Accelerating Distributed Digital Ising Machines
Ising machines, dedicated accelerators built around the dynamics of Ising-like spin models, have emerged as a leading platform for combinatorial optimization and probabilistic sampling. The problems that motivate them require millions of spins, far beyond the on-chip capacity of any single device, so a practical Ising machine must distribute its computation across many devices. Prior work reports throughput at a single operating point, leaving the binding resource unidentified and platform crossovers measurable only by experiment; no calibrated cross-platform cost model of distributed Ising machines has been reported, nor have systematic techniques to accelerate their Markov chain Monte Carlo (MCMC) workloads. This work presents a calibrated cost model that decomposes digital Ising sweep time into compute, memory, synchronization, and inter-device communication terms, validated with 4.8% mean error across three GPU generations, FPGA and ASIC up to 1 million spins. Guided by the model, we address each term in turn and propose: (i) a data placement strategy, worth up to 4.2$\times$ speedup; (ii) multi-rate and bounded-staleness schedules that relax the barrier that Gibbs sampling imposes, cutting time-to-solution (TTS) by up to 3.16$\times$ on three benchmarks; and (iii) a phase-offset streaming dataflow that hides boundary exchange behind interior computation whenever a link satisfies a latency-transparency criterion, yielding up to 1.25$\times$/1.74$\times$/2.01$\times$ on an H200 pair, a ZCU106 pair, and a four-board XEM8320 $2{\times}2$ mesh. The streaming dataflow is also implemented on a fabricated four-chip 28 nm ASIC sustaining 28.1 Gflips/s at 4.81 pJ/flip.
Authors
- Kerem Yunus Camsari (ORCID: https://orcid.org/0000-0002-6876-8812)
- Tathagata Srimani (ORCID: https://orcid.org/0000-0002-1238-7324)
- Navid Anjum Aadit (ORCID: https://orcid.org/0000-0001-9933-0728)
- Kemal Selçuk (ORCID: https://orcid.org/0009-0001-4840-7534)
- P. Mohan (ORCID: https://orcid.org/0000-0002-2211-0660)
- Shreya Mukherjee (ORCID: https://orcid.org/0000-0003-0898-9821)
- Atharva Raut (ORCID: https://orcid.org/0009-0006-0047-1090)
- Ziyad Alswaidan
- Ting-Yu Lee
- Harry Tye
- Abhinav K. Puthran
- Daniel Xu
- Tong Wu
- Ken Mai
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.48550/arxiv.2611.23883
- Primary Topic
- Parallel Computing and Optimization Techniques
- Type
- preprint