Demystifying GPU microarchitecture through microbenchmarking
Department of Electrical and Computer Engineering, University of Toronto
IEEE International Symposium on Performance Analysis of Systems & Software (ISPASS), 2010, p.235-246
@conference{wong2010demystifying,
title={Demystifying GPU microarchitecture through microbenchmarking},
author={Wong, H. and Papadopoulou, M.M. and Sadooghi-Alvandi, M. and Moshovos, A.},
booktitle={Performance Analysis of Systems & Software (ISPASS), 2010 IEEE International Symposium on},
pages={235–246},
year={2010},
organization={IEEE}
}
Graphics processors (GPU) offer the promise of more than an order of magnitude speedup over conventional processors for certain non-graphics computations. Because the GPU is often presented as a C-like abstraction (e.g., Nvidia’s CUDA), little is known about the characteristics of the GPU’s architecture beyond what the manufacturer has documented. This work develops a microbechmark suite and measures the CUDA-visible architectural characteristics of the Nvidia GT200 (GTX280) GPU. Various undisclosed characteristics of the processing elements and the memory hierarchies are measured. This analysis exposes undocumented features that impact program performance and correctness. These measurements can be useful for improving performance optimization, analysis, and modeling on this architecture and offer additional insight on the decisions made in developing this GPU.
December 21, 2010 by hgpu
