Abstract
NVIDIA have released a new platform (CUDA) for general purpose computing on their graphical processing units (GPU). This paper evaluates use of this platform for statistical machine learning applications. The transfer rates to and from the GPU are measured, as is the performance of matrix vector operations on the GPU. An implementation of a sparse matrix vector product on the GPU is outlined and evaluated. Performance comparisons are made with the host processor.
Chapter PDF
Similar content being viewed by others
Keywords
- Graphical Processing Unit
- Matrix Vector Product
- Stream Processor
- Streaming Multiprocessor
- Graphical Processing Unit Memory
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
NVIDIA: NVIDIA CUDA Programming Guide. 1.0 edn. (2007)
Vapnik, V.N.: Statistical Learning Theory. John Wiley & Sons, Inc., Chichester (1998)
Teo, C.H., Smola, A., Vishwanathan, S.V., Le, Q.V.: A scalable modular convex solver for regularized risk minimization. In: KDD 2007: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 727–736. ACM, New York (2007)
NVIDIA: NVIDIA GeForce 8800 GPU Architecture Overview (2006)
Duff, I.S., Erisman, A.M., Reid, J.K.: Direct Methods for Sparse Matrices. Oxford University Press, Oxford (1986)
Bolz, J., Farmer, I., Grinspun, E., Schröoder, P.: Sparse matrix solvers on the gpu: conjugate gradients and multigrid. ACM Trans. Graph. 22(3), 917–924 (2003)
Buck, I.: Data parallel computation on graphics hardware (2003)
Krüger, J., Westermann, R.: Linear algebra operators for gpu implementation of numerical algorithms. In: SIGGRAPH 2003: ACM SIGGRAPH 2003 Papers, pp. 908–916. ACM, New York (2003)
Ujaldon, M., Saltz, J.: The gpu on irregular computing: Performance issues and contributions. In: CAD-CG 2005: Proceedings of the Ninth International Conference on Computer Aided Design and Computer Graphics (CAD-CG 2005), pp. 442–450. IEEE Computer Society, Washington DC (2005)
Sengupta, S., Harris, M., Zhang, Y., Owens, J.D.: Scan primitives for gpu computing. In: Graphics Hardware, pp. 97–106. ACM, New York (2007)
Gahvari, H., Mark Hoemmen, J.D., Yelick, K.: Benchmarking sparse matrix-vector multiply in five minute. In: SPEC Benchmark Workshop (2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
El Zein, A., McCreath, E., Rendell, A., Smola, A. (2008). Performance Evaluation of the NVIDIA GeForce 8800 GTX GPU for Machine Learning. In: Bubak, M., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds) Computational Science – ICCS 2008. ICCS 2008. Lecture Notes in Computer Science, vol 5101. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69384-0_52
Download citation
DOI: https://doi.org/10.1007/978-3-540-69384-0_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69383-3
Online ISBN: 978-3-540-69384-0
eBook Packages: Computer ScienceComputer Science (R0)