Sparse Matrix-Vector Multiplication: A Low Communication Cost Data Mapping-Based Architecture
碩士 === 國立臺灣科技大學 === 電子工程系 === 103 === The performance of the sparse matrix-vector multiplication (SMVM) on a parallel system is strongly conditioned by the distribution of data among its components. Two costs arise as a result of the used data mapping method: arithmetic and communication. The commun...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2015
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/09761233547687794389 |