會議論文
| 學年 | 101 |
|---|---|
| 學期 | 1 |
| 發表日期 | 2012-12-17 |
| 作品名稱 | Accelerating Volkov’s hybrid implementation of Cholesky factorization on a Fermi GPU |
| 作品名稱（其他語言） | |
| 著者 | Wei, Shih-Chieh; Huang , Bormin |
| 作品所屬單位 | 淡江大學資訊管理學系 |
| 出版者 | |
| 會議名稱 | 18th IEEE International Conference on Parallel and Distributed Systems (ICPAD12) |
| 會議地點 | Singapore, Republic of Singapore |
| 摘要 | In linear algebra, Cholesky factorization is useful in solving a system of equations with a symmetric positive definite coefficient matrix. Cholesky factorization is roughly twice as fast relative to LU factorization which applies to general matrices. In recent years, with advances in technology, a Fermi GPU card can accommodate hundreds of cores compared to the small number of 8 or 16 cores on CPU. Therefore a trend is seen to use the graphics card as a general purpose graphics processing unit (GPGPU) for parallel computation. In this work, Volkov's hybrid implementation of Cholesky factorization is evaluated on the new Fermi GPU with others and then some improvement strategies were proposed. After experiments, compared to the CPU version using Intel Math Kernel Library (MKL), our proposed GPU improvement strategy can achieve a speedup of 3.85x on Cholesky factorization of a square matrix of dimension 10,000. |
| 關鍵字 | Cholesky factorization;general purpose graphics processing unit;parallel computing |
| 語言 | en |
| 收錄於 | |
| 會議性質 | 國際 |
| 校內研討會地點 | |
| 研討會時間 | 20121217~20121219 |
| 通訊作者 | |
| 國別 | SGP |
| 公開徵稿 | Y |
| 出版型式 | 紙本 |
| 出處 | Parallel and Distributed Systems (ICPADS), 2012 IEEE 18th International Conference on, pp.896-900 |
| 相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/96252 ) |