Metraipolis › archive › dc_32d641138b29

GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay — arXiv:2609.11923

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11923
License (as archived)
CC0-1.0
Archived
2026-10-16T05:29:24.616Z
SHA-256 of the archived text
c05ca2532881d794e578a0c0634fc1ed49fd61ecc69a5384e037d73984a694a0
Stable URL of this page
https://metraipolis.com/documento/dc_32d641138b29

How to cite

GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay — arXiv:2609.11923 — arXiv (en), https://arxiv.org/abs/2609.11923 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_32d641138b29 (Metraipolis archive dc_32d641138b29, sha256 c05ca2532881d794e578a0c0634fc1ed49fd61ecc69a5384e037d73984a694a0)
BibTeX
@misc{dc32d641138b29,
  title = {GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay — arXiv:2609.11923},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11923},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_32d641138b29; sha256 c05ca2532881d794e578a0c0634fc1ed49fd61ecc69a5384e037d73984a694a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11923. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Counterfactual regret minimization (CFR) is one of the few large numerical workloads that still runs faster on CPUs than on GPUs. Each iteration sweeps a game tree with up to billions of states in millions of small, interdependent gather and scatter steps issued through a generic tree interface. On a GPU every kernel finishes in microseconds, so kernel launches and framework dispatch dominate the run time, and prior GPU implementations have lost to optimized CPU code. We observe that for a fixed game, everything about a CFR iteration except the numerical values is known before the first iteration runs. We propose GPU-CFR, a compiler and runtime built on this observation. It compiles any game once into static dataflow: flat edge and information-set arrays, precomputed indices, and depth-level batched passes fix the entire operation sequence, and only solver state changes between iterations. Static chance folding, depth-level execution blocks, and a dual-lane reach buffer cut the number of framework operations by up to 18.1x. Because shapes, indices, and buffer addresses never change, CUDA Graph Replay records the iteration once and replays it with a single graph launch. On one A100, across an eight-game suite that spans card games, dice games, and board games, GPU-CFR runs 29.8--80.4x faster than the fastest prior GPU CFR on the same accelerator, and 14--258x faster than LiteEFG, one of the fastest open-source CPU implementations, on the four largest games. The compiled representation carries most of that margin: on eight CPU threads with no accelerator it is already 2.2--51.1x faster than the GPU baseline. On the CPU the optimized path reproduces the reference iterates bitwise, and tree construction and graph capture pay for themselves within the first solve. GPU-CFR beats every CPU and GPU baseline on the mid-to-large games of the suite without changing the update rule.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT); Mathematical Software (cs.MS); Programming Languages (cs.PL).
Pagina del lavoro: https://arxiv.org/abs/2609.11923 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:17:52.214Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).