Title
Statistical Performance Analysis and Estimation of Coarse Grain Parallel Multimedia Processing System
Abstract
When parallelizing complex multimedia processing on multiple processors, the stochastic timing behavior should be carefully studied. Although there are already many papers on the performance analysis of stochastic parallel system, they are not targeted on multimedia processing. In this paper, first we study H.264/AVC encoder (running on x86) and QSDPCM encoder (running on TI TMS32C62 instruction simulator) to characterize important aspects of the stochastic timing behavior in complicated multimedia processing applications. It is shown that the variation and correlation are indeed very significant. In order to make systematic analysis feasible, we apply Stochastic Timed Marked Graph (STMG) as a formal model to capture essential timing related behaviors of parallel multimedia processing systems. Then, we show how the local timing variations and correlations interact and propagate to the global timing behavior; from this we conclude general parallelization guidelines. Furthermore, we develop an analytical performance estimation technique to derive the probability distribution of timing behavior for parallel multimedia processing systems that have correlated stochastic timing behaviors inside. The estimation technique is based on principal component analysis and approximations.
Year
DOI
Venue
2006
10.1109/RTAS.2006.41
IEEE Real-Time Technology and Applications Symposium
Keywords
Field
DocType
principal component analysis,stochastic processes,statistical analysis,probability distribution,parallel systems,local time
Marked graph,x86,Computer science,Performance estimation,Stochastic process,Real-time computing,Probability distribution,Encoder,Multimedia,Principal component analysis,Statistical analysis
Conference
ISBN
Citations 
PageRank 
0-7695-2516-4
6
0.52
References 
Authors
12
4
Name
Order
Citations
PageRank
Min (Leon) Li1111.08
Tanja Van Achteren2272.53
Erik Brockmeyer322318.95
Francky Catthoor43932423.30