@inproceedings{bf1bd27c55034d3cb86d1e4864ccf8b3,
title = "Towards unification of accelerated computing and interconnection for extreme-scale computing",
abstract = "Heterogeneous clusters using accelerators are widely used for high-performance computing system. In such systems, the inter-node communication among accelerators becomes bottleneck due to the data transfer between the accelerator and the host. To eliminate this overhead, we have been developing a novel communication system realizing direct communication among accelerators over computation nodes under the HA-PACS (Highly Accelerated Parallel Advanced system for Computational Sciences) project. Also we are investigating high-level parallel programming language, and several practical application programs on our concept, as well as studying the enhancement of TCA and developing system software stack in the CREST project.",
keywords = "Accelerator computing, GPU direct, Interconnection network, PCI express, Remote DMA",
author = "Toshihiro Hanawa and Yuetsu Kodama and Taisuke Boku and Hideharu Amano and Hitoshi Murai and Masayuki Umemura and Mitsuhisa Sato",
year = "2015",
month = jan,
day = "1",
doi = "10.1007/978-3-319-16214-0_43",
language = "English",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "463--474",
editor = "Diniz, {Pedro C.} and Kentaro Sano and Michael H{\"u}bner and Dimitrios Soudris",
booktitle = "Applied Reconfigurable Computing - 11th International Symposium, ARC 2015, Proceedings",
note = "11th International Symposium on Applied Reconfigurable Computing, ARC 2015 ; Conference date: 13-04-2015 Through 17-04-2015",
}