GPU is good at doing parallel task that in nature is the same. So it fit perfectly in CFR context. CFR is basically doing a lot of similar work across nodes. So if you implememnt a cuda kernel for regret matching, it will accelerate the solving process a lot.
I’ve done good deal of cfr/deepstack work my self, can you tell us bit more details how it works under the hood?
In particular, what is the gpu part?
GPU is good at doing parallel task that in nature is the same. So it fit perfectly in CFR context. CFR is basically doing a lot of similar work across nodes. So if you implememnt a cuda kernel for regret matching, it will accelerate the solving process a lot.