报 告 人：Torsten Hoefler 院士
工作单位：苏黎世联邦理工学院（瑞士）
报告题目：用于加速分布式文件系统的网络内流处理
报告时间：2023年6月6日（周二）14:30-15:30
报告链接：Teams Link
https://teams.microsoft.com/l/meetup-join/19%3aB4gmRcUATAMA2iJqi-xXvtfPFfTbxVJPxSW_pcAPBao1%40thread.tacv2/1638719716825?context=%7b%22Tid%22%3a%2222804ebb-30d5-47df-942f-f3a3722f0225%22%2c%22Oid%22%3a%2216a60c03-ad7a-4b85-a403-8ebd947e010c%22%7d
内容摘要：
高性能的集群和数据中心对存储系统的需求日益增加。如果这些系统不能大规模运行，应用程序注定会成为I/O的束缚，且浪费计算周期。为了加快到远程存储节点的数据路径，存储系统采用了远程直接内存访问（RDMA），使数据从网络流到存储目标，从而降低总体延迟和CPU利用率。然而，这种方法仍然需要CPU在数据路径上执行存储策略，如认证、复制和清除编码。本报告将说明如何将存储策略卸载到完全可编程的SmartNIC，而不涉及主机CPU。通过使用一个开放的硬件智能网卡PsPIN，本报告将展示与各自的基于CPU和RDMA的替代方案相比，写入（高达2倍）、数据复制（高达2倍）和擦除编码（高达2倍）的延迟改进。
个人简介：
Torsten Hoefler院士是苏黎世联邦理工学院计算机科学教授，欧洲科学院院士，以及IEEE会员。Torsten Hoefler院士遵循 性能是一门科学 的理念，将架构和应用的数学模型结合起来，设计优化的计算系统。在加入苏黎世联邦理工学院之前，Torsten Hoefler院士领导了伊利诺伊大学厄巴纳-香槟分校的第一台持续Petascale超级计算机蓝水的性能建模和模拟工作。他也是消息传递接口（MPI）标准的主要贡献者，曾担任 集体操作和拓扑结构 工作组主席。Torsten Hoefler院士曾分别在2010年、2013年、2014年、2019年的ACM/IEEE超级计算会议以及其他国际会议上获最佳论文奖，发表了许多同行评议的科学文章，并撰写了MPI-2.2和MPI-3.0标准的章节。Torsten Hoefler院士曾获2019年ACM戈登贝尔奖、IEEE TCSC优秀奖（MCR）、苏黎世联邦理工学院的Latsis奖、SIAM SIAG/超级计算初级科学家奖、IEEE TCSC可扩展计算青年成就者奖和BenchCouncil新星奖。博士毕业后，他获得了他的母校印第安纳大学的2014年青年校友奖和2022年杰出校友奖。2013年，Torsten Hoefler院士当选ACM的SIGHPC的第一届指导委员会成员，此后每届都当选连任，是第一个获得这些荣誉的欧洲人。Torsten Hoefler院士还获得了ERC启动和巩固者资助。Torsten Hoefler院士的研究领域围绕着以性能为中心的系统设计这一中心议题，包括可扩展网络、并行编程技术以及大规模模拟和人工智能系统的性能建模等。
【编辑：王健】
英文版：
Academic Report Notice of Torsten Hoefler : Streaming in-Network Processing for Accelerated Distributed File Systems
Speaker: Academician Torsten Hoefler
Title: Streaming in-Network Processing for Accelerated Distributed File Systems
Time: 14:30pm, June 6th, 2023 (Tuesday)
Website: Teams Link
https://teams.microsoft.com/l/meetup-join/19%3aB4gmRcUATAMA2iJqi-xXvtfPFfTbxVJPxSW_pcAPBao1%40thread.tacv2/1638719716825?context=%7b%22Tid%22%3a%2222804ebb-30d5-47df-942f-f3a3722f0225%22%2c%22Oid%22%3a%2216a60c03-ad7a-4b85-a403-8ebd947e010c%22%7d
Abstract:
High-performance clusters and datacenters pose increasingly demanding requirements on storage systems. If these systems do not operate at scale, applications are doomed to become I/O bound and waste compute cycles. To accelerate the data path to remote storage nodes, remote direct memory access (RDMA) has been embraced by storage systems to let data flow from the network to storage targets, reducing overall latency and CPU utilization. Yet, this approach still involves CPUs on the data path to enforce storage policies such as authentication, replication, and erasure coding. We show how storage policies can be offloaded to fully programmable SmartNICs, without involving host CPUs. By using PsPIN, an open-hardware SmartNIC, we show latency improvements for writes (up to 2x), data replication (up to 2x), and erasure coding (up to 2x), when compared to respective CPU- and RDMA-based alternatives.
Personal Introduction:
Torsten Hoefler is a Professor of Computer Science at ETH Zurich, a member of Academia Europaea, and a Fellow of the IEEE. Following a “Performance as a Science” vision, he combines mathematical models of architectures and applications to design optimized computing systems. Before joining ETH Zurich, he led the performance modeling and simulation efforts for the first sustained Petascale supercomputer, Blue Waters, at the University of Illinois at Urbana-Champaign. He is also a key contributor to the Message Passing Interface (MPI) standard where he chaired the “Collective Operations and Topologies” working group. Torsten won best paper awards at ACM/IEEE Supercomputing in 2010, 2013, 2014, 2019, and at other international conferences. He has published numerous peer-reviewed scientific articles and authored chapters of the MPI-2.2 and MPI-3.0 standards. For his work, Torsten received the ACM Gordon Bell Prize in 2019, the IEEE TCSC Award of Excellence (MCR), ETH Zurich’s Latsis Prize, the SIAM SIAG/Supercomputing Junior Scientist Prize, the IEEE TCSC Young Achievers in Scalable Computing Award, and the BenchCouncil Rising Star Award. Following his Ph.D., he received the 2014 Young Alumni Award and the 2022 Distinguished Alumni Award of his alma mater, Indiana University. Torsten was elected to the first steering committee of ACM’s SIGHPC in 2013 and he was re-elected for every term since then. He was the first European to receive many of those honors; he also received both an ERC Starting and Consolidator grant. His research interests revolve around the central topic of performance-centric system design and include scalable networks, parallel programming techniques, and performance modeling for large-scale simulations and artificial intelligence systems.
[Editor: Jian Wang]