN ↗
      Go is simply not feasible for CUDA work mainly because of the go runtime that manages GC, allocation, scheduling etc

      GPU kernels want explicit memory control and as little go-runtime like overhead as possible

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.