Preliminary Results of Autotuning GEMM Kernels for the NVIDIA Kepler Architecture- GeForce GTX 680
Abstract
Kepler is the newest GPU architecture from NVIDIA, and the GTX 680 is the first commercially available graphics card based on that architecture. Matrix multiplication is a canonical computational kernel, and often the main target of initial optimization efforts for a new chip. This article presents preliminary results of automatically tuning matrix multiplication kernels for the Kepler architecture using the GTX 680 card.
- Authors:
-
- Univ. of Tennessee, Knoxville, TN (United States)
- Univ. of Tennessee, Knoxville, TN (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Univ. of Manchester (United Kingdom)
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC)
- OSTI Identifier:
- 1173292
- Report Number(s):
- LBNL-5788E
- DOE Contract Number:
- AC02-05CH11231
- Resource Type:
- Technical Report
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING
Citation Formats
Kurzak, Jakub, Luszczek, Pitor, Tomov, Stanimire, and Dongarra, Jack. Preliminary Results of Autotuning GEMM Kernels for the NVIDIA Kepler Architecture- GeForce GTX 680. United States: N. p., 2012.
Web. doi:10.2172/1173292.
Kurzak, Jakub, Luszczek, Pitor, Tomov, Stanimire, & Dongarra, Jack. Preliminary Results of Autotuning GEMM Kernels for the NVIDIA Kepler Architecture- GeForce GTX 680. United States. https://doi.org/10.2172/1173292
Kurzak, Jakub, Luszczek, Pitor, Tomov, Stanimire, and Dongarra, Jack. 2012.
"Preliminary Results of Autotuning GEMM Kernels for the NVIDIA Kepler Architecture- GeForce GTX 680". United States. https://doi.org/10.2172/1173292. https://www.osti.gov/servlets/purl/1173292.
@article{osti_1173292,
title = {Preliminary Results of Autotuning GEMM Kernels for the NVIDIA Kepler Architecture- GeForce GTX 680},
author = {Kurzak, Jakub and Luszczek, Pitor and Tomov, Stanimire and Dongarra, Jack},
abstractNote = {Kepler is the newest GPU architecture from NVIDIA, and the GTX 680 is the first commercially available graphics card based on that architecture. Matrix multiplication is a canonical computational kernel, and often the main target of initial optimization efforts for a new chip. This article presents preliminary results of automatically tuning matrix multiplication kernels for the Kepler architecture using the GTX 680 card.},
doi = {10.2172/1173292},
url = {https://www.osti.gov/biblio/1173292},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sun Apr 01 00:00:00 EDT 2012},
month = {Sun Apr 01 00:00:00 EDT 2012}
}
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.