The Community for Technology Leaders
Hot Topics in Operating Systems, Workshop on (1999)
Rio Rico, Arizona
Mar. 28, 1999 to Mar. 30, 1999
ISSN: 1530-1621
ISBN: 0-7695-0237-7
pp: 102
David Krinsky , Harvard University
Keith Smith , Harvard University
Margo Seltzer , Harvard University
Xiaolan Zhang , Harvard University
Most performance analysis today uses either microbenchmarks or standard macrobenchmarks (e.g., SPEC, LADDIS, the Andrew benchmark). However, the results of such benchmarks provide little information to indicate how well a particular system will handle a particular application. Such results are, at best, useless and, at worst, misleading. In this paper, we argue for an application-directed approach to benchmarking, using performance metrics that reflect the expected behavior of a particular application across a range of hardware or software platforms. We present three different approaches to application-specific measurement, one using vectors that characterize both the underlying system and an application, one using trace-driven techniques, and a hybrid approach. We argue that such techniques should become the new standard.
benchmark, performance, application-specific, measurement
David Krinsky, Keith Smith, Margo Seltzer, Xiaolan Zhang, "The Case for Application-Specific Benchmarking", Hot Topics in Operating Systems, Workshop on, vol. 00, no. , pp. 102, 1999, doi:10.1109/HOTOS.1999.798385
86 ms
(Ver 3.3 (11022016))