The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.10 - October (2009 vol.42)
pp: 70-76
Kenneth Hoste , Ghent University
Lieven Eeckhout , Ghent University
ABSTRACT
The wealth of performance numbers provided by benchmarking corporations makes it difficult to detect trends across commercial machines. A proposed methodology, based on statistical data analysis, simplifies exploration of these machines' large datasets.
INDEX TERMS
computer architecture modeling, system performance, computer systems organization
CITATION
Kenneth Hoste, Lieven Eeckhout, "A Methodology for Analyzing Commercial Processor Performance Numbers", Computer, vol.42, no. 10, pp. 70-76, October 2009, doi:10.1109/MC.2009.307
REFERENCES
1. R.A. Johnson and D.W. Wichern, Applied Multivariate Statistical Analysis, 5th ed., Prentice Hall, 2002.
2. M. Wolfe, "Compilers and More: Gloptimizations," HPCwire,9 Nov. 2007; www.hpcwire.com/topic/developertoolsCompilers_and_More_Gloptimizations.html .
3. K. Hoste and L. Eeckhout, "Microarchitecture-Independent Workload Characterization," IEEE Micro, May/June 2007, pp. 63-72.
20 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool