OpenFPM CUDA-style kernels now run on Apple Silicon GPUs via Metal
Scobleizer · x · 2026-07-22
- A CUDA/HIP-style simulation kernel in OpenFPM has been made to run directly on Apple Silicon GPUs via Apple Metal.
- The thread says GPT 5.6 Sol helped with the porting work.
- It also points to the first real Dam break benchmark and explains how the team got there.
More from coding & agent
- GitHub adds repository agent skill starters in a new draft PR — jonathan_wilke · 2026-07-22
- Hermes agent user asks which cheap open-source model can handle long-running automation — OkCare6395 · 2026-07-22
- Fable 5’s July 2026 benchmark shows PostgreSQL leading database picks at 53% — dshukertjr · 2026-07-22
- Palo Alto Networks CEO says frontier model teams should test their own code and configs first — Scobleizer · 2026-07-22
- Buzz adds Grok Build support alongside Claude Code and Codex harnesses — Daniel_Farinax · 2026-07-22
- Google’s CodeMender is now standalone, but its best version still needs an invite — shashib · 2026-07-22