Hacker News Reader

I'm curious what you mean by "wrong shape"? Because GPUs are for for very data-parallel workloads? Or because the latency is high?

View on HN

Yeah, we made both of those assumptions. But it's apparently less true of the latest generation of compute engines. We probably won't bother with CUDA, but Metal is certainly a viable platform to try. It's one of those things where nobody really knows how it'll do until you try it.

Also, we do know a few people who want to use SOUL to write audio code which does need high parallelism. It's not a super-common use-case for audio, but it does exist.

I hope you'll consider writing up your results in a blog post or something! As I just mentioned elsewhere in this thread, I have experimentally found latency with Metal compute to be too high to be feasible, but I would dearly love to be proven wrong, if there's a trick I'm missing.

Yes, we'll certainly be writing it up. Similarly i'd be interested in reading about your experiences attempting the same if that's available.

Reply on news.ycombinator.com