Evaluating the transport layer of the ALFA framework for the Intel? Xeon Phi? Coprocessor

21st International Conference on Computing in High Energy and Nuclear Physics

物理学;计算机科学

Santogidis, Aram^1,2 ; Hirstius, Andreas^3 ; Lalis, Spyros^4

CERN IT/Openlab, Geneva

1211, Switzerland^1

Maynooth University Co., Maynooth, Ireland^2

Intel GmbH, Feldkirchen/Munich

85622, Germany^3

University of Thessaly, Volos

38221, Greece^4

关键词: High energy physics experiments;    Inter-node communication;    ITS data;    Performance data;    Performance measurements;    Research efforts;    Transfer performance;    Transport layers;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/664/9/092021/pdf
DOI  :  10.1088/1742-6596/664/9/092021

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

The ALFA framework supports the software development of major High Energy Physics experiments. As part of our research effort to optimize the transport layer of ALFA, we focus on profiling its data transfer performance for inter-node communication on the Intel Xeon Phi Coprocessor. In this article we present the collected performance measurements with the related analysis of the results. The optimization opportunities that are discovered, help us to formulate the future plans of enabling high performance data transfer for ALFA on the Intel Xeon Phi architecture.