This talk will highlight probabilistic computers as an emerging paradigm for domain-specific computation. Firmly connected to the widely used Markov Chain Monte Carlo algorithms widely used in physics, statistics, and ML, the talk will show how networks of probabilistic bits, or p-bits, in hardware can deliver improvements in time and energy to solution for ML, optimization, and quantum simulation.

Probabilistic computers leverage a physics-inspired architecture with sparse connectivity and asynchronous updates, enabling massive parallelism. Digital implementations in single FPGAs show competitive performance against optimized GPUs/TPUs. Recent efforts with a distributed system of multiple FPGAs creates the “illusion” of a single, more powerful system, achieving near-linear speedup with minimal communication overhead.

Beyond digital CMOS, magnetic nanodevices offer intrinsic randomness, replacing thousands of transistors per p-bit and reducing energy per operation. Our ongoing efforts aim to integrate these devices into energy-efficient CMOS+X systems. Comparisons with quantum computers, GPUs/TPUs, and coupled oscillators will illustrate how probabilistic computers combined with tailored algorithms could achieve GPU-like impact and enable new applications.

[1] W. A. Borders, A. Z. Pervaiz, S. Fukami, K. Y. Camsari, H. Ohno, S. Datta, Integer Factorization Using Stochastic Magnetic Tunnel Junctions, Nature, (2019)

[2] N. A. Aadit, A. Grimaldi, M. Carpentieri, L. Theogarajan, J. M. Martinis, G. Finocchio, K. Y. Camsari, Massively Parallel Probabilistic Computing with Sparse Ising Machines, Nature Electronics (2022)

[3] S. Niazi, S. Chowdhury, N. A. Aadit, M. Mohseni, Y. Qin, and K. Y. Camsari. Training deep Boltzmann networks with sparse Ising machines. Nature Electronics (2024)

[4] N. S. Singh, K. Kobayashi, Q. Cao, K. Selcuk, T. Hu, S. Niazi, N. A. Aadit, S. Kanai, H. Ohno, S. Fukami, K. Y. Camsari, “CMOS plus stochastic nanomagnets enabling heterogeneous computers for probabilistic inference and learning,” Nature Communications, (2024).

Bio: Kerem Camsari received his Ph.D. in Electrical and Computer Engineering from Purdue University in 2015 and worked there as a postdoctoral researcher until 2020. He is currently an Associate Professor at the University of California, Santa Barbara. Kerem is a founding member and leads the unconventional computing section of the IEEE Nanotechnology Council’s Technical Committee on Quantum, Neuromorphic, and Unconventional Computing. He has received several honors, including the IEEE Magnetics Society Early Career Award, a Bell Labs Prize, the ONR Young Investigator Award, and the NSF CAREER Award for his work on probabilistic computing. He served as an IEEE Distinguished Lecturer in 2024 and is a senior member of IEEE.