Institutional Repository
| a locality-based performance model for load-and-compute style computation | |
| Yuan Liang; Zhang Yunquan | |
| 2012 | |
| Conference Name | IEEE International Conference on Cluster Computing |
| Source | Proceedings - 2012 IEEE International Conference on Cluster Computing, CLUSTER 2012 |
| Pages | 566-571 |
| Conference Date | SEP 24-28, 2012 |
| Conference Place | Beijing, PEOPLES R CHINA |
| Indexed Type | ISTP ; EI |
| ISSN | 1552-5244 |
| Department | Yuan Liang; Zhang Yunquan Chinese Acad Sci Lab Parallel Software & Computat Sci Inst Software Beijing 100864 Peoples R China. |
| English Abstract | The increasing speed gap between the processor and memory is usually the critical bottleneck in achieving high performance. Hardware caches, programming models, algorithms and data structures have been introduced and proposed to exploit localities on reducing the memory overhead. Some of these new designs share a common load and compute style in which the algorithm first moves all needed data to cache and then performs operations only on the ready data. In this paper, we introduce a locality function to model the reuse ability of an algorithm and propose a corresponding performance model. Then we theoretically analyze how to utilize and design on cache under our model: (1) We present theorems to give the optimal cache partition scheme for the software buffering technique targeting at hiding the memory overhead. (2) We provide methods to decide the optimal multicore design to maximally leverage benefits of both the shared and private caches. (3) We incorporate the memory overhead into the Amdahl's Law to study the speedup limitation on memory bandwidth.; The increasing speed gap between the processor and memory is usually the critical bottleneck in achieving high performance. Hardware caches, programming models, algorithms and data structures have been introduced and proposed to exploit localities on reducing the memory overhead. Some of these new designs share a common load and compute style in which the algorithm first moves all needed data to cache and then performs operations only on the ready data. In this paper, we introduce a locality function to model the reuse ability of an algorithm and propose a corresponding performance model. Then we theoretically analyze how to utilize and design on cache under our model: (1) We present theorems to give the optimal cache partition scheme for the software buffering technique targeting at hiding the memory overhead. (2) We provide methods to decide the optimal multicore design to maximally leverage benefits of both the shared and private caches. (3) We incorporate the memory overhead into the Amdahl's Law to study the speedup limitation on memory bandwidth. |
| Keyword | Locality Function Cache Partition Private Cache Shared Cache |
| Sponsorship | IEEE, IEEE Comp Soc, IEEE Tech Comm Scalable Comp (TCSC), Sugon, Intel, Inspur, VMware, Mellanox, PARATERA, BLSC, LoongStore, Nvidia |
| Subject | Computer Science |
| Language | 英语 |
| Content Type | 会议论文 |
| URI | http://ir.iscas.ac.cn/handle/311060/15803 |
| Collection | 中国科学院软件研究所 |
| Recommended Citation GB/T 7714 | Yuan Liang,Zhang Yunquan. a locality-based performance model for load-and-compute style computation[C],2012:566-571. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment