By Topic

Redeeming IPC as a performance metric for multithreaded programs

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Lepak, K.M. ; Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA ; Cain, H.W. ; Lipasti, M.H.

Recent work has shown that multithreaded workloads running in execution-driven, full-system simulation environments cannot use instructions per cycle (IPC) as a valid performance metric due to nondeterministic program behavior. Unfortunately, invalidating IPC as a performance metric introduces its own host of difficulties: special workload setup, consideration of cold-start and end-effects, statistical methodologies leading to increased simulation bandwidth, and workload-specific, higher-level metrics to measure performance. We explore the nondeterminism problem in multithreaded programs, describe a method to eliminate nondeterminism across simulations of different experimental machine models, and demonstrates the suitability of this methodology for performing architectural performance analysis, thus redeeming IPC as a performance metric for multithreaded programs.

Published in:

Parallel Architectures and Compilation Techniques, 2003. PACT 2003. Proceedings. 12th International Conference on

Date of Conference:

27 Sept.-1 Oct. 2003