Parallel Simulation of Parallel File Systems and I/O Programs

Efficient I/O implementations can have a significant impact on the performance of parallel applications. This paper describes the design and implementation of PIOSIM, a parallel simulation library for MPI-IO programs. The simulator can be used to predict the performance of existing MPI-IO programs as a function of architectural characteristics, caching algorithms, and alternative implementations of collective I/O operations. We describe the simulator and presents the results of a number of performance studies to evaluate the impact of the preceding factors on a set of MPI-IO benchmarks, including programs from the NAS benchmark suite.

[1]  Yarsun Hsu,et al.  Performance evaluation of a massively parallel I/O subsystem , 1994, CARN.

[2]  David Kotz,et al.  The galley parallel file system , 1996, ICS '96.

[3]  Dror G. Feitelson,et al.  The Vesta parallel file system , 1996, TOCS.

[4]  Corporate The MPI Forum,et al.  MPI: a message passing interface , 1993, Supercomputing '93.

[5]  Günter Haring,et al.  Performance Prediction of Parallel Programs , 1993, MMB.

[6]  Sandhya Dwarkadas,et al.  Efficient Simulation of Parallel Computer Systems , 1991, Int. J. Comput. Simul..

[7]  Dror G. Feitelson,et al.  Parallel File Systems for the IBM SP Computers , 1995, IBM Syst. J..

[8]  David Kotz,et al.  Disk-directed I/O for MIMD multiprocessors , 1994, OSDI '94.

[9]  Rajive Bagrodia,et al.  Performance prediction of parallel programs , 1996 .

[10]  John L. Hennessy,et al.  Multiprocessor Simulation and Tracing Using Tango , 1991, ICPP.

[11]  David A. Patterson,et al.  Cooperative Caching: Using Remote Client Memory , 1994 .

[12]  James R. Larus,et al.  The Wisconsin Wind Tunnel: virtual prototyping of parallel computers , 1993, SIGMETRICS '93.

[13]  David M. Nicol,et al.  A distributed memory LAPSE: parallel simulation of message-passing programs , 1994, PADS '94.

[14]  William E. Weihl,et al.  Reducing synchronization overhead in parallel simulation , 1996, Workshop on Parallel and Distributed Simulation.

[15]  Marianne Winslett,et al.  Server-Directed Collective I/O in Panda , 1995, Proceedings of the IEEE/ACM SC95 Conference.

[16]  Alok N. Choudhary,et al.  Improved parallel I/O via a two-phase run-time access strategy , 1993, CARN.

[17]  M. Winslett,et al.  Server-directed collective I/O in Panda , 1995 .

[18]  Michael Dahlin,et al.  Cooperative caching: using remote client memory to improve file system performance , 1994, OSDI '94.

[19]  Jesús Labarta,et al.  Avoiding the Cache-Coherence Problem in a Parallel/Distributed File System , 1997, HPCN Europe.

[20]  Eric A. Brewer,et al.  PROTEUS: a high-performance parallel-architecture simulator , 1992, SIGMETRICS '92/PERFORMANCE '92.

[21]  Bill Nitzberg,et al.  PMPIO-a portable implementation of MPI-IO , 1996, Proceedings of 6th Symposium on the Frontiers of Massively Parallel Computation (Frontiers '96).

[22]  Forum Mpi.  MPI: A Message-Passing Interface , 1994 .

[23]  Sandra Johnson Baylor,et al.  A methodology for evaluating parallel I/O performance for massively parallel processors , 1994, 27th Annual Simulation Symposium.

[24]  David Kotz.  Tuning STARFISH , 1996 .