Back in April, I built auto-arch-tournament (https://github.com/FeSens/auto-arch-tournament) to explore a question I’m still curious about: how well can different AI models improve a RISC-V CPU? I’ve been tracking the results on HWEBench(https://hwebench.com/v2).

It’s fun to see OpenAI exploring a similar question in today’s chip design post(https://openai.com/index/advancing-chip-design-with-our-models/). If you’d like to try an experiment yourself, you can run the research loop from the repo.


Comments URL: https://news.ycombinator.com/item?id=50553802

Points: 6

# Comments: 0