Exploiting copy engines for intra-node MPI collective communication
Open Access
- 11 May 2023
- journal article
- research article
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 79 (16) , 17962-17982
Abstract
As multi/many-core processors are widely deployed in high-performance computing systems, efficient intra-node communication becomes more important. Intra-node communication involves data copy operations to move messages from source to destination buffer. Researchers have tried to reduce the overhead of this copy operation, but the copy operation performed by CPU still wastes the CPU resources and even hinders overlapping between computation and communication. The copy engine is a hardware component that can move data between intra-node buffers without intervention of CPU. Thus, we can offload the copy operation performed by CPU onto the copy engine. In this paper, we aim at exploiting copy engines for MPI blocking collective communication, such as broadcast and gather operations. MPI is a messaging-based parallel programming model and provides point-to-point, collective, and one-sided communications. Research has been conducted to utilize the copy engine for MPI, but the support for collective communication has not yet been studied. We propose the asynchronism in blocking collective communication and the CE-CPU hybrid approach to utilize both copy engine and CPU for intra-node collective communication. The measurement results show that the proposed approach can reduce the overall execution time of a microbenchmark and a synthetic application that perform collective communication and computation up to 72% and 57%, respectively.Keywords
Funding Information
- Ministry of Science and ICT, South Korea (2020M3H6A1084853, 2020M3H6A1084853)
This publication has 23 references indexed in Scilit:
- MPI performance engineering with the MPI tool interface2017
- Casper: An Asynchronous Progress Model for MPI RMA on Many-Core Architectures2015
- Benefits of Cross Memory Attach for MPI libraries on HPC Clusters2014
- Exploring Traditional and Emerging Parallel Programming Models Using a Proxy Application2013
- KNEM: A generic and scalable kernel-assisted intra-node MPI communication frameworkJournal of Parallel and Distributed Computing, 2013
- Kernel Assisted Collective Intra-node MPI Communication among Multi-Core and Many-Core CPUs2011
- Message progression in parallel computing - to thread or not to thread?2008
- Implementation and performance analysis of non-blocking collective operations for MPI2007
- Efficient asynchronous memory copy operations on multi-core systems and I/OAT2007
- The NAS parallel benchmarks---summary and preliminary results1991