Parallel molecular dynamics on a multi signalprocessor system

Laboratory of Physical Chemistry, Swiss Federal Institute of Technology, CH-8092 Zürich, Switzerland; Electronics Laboratory, Swiss Federal Institute of Technology, CH-8092 Zürich, Switzerland; Seminar for Applied Mathematics, Swiss Federal Institute of Technology, CH-8092 Zürich, Switzerland
Computer Physics Communications (Impact Factor: 2.41). 01/1993; DOI: 10.1016/0010-4655(93)90165-9

ABSTRACT This paper gives an overview of a parallel computer architecture called MUSIC (Multi Signalprocessor System with Intelligent Communication), which has been developed at the Swiss Federal Institute of Technology. The current version achieves a peak performance of 3.8 GFlops. We discuss the system software and tools used to program the system and then present our implementation of a molecular dynamics simulation program which uses the architecture of MUSIC in an efficient way. We demonstrate the correctness of our implementation and give measurements of the performance of the system. To the best of our knowledge, MUSIC outperforms the most powerful present-day vector supercomputers.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Classical molecular dynamics simulations of biological macromolecules in explicitly modeled solvent typically require the evaluation of interactions between all pairs of atoms separated by no more than some distance R, with more distant interactions handled using some less expensive method. Performing such simulations for periods on the order of a millisecond is likely to require the use of massive parallelism. The extent to which such simulations can be efficiently parallelized, however, has historically been limited by the time required for interprocessor communication. This article introduces a new method for the parallel evaluation of distance-limited pairwise particle interactions that significantly reduces the amount of data transferred between processors by comparison with traditional methods. Specifically, the amount of data transferred into and out of a given processor scales as O(R(3/2)p(-1/2)), where p is the number of processors, and with constant factors that should yield a substantial performance advantage in practice.
    Journal of Computational Chemistry 11/2005; 26(13):1318-28. · 3.84 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this report the work of the first 18 months of the Polyproject "Parallel Computing in Quantum and Classical Molecular Dynamical Simulation" is summarized. The project is planned for a total dura-tion of three years. Four labs of the ETH attend the project: IGC (Computational Chemistry Group, head of the project), IFE (Electronics Lab), TIK (Computer Engineering and Networks Lab) and IWR (Scientific Computing Lab). GROMOS (GROningen MOlecular Simulation package) is a computer simulation tool which is distributed and supported in various versions by the Computational Chemistry Group. The main goal of the project is to accelerate the simulation of molecules in liquids by a factor of ten. To achieve the goal dedicated hardware must be developed to speed-up the Gromos software. The main topics in this report are as follows: First we present profiling results of the Gromos program, per-formed on different workstations and processors. Then we give an overview on existing hardware accelerators. New modelling techniques for the molecular dynamics algorithm are presented as well as models for different new parallel hardware solutions. With these models a design space exploration was performed using techniques such as system synthesis using Evolutionary Algorithms.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The purpose of the paper is to describe a new semi-automated design space exploration method based on genetic programming. A new control/dataflow specification method is proposed as well as appropriate models for hardware parts and algorithms. With this method we are able to test many different hardware architectures and algorithms against cost, speed, computation time and other constraints within a very short time. The remaining manual work is to exploit the model parameters of the components of the architecture and the algorithm. In contrast to other approaches our method is suited for embedded and distributed systems. The method, models and application are explained in detail by means of a comprehensive case study
    Circuits and Systems, 1998. ISCAS '98. Proceedings of the 1998 IEEE International Symposium on; 09/1998