Janus

Computational science

Engineering

Exploit

Materials science

Embedded system

Computer security

Theoretical computer science

Parallel computing

Computer science

Visual arts

Statistical physics

Architecture

Boosting (machine learning)

Physics

Nanotechnology

Computer architecture

Spin glass

Computer engineering

Condensed matter physics

Artificial intelligence

Programming language

Field-programmable gate array

IFAC Proceedings Volumes

Spin-glasses have become one of the most computing-demanding problems of the last 50 years in Statistical Physics. These extremely slow systems represent a clear example of an easy-to-describe but hard-to-simulate numerical problem. We have developed an FPGAs architecture, called Janus, able to exploit the simplicity of the problem by an extensive parallelization of the computing units. In this work we describe the architecture after motivating the problem. We give the performance figures compared with other more usual architectures. We have obtained a clear advantage in terms of computing power which produced several top results in the field. In addition, we describe the current development of the next generation of the infrastructure: Janus II.

The Janus project: boosting spin-glass simulations using FPGAs