October 9, 1999

Workload behavior studies are extremely important in guiding the design of computer architectures. Accurate characterization of application and operation system behavior leads to the design of improved architectures. This 1-day workshop, sponsored by IEEE and the Technical Committee on Computer Architecture, will focus on quantitative characterization and analytical modeling of workloads from commercial and scientific computing. Analytical modeling of workloads is extremely difficult and warrants careful consideration, especially because it takes significant amounts of time to perform trace-driven or execution-driven simulations due to the increased complexity of the processor, memory subsystem and the workload domain. The quantitative characterization studies can lead to the creation and validation of analytical models that capture the essential features of systems and workloads, which can be very useful in efficient exploration of the design space and making early design tradeoffs.

Topics of Interest

Papers are solicited in all areas related to characterization of workloads (system and/or application behavior) in a variety of computing environments. Topics of interest include (but not limited to):

Quantitative Workload Behavior Characterization

Abstract Modeling of Program Behavior

Machine Independent Characterization of Workloads

Characterization of Network Computing and Java workloads

Operating System Intensive Workloads

Characterization of E-commerce, web server and database workloads

Characterization of Multimedia workloads

Effects of Architectural Features on Workload Behavior

Memory and I/O Access Patterns

Characterization of Multiprocessor Applications

Multithreaded Workload Characterization

Representative Trace Generation

Profiling, Trace Collection and Validation Issues

Workload Synthesis

Authors are requested to submit an extended abstract of approximately 8 double-spaced pages by 07/26/99 to:

Lizy K. John ECE Department, ENS 143 The University of Texas at Austin Austin, TX 78712 ljohn@ece.utexas.edu

or

Ann Marie G. Maynard IBM-Austin Research Labs 11400 Burnet Road Austin,TX 78758 amgm@us.ibm.com

An automatic extension of one week is granted to all authors without request. Clearly describe the nature of the work, its significance and the current status of the research. Include a title page containing the title of the paper, list of authors and their affiliations, addresses, telephone and fax numbers, email addresses and the name of the corresponding author. Acceptances will be mailed out by 8/30/99. Final version of the papers must be submitted by 9/17/99. Selected papers will be published in a book from Kluwer Academic Publishers.

Author Schedule

July 26, 99 (Extended until Aug 2, 99)	:	Extended Abstract Submission
August 30, 1999	:	Acceptance Notified
September 17, 1999	:	Final Manuscript Submission

Program Committee

Pradip Bose, IBM T.J. Watson Research Center

Harry Dwyer, Bell Labs, Lucent Technologies

Manoj Franklin, University of Maryland

Lizy K. John, University of Texas at Austin

Corinna G. Lee, ATI Technologies Inc.

Ann Marie Maynard, IBM-Austin Research Labs

Balaram Sinharoy, IBM T.J. Watson Research Center

John P. Shen, Carnegie Mellon University

Nasr Ullah, Motorola

Last Revised: July 6, 1999