conference paper
Designing Non-blocking Personalized Collectives with Near Perfect Overlap for RDMA-Enabled Clusters
Hari Subramonia✉, Ammar Ahmad Awana, Khaled Hamidouchea, Dmitry Pekurovskyb, Akshay Venkatesha, Sourav Chakrabortya, Karen A. Tomkoc, Dhabaleswar K. DK Pandaa
- aDepartment of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA
- bSan Diego Supercomputer Center, San Diego, California
- cOhio Supercomputer Center, Columbus, OH, USA
- ✉Corresponding author
Lecture notes in computer scienceSpringer Science+Business Media2015-01-01 17 citations25 references
Looking for the full paper…
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
No abstract is available from our sources. Use “Read paper” to view it.
TL;DRThe proposed RDMA-Aware collectives are able to deliver near perfect overlap of computation and communication for personalized collective operations on modern HPC systems at scale and deliver improvements in latency and communication at the microbenchmark level. (Semantic Scholar)