# Virtual reservoir acceleration for CPU and GPU: Case study for coupled spin-torque oscillator reservoir

arXiv: https://arxiv.org/abs/2312.01121 · HTML: https://mlsanity.com/paper/2312.01121/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 43 references that are in the map.
- First posted on arXiv 2 Dec 2023.

## Builds on (most cited first, 10 of 10)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Hamiltonian Neural Networks](https://mlsanity.com/paper/1906.01563/) (2019)
- [Lagrangian Neural Networks](https://mlsanity.com/paper/2003.04630/) (2020)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [Next Generation Reservoir Computing](https://mlsanity.com/paper/2106.07688/) (2021)
- [Physical reservoir computing -- An introductory perspective](https://mlsanity.com/paper/2005.00992/) (2020)
- [Vowel recognition with four coupled spin-torque nano-oscillators](https://mlsanity.com/paper/1711.02704/) (2017)
- [Multifunctionality in a Reservoir Computer](https://mlsanity.com/paper/2008.06348/) (2020)
- [A Unifying Framework for Information Processing in Stochastically Driven Dynamical Systems](https://mlsanity.com/paper/1906.04608/) (2019)

## Built on by (most cited first, 1 of 1)

- [Harnessing omnipresent oscillator networks as computational resource](https://mlsanity.com/paper/2502.04818/) (2025)

## Abstract (arXiv)

We provide high-speed implementations for simulating reservoirs described by N-coupled spin-torque oscillators. Here N also corresponds to the number of reservoir nodes. We benchmark a variety of implementations based on CPU and GPU. Our new methods are at least 2.6 times quicker than the baseline for N in range 1 to 104. More specifically, over all implementations the best factor is 78.9 for N=1 which decreases to 2.6 for N=103 and finally increases to 23.8 for N=104. GPU outperforms CPU significantly at N=2500. Our results show that GPU implementations should be tested for reservoir simulations. The implementations considered here can be used for any reservoir with evolution that can be approximated using an explicit method.