Paper Info
Title
Improving accuracy of source level timing simulation for GPUs using a probabilistic resource model
Abstract
After their success in the high performance and desktop market, Graphic Processing Units (GPUs), that can be used for general purpose computing are introduced for embedded systems on a chip (SOCs). Due to some advanced architectural features, like massive simultaneous multithreading, static performance analysis and high-level timing simulation are difficult to apply to code running on these systems. This paper extends a method for performance simulation of GPUs. The method uses automated performance annotations in the application's OpenCL C source code, and an extended performance model for derivation of a kernels runtime from metrics produced by the execution of annotated kernels. The final results are then generated using a probabilistic resource conflict model. The model reaches an accuracy of 90% on most test cases and delivers a higher average accuracy than previous methods.
Year
DOI
Venue
2015
10.1109/SAMOS.2015.7363655
2015 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS)
Keywords
Field
DocType
probabilistic resource conflict model,application OpenCL C source code,automated performance annotations,GPU performance simulation,high-level timing simulation,static performance analysis,multithreading,advanced architectural features,SOC,embedded system on a chip,general purpose computing,graphic processing units,desktop market,source level timing simulation
Kernel (linear algebra),Pipeline transport,Computer science,Source code,Parallel computing,Chip,Simultaneous multithreading,Performance model,Test case,Probabilistic logic
Conference
Citations 
PageRank 
References 
0
0.34
13
Authors
3
Name
Order
Citations
PageRank
Christoph Gerum171.53
Wolfgang Rosenstiel21462212.32
Oliver Bringmann358671.36