HMMER Performance Model for Multicore Architectures

2011 14th Euromicro Conference on Digital System Design Pub Date : 2011-08-31 DOI:10.1109/DSD.2011.111

S. Isaza, Ernst Houtgast, G. Gaydadjiev

引用次数: 3

Abstract

Exponential growth in biological sequence data combined with the computationally intensive nature of bioinformatics applications results in a continuously rising demand for processing power. In this paper, we propose a performance model that captures the behavior and performance scalability of HMMER, a bioinformatics application that identifies similarities between protein sequences and a protein family model. With our analytical model, the optimal master-worker ratio for a user scenario can be estimated. The model is evaluated and is found accurate with less than 2% error. We applied our model to a widely used heterogeneous multicore, the Cell BE, using the PPE and SPEs as master and workers respectively. Experimental results show that for the current parallelization strategy, the I/O speed at which the database is read from disk and the inputs pre-processing are the two most limiting factors in the Cell BE case.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

多核架构的hmm性能模型

生物序列数据的指数级增长与生物信息学应用的计算密集型性质相结合，导致对处理能力的需求不断上升。在本文中，我们提出了一个性能模型，该模型捕获了HMMER的行为和性能可扩展性，HMMER是一种生物信息学应用程序，用于识别蛋白质序列和蛋白质家族模型之间的相似性。使用我们的分析模型，可以估计用户场景的最佳主工比例。对模型进行了评估，发现模型精度小于2%。我们将我们的模型应用于广泛使用的异构多核Cell BE，分别使用PPE和spe作为主节点和工作节点。实验结果表明，对于当前的并行化策略，从磁盘读取数据库的I/O速度和输入预处理是Cell BE情况下的两个最大限制因素。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2011 14th Euromicro Conference on Digital System Design

自引率

0.00%

发文量

期刊最新文献

Generalized If-Then-Else Operator for Compact Polynomial Representation of Multi Output Functions Numeral-Based Crosstalk Avoidance Coding to Reliable NoC Design VHDL Code Generation from Formal Event-B Models Cost of Sparse Mesh Layouts Supporting Throughput Computing LastZ: An Ultra Optimized 3D Networks-on-Chip Architecture