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

arXiv: https://arxiv.org/abs/2609.11923 · HTML: https://mlsanity.com/paper/2609.11923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 69 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 30 of 33)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker](https://mlsanity.com/paper/1701.01724/) (2017)
- [Combining Deep Reinforcement Learning and Search for Imperfect-Information Games](https://mlsanity.com/paper/2007.13544/) (2020)
- [Deep Counterfactual Regret Minimization](https://mlsanity.com/paper/1811.00164/) (2018)
- [Solving Large Imperfect Information Games Using CFR+](https://mlsanity.com/paper/1407.5042/) (2014)
- [Solving Imperfect-Information Games via Discounted Regret Minimization](https://mlsanity.com/paper/1809.04040/) (2018)
- [Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent](https://mlsanity.com/paper/2007.14358/) (2020)
- [Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning](https://mlsanity.com/paper/2303.17503/) (2023)
- [Safe and Nested Subgame Solving for Imperfect-Information Games](https://mlsanity.com/paper/1705.02955/) (2017)
- [Solving Imperfect Information Games Using Decomposition](https://mlsanity.com/paper/1303.4441/) (2013)
- [Depth-Limited Solving for Imperfect-Information Games](https://mlsanity.com/paper/1805.08195/) (2018)
- [Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions](https://mlsanity.com/paper/1910.10906/) (2019)
- [Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games using Baselines](https://mlsanity.com/paper/1809.03057/) (2018)
- [Student of Games: A unified learning algorithm for both perfect and imperfect information games](https://mlsanity.com/paper/2112.03178/) (2021)
- [Stable-Predictive Optimistic Counterfactual Regret Minimization](https://mlsanity.com/paper/1902.04982/) (2019)
- [Single Deep Counterfactual Regret Minimization](https://mlsanity.com/paper/1901.07621/) (2019)
- [Revisiting CFR+ and Alternating Updates](https://mlsanity.com/paper/1810.11542/) (2018)
- [Regret Matching+: (In)Stability and Fast Convergence in Games](https://mlsanity.com/paper/2305.14709/) (2023)
- [Subgame solving without common knowledge](https://mlsanity.com/paper/2106.06068/) (2021)
- [RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning](https://mlsanity.com/paper/2403.04344/) (2024)
- [Monte Carlo Continual Resolving for Online Strategy Computation in Imperfect Information Games](https://mlsanity.com/paper/1812.07351/) (2018)
- [Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent](https://mlsanity.com/paper/2404.13891/) (2024)
- [Effective, Efficient, and General Information Abstraction for Imperfect-Information Extensive-Form Games](https://mlsanity.com/paper/2605.10900/) (2026)
- [Real-Time Parallel Counterfactual Regret Minimization](https://mlsanity.com/paper/2605.19928/) (2026)
- [Correlated Chance Sampling for Monte Carlo Counterfactual Regret Minimization](https://mlsanity.com/paper/2607.27035/) (2026)
- [PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers](https://mlsanity.com/paper/2605.30094/) (2026)
- [Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation](https://mlsanity.com/paper/2607.28520/) (2026)
- [Limited Lookahead in Imperfect-Information Games](https://mlsanity.com/paper/1902.06335/) (2019)
- [Parallelizing Counterfactual Regret Minimization](https://mlsanity.com/paper/2605.14277/) (2026)
- [Solver-Guided Reasoning for Mixed-Equilibrium Strategies](https://mlsanity.com/paper/2608.06741/) (2026)

## Abstract (arXiv)

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.