The CHARISMA Project (1993-1996)

The CHARISMA project began in June 1993 (at DAGS'93) to CHARacterize I/O in Scientific Multiprocessor Applications from a variety of production parallel computing platforms and sites. The CHARISMA project is unique in recording individual read and write requests in live, multiprogramming, parallel workloads (rather than from selected or non-parallel applications).

The project is finished, i.e., there is no work currently underway and none planned.

More details about the CHARISMA work.

Papers:

• Dynamic File-Access Characteristics of a Production Parallel Scientific Workload (iPSC results)
  • 1994 TR
  • Supercomputing '94
  • IEEE Parallel & Distributed Technology.
• Characterizing Parallel File-Access Patterns on a Large-Scale Multiprocessor (CM-5 results)
  • 1994 TR
  • IPPS '95
• A Multiprocessor Extension to the Conventional File System Interface
  • 1994 TR (updated, renamed and rereleased below)
• Low-level Interfaces for High-level Parallel I/O
  • 1995 TR
  • IOPADS at IPPS '95
• File-Access Characteristics of Parallel Scientific Workloads
  • 1995 TR
  • IEEE TPDS

The CHARISMA trace format

The CHARISMA group:

Dartmouth College

David Kotz

Nils Nieuwejaar

Duke University

Carla Ellis

Apratim Purakayastha

NASA Ames NAS

Jeff Becker

Russell Carter

Sam Fineberg

Art Lazanoff

Bill Nitzberg

Bernard Traversat

MIT

Mike Best (formerly of Thinking Machines)

Cornell Theory Center

Dave Schneider

IBM T.J. Watson Research Center

Caroline Benveniste

Carnegie-Mellon University

Garth Gibson

Dan Stodolsky

University of Toronto

Orran Krieger

Syracuse University and NPAC

Mike Del Rosario

General Information about Parallel I/O.

This research was supported in part by the NASA Ames Research Center under Agreement Number NCC 2-849, the National Science Foundation under grant number CCR-9113170, the National Center for Supercomputing Applications, and Thinking Machines Corporation.

Back to Dartmouth CS Home Page