Hybrid PDES Simulation of HPC Networks Using Zombie Packets

Author:

Cruz-Camacho Elkin1ORCID,Brown Kevin2ORCID,Wang Xin3ORCID,Xu Xiongxiao4ORCID,Shu Kai4ORCID,Lan Zhiling5ORCID,Ross Bob2ORCID,Carothers Christopher1ORCID

Affiliation:

1. Computer Science, Rensselaer Polytechnic Institute, Troy, United States

2. Argonne National Laboratory, Lemont, United States

3. Computer Science, University of Illinois Chicago, Chicago, United States

4. Illinois Institute of Technology, Chicago, United States

5. University of Illinois Chicago, Chicago, United States

Abstract

Although high-fidelity network simulations have proven to be reliable and cost-effective tools to peer into architectural questions for high-performance computing (HPC) networks, they incur a high resource cost. The time spent in simulating a single millisecond of network traffic in the highest detail can take hours, even for static, well-behaved traffic patterns such as uniform random. Surrogate models offer a significant reduction in runtime, yet they cannot serve as complete replacements and should only be used when appropriate. Thus, there is a need for hybrid modeling, where high-fidelity simulation and surrogates run side-by-side. We present a surrogate model for HPC networks in which: packets bypass the network, while the network state is left untouched, i.e , suspended. To bypass the network, we use historical data to estimate the arrival time at which every packet should be scheduled at; to suspend the network, all in-flight packets are scheduled to arrive at their destinations, and are kept in the system to awaken as zombies when switching back to high-fidelity. Speedup for a hybrid model is relative to the proportion of surrogate to high-fidelity. This light-weight surrogate obtained up to 76 × speedup. Keeping the zombies in the network showed an increase in the accuracy of the high-fidelity simulation on restart when compared to restarting the network from an empty state.

Publisher

Association for Computing Machinery (ACM)

Reference24 articles.

1. Warp speed

2. Kevin A. Brown, Neil McGlohon, Sudheer Chunduri, Eric Borch, Robert B. Ross, Christopher D. Carothers, and Kevin Harms. 2021. A Tunable Implementation of Quality-of-Service Classes for HPC Networks. In ISC High Performance 2021: High Performance Computing (ISC) ((Virtual) Frankfurt, Germany).

3. Center for Computational Innovations. [n.d.]. Artificial intelligence multiprocessing optimized system (AiMOS). cci.rpi.edu. (accessed December 13, 2023).

4. Multiscale modeling: recent progress and open questions

5. William James Dally and Brian Patrick Towles. 2004. Principles and Practices of Interconnection Networks. Elsevier.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3