VLBI-resolution radio-map algorithms: Performance analysis of different levels of data-sharing on multi-socket, multi-core architectures

详细信息	查看全文 | 推荐本文 |

• 作者：S. Tabik^a ; ^{stabik@uma.es} ; L.F. Romero^a ; P. Mimica^b ; O. Plata^a ; E.L. Zapata^a
• 关键词：VLBI-resolution radio-map algorithms ; Parallel approaches ; Multi-socket multi-core systems ; UMA ; NUMA ; NUCA
• 刊名：Computer Physics Communications
• 出版年：2012
• 期刊代码：30_00104655
• 类别：cp
• 出版时间：September, 2012
• 卷：183
• 期：9
• 页码：1937-1946
• 文件大小：896 K

摘要

A broad area in astronomy focuses on simulating extragalactic objects based on Very Long Baseline Interferometry (VLBI) radio-maps. Several algorithms in this scope simulate what would be the observed radio-maps if emitted from a predefined extragalactic object. This work analyzes the performance and scaling of this kind of algorithms on multi-socket, multi-core architectures. In particular, we evaluate a sharing approach, a privatizing approach and a hybrid approach on systems with complex memory hierarchy that includes shared Last Level Cache (LLC). In addition, we investigate which manual processes can be systematized and then automated in future works. The experiments show that the data-privatizing model scales efficiently on medium scale multi-socket, multi-core systems (up to 48 cores) while regardless of algorithmic and scheduling optimizations, the sharing approach is unable to reach acceptable scalability on more than one socket. However, the hybrid model with a specific level of data-sharing provides the best scalability over all used multi-socket, multi-core systems.