Institutional Repository
| PLASMA自适应调优与性能优化的设计与实现 | |
| Alternative Title | design and implementation for plasma auto-tuning and performance optimizing |
| 吕渐春; 张云泉; 王婷; 肖玄基 | |
| 2012 | |
| Source | Computer Science
 |
| ISSN | 1002-137X |
| Volume | 39Issue:4Pages:282-286 |
| English Abstract | PLASMA是一个高效的线性代数软件包,其数据分布结合分堆、细粒度并行以及乱序执行机制等大大提高了程序的性能。但PLASMA仍然存在一些问题,比 如分块大小对程序性能的影响非常大,以及产生了大量的数据拷贝等。通过对比传统的LAPACK和PLASMA的实现机制,分析了PLASMA中存在的优势 和不足,介绍了两种弥补PLASMA自身不足的方法。针对PLASMA的架构,经过大量的测试与分析,提出了边缘矩阵的概念并分析了其对性能的影响,据此 提出了一种自适应调优的方法。并通过数据拷贝与计算并行的运行方式,进一步提高了PLASMA性能,最后通过大量的测试验证了该优化方法的效果。 |
| Indexed Type | cscd,cnki,wanfang |
| Abstract | PLASMA is a high performance linear algebra package.Its innovative approach such as block data layout with tiling,fine grain parallelism and out of order execution mechanism greatly improves the performance of the program.However,there are still some problems,for example,the size of block plays a severe role in performance and this mechanism brings some data copy.In this paper,by comparing the traditional LAPACK and PLASMAs mechanism,we aimed to analyze the advantages and disadvantages of PLASMA,and proposed two methods to make up the disadvantages.As to the PLASMA architecture,we proposed a concept of marginal matrix and analysed their impact on perfor-mance via extensive testing and analysis,and then proposed a method of auto-tuning.Besides,we also found a way to further improve the performance of PLASMA,which is adopting data transmission and computing in parallel.Finally,we verified the effect of optimized method by doing a large number of testing. |
| Keyword | Lapack Plasma Lapack Plasma Auto-tuning Optimization |
| Department | 吕渐春, 中国科学院软件所并行计算实验室, 北京 100190, 中国. 张云泉, 中国科学院软件所并行计算实验室, 北京 100190, 中国. 王婷, 中国科学院软件所并行计算实验室, 北京 100190, 中国. 肖玄基, 中国科学院软件所并行计算实验室, 北京 100190, 中国. |
| Subject | Computer Science |
| Language | 中文 |
| Content Type | 期刊论文 |
| URI | http://ir.iscas.ac.cn/handle/311060/14699 |
| Collection | 中国科学院软件研究所 |
| Recommended Citation GB/T 7714 | 吕渐春,张云泉,王婷,等. PLASMA自适应调优与性能优化的设计与实现[J]. Computer Science,2012,39(4):282-286. |
| APA | 吕渐春,张云泉,王婷,&肖玄基.(2012).PLASMA自适应调优与性能优化的设计与实现.Computer Science,39(4),282-286. |
| MLA | 吕渐春,et al."PLASMA自适应调优与性能优化的设计与实现".Computer Science 39.4(2012):282-286. |
| Files in This Item: | ||||||
| File Name/Size | DocType | Version | Access | License | ||
| PLASMA自适应调优与性能优化的设计与（524KB） | 开放获取 | License | Application Full Text | |||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment