Search

This paper describes the architecture, the development and the implementation of Janus II, a new generation application-driven number cruncher optimized for Monte Carlo simulations of spin systems (mainly spin glasses). This domain of computational physics is a recognized grand challenge of high-performance computing: the resources necessary to study in detail theoretical models that can make contact with experimental data are by far beyond those available using commodity computer systems. On the other hand, several specific features of the associated algorithms suggest that unconventional computer architectures, which can be implemented with available electronics technologies, may lead to order of magnitude increases in performance, reducing to acceptable values on human scales the time needed to carry out simulation campaigns that would take centuries on commercially available machines. Janus II is one such machine, recently developed and commissioned, that builds upon and improves on the successful JANUS machine, which has been used for physics since 2008 and is still in operation today. This paper describes in detail the motivations behind the project, the computational requirements, the architecture and the implementation of this new machine and compares its expected performances with those of currently available commercial systems., Comment: 28 pages, 6 figures

In this chapter we describe the Janus supercomputer, a massively parallel FPGA-based system optimized for the simulation of spin-glasses, theoretical models that describe the behavior of glassy materials. The custom architecture of Janus has been developed to meet the computational requirements of these models. Spin-glass simulations are performed using Monte Carlo methods that lead to algorithms characterized by (1) intrinsic parallelism allowing us to implement many Monte Carlo update engines within a single FPGA; (2) rather small data base (2 MByte) that can be stored on-chip, significantly boosting bandwidth and reducing latency. (3) need to generate a large number of good-quality long (≥ 32 bit) random numbers; (4) mostly integer arithmetic and bitwise logic operations. Careful tailoring of the architecture to the specific features of these algorithms has allowed us to embed up to 1024 special purpose cores within just one FPGA, so that simulations of systems that would take centuries on conventional architectures can be performed in just a few months.

We describe Janus, an application-driven architecture for Monte Carlo simulations of spin glasses. Janus is a massively parallel architecture, based on reconfigurable FPGA nodes; it offers two orders of magnitude better performance than commodity systems for spin glass applications. The first generation Janus machine has been operational since early 2008; we are currently developing a new generation, that will be on line in early 2013. In this paper we present the Janus architecture, describe both implementations and compare their performances with those of commodity systems.

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.

We have characterized numerically, using the Janus computer, the Lee-Yang complex singularities related to the overlap in the 3D Ising spin glass with binary couplings in a wide range of temperatures (both in the critical and in the spin-glass phase). Studying the behavior of the zeros at the critical point, we have obtained an accurate measurement of the anomalous dimension in very good agreement with the values quoted in the literature. In addition, by studying the density of the zeros we have been able to characterize the phase transition and to investigate the Edwards-Anderson order parameter in the spin-glass phase, finding agreement with the values obtained using more conventional techniques., 20 pages, 11 figures. Some typos corrected and references added

We describe the past and future of the Janus project. The collaboration started in 2006 and deployed in early 2008 the Janus supercomputer, a facility that allowed to speed-up Monte Carlo Simulations of a class of model glassy systems and provided unprecedented results for some paradigms in Statistical Mechanics. The Janus Supercomputer was based on state-of-the-art FPGA technology, and provided almost two order of magnitude improvement in terms of cost/performance and power/performance ratios. More than four years later, commercial facilities are closing-up in terms of performance, but FPGA technology has largely improved. A new generation supercomputer, Janus2, will be able to improve by more than one orders of magnitude with respect to the previous one, and will accordingly be again the best choice in Monte Carlo simulations of Spin Glasses for several years to come with respect to commercial solutions.

We study the 3D Disordered Potts Model with p=5 and p=6. Our numerical simulations (that severely slow down for increasing p) detect a very clear spin glass phase transition. We evaluate the critical exponents and the critical value of the temperature, and we use known results at lower $p$ values to discuss how they evolve for increasing p. We do not find any sign of the presence of a transition to a ferromagnetic regime., Comment: 9 pages and 9 Postscript figures. Final version published in J. Stat. Mech