Show HN: A free, GPU-accelerated Texas Hold'em GTO solver in C++/CUDA

 (bupticybee.github.io)

4 points | by bupticybee 4 hours ago

2 comments

  • rh94 3 hours ago
    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?

    [-]
    • bupticybee 1 hour ago
      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.
  • 217 3 hours ago
    [dead]