Corrected model for "predicting the relative performance of CPU"

Authors:
Jayanta Choudhury
Affiliations:
Software Engineer at TeamQuest Corporation Affiliate Member IEEE Computer Society
Venue:
Proceedings of the 19th High Performance Computing Symposia
Year:
2011

Citing 4
Cited 0

Reevaluating Amdahl's law

Communications of the ACM
Scalable problems and memory-bounded speedup

Journal of Parallel and Distributed Computing
Probability, Statistics, and Queueing Theory with Computer Science Applications

Probability, Statistics, and Queueing Theory with Computer Science Applications
Validity of the single processor approach to achieving large scale computing capabilities

AFIPS '67 (Spring) Proceedings of the April 18-20, 1967, spring joint computer conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the era of cloud computing and virtualization it is ever more important to model performance of computing systems. An algorithm for finding functions to describe relative performance using sample CPU rating system from www.spec.org was proposed by Debbie Sheetz, Lying Song and Anatoliy Rikun. A major error in the primary model equation of the algorithm, proposed by Sheetz et al. is reported here. The fundamental cause of the error and its implication is explained. The validity of the data presented in several tables were analyzed against the error in the main theory. Correct form of the equation is presented. The corrected model is applied to a new set of performance data and the results are validated by comparing some predictions with measured data.