PPT-Designing In-network Computing Aware Reduction Collectives in MPI

Author : gatlin110 | Published Date : 2024-12-06

Presentation at OSU booth at SC23 Follow us on https twittercommvapich Bharath Ramesh The Ohio State University ramesh113osuedu Introduction Drivers of Modern HPC

Presentation Embed Code

Download Presentation

Download Presentation The PPT/PDF document "Designing In-network Computing Aware Red..." is the property of its rightful owner. Permission is granted to download and print the materials on this website for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Designing In-network Computing Aware Reduction Collectives in MPI: Transcript

Presentation at OSU booth at SC23 Follow us on https twittercommvapich Bharath Ramesh The Ohio State University ramesh113osuedu Introduction Drivers of Modern HPC Cluster Architectures. Uni processor computing can be called centralized computing brPage 3br mainframe computer workstation network host network link terminal centralized computing distributed computing A distributed system is a collection of independent computers interc Rui. Wang, . Erlin. Yao, . Pavan. . Balaji. , Darius . Buntinas. , . Mingyu. Chen, and . Guangming. Tan. Argonne National Laboratory, Chicago, USA. ICT, Chinese Academy of Sciences, China. Hardware Resilience for large-scale systems. Two-tier Direct Networks. EuroMPI – 2012. Nikhil . Jain, . JohnMark. . Lau, . Laxmikant. Kale. 26. th. . September, 2012. Motivation. Collectives are an important component of parallel programs. Parallel Computing. CIS . 410/. 510. Department of Computer and Information Science. Outline. What are Collectives?. Reduce Pattern. Scan Pattern. Sorting. 2. Introduction to Parallel Computing, University of Oregon, IPCC. Brief reflections on Dotter and . Klasen’s. proposals. Sabina . Alkire . and OPHI colleagues . 4 March 2013. A background paper is available upon request. Proposals by Dotter and Klasen 2013. Empirical . eet, we . c. hange the world.. http. ://youtu.be/BeyNb7Nft9o. Today’s Discussion. Overview. Leadership. MPI Foundation. Membership Value . I Am MPI. State of MPI. Open Discussion. Overview. Global Industry Impact. Junchao. Zhang. Argonne National Laboratory. jczhang@anl.gov. Pavan Balaji. Argonne National Laboratory. balaji@anl.gov. Ken . Raffenetti. Argonne National Laboratory. raffenet@anl.gov. Bill. . Long. By Using MPI on . . EumedGrid. . Abdallah. ISSA . Mazen. TOUMEH . Higher . Institute for Applied Sciences and . Technology-HIAST. . Damascus – Syria. Africa . James . Dinan. , . Pavan. . Balaji. , Jeff Hammond,. Sriram. . Krishnamoorthy. , and . Vinod. . Tipparaju. Presented by: James . Dinan. James Wallace Gives Postdoctoral Fellow. Argonne National Laboratory. Dhabaleswar K. (DK) Panda. The Ohio State University. E-mail: panda@cse.ohio-state.edu. http://www.cse.ohio-state.edu/~panda. Keynote Talk at ISCS (2015). by. High-End Computing (HEC): ExaFlop & ExaByte. Communication on Multicore Petascale Systems. Gabor Dozsa. 1. , Sameer Kumar. 1. , Pavan Balaji. 2. , Darius Buntinas. 2. ,. David Goodell. 2. , William Gropp. 3. , Joe Ratterman. 4. , and Rajeev Thakur. Slides Available at https://anl.box.com/v/2019-ANL-MPI/. Rajeev Thakur. Email: . thakur@anl.gov. Web: . http://www.mcs.anl.gov/~thakur. Pavan Balaji. Email: . balaji@anl.gov. Web: . http://www.mcs.anl.gov/~balaji. 2. Last Time…. We covered:. What is MPI (and the implementations of it)?. Startup & Finalize. Basic Send & Receive. Communicators. Collectives. Datatypes. 3. Basic Send/. Recv. 8. 19. 23. Process1. draft-he-coin-datacenter-00. Jeffrey He, Huawei. Rachel Chen, Huawei. Marie-José Montpetit, Triangle Video (. ed. ).. Draft Overview. Informative. Review the state of the art, current research and open questions.

Download Document

Here is the link to download the presentation.
"Designing In-network Computing Aware Reduction Collectives in MPI"The content belongs to its owner. You may download and print it for personal use, without modification, and keep all copyright notices. By downloading, you agree to these terms.