Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Osamu Tatebe"'
Publikováno v:
Journal of Universal Computer Science, Vol 26, Iss 1, Pp 89-106 (2020)
Metadata performance scalability is critically important in high-performance computing when accessing many small files from millions of clients. This paper proposes a design of a scalable distributed metadata server, PPMDS, for parallel file systems
Externí odkaz:
https://doaj.org/article/2ccef8d34bb446cb99c4f1763ab41a04
Autor:
Ken T Murata, Shinichi Watari, Tsutomu Nagatsuma, Manabu Kunitake, Hidenobu Watanabe, Kazunori Yamamoto, Yasufumi Kubota, Hisao Kato, Takuya Tsugawa, Kentaro Ukawa, Kazuya Muranaga, Eizen Kimura, Osamu Tatebe, Keiichiro Fukazawa, Yasuhiro Murayama
Publikováno v:
Data Science Journal, Vol 12 (2013)
It is often discussed that the fourth methodology for science research is "informatics". The first methodology is a theoretic approach, the second one is observation and/or experiment, and the third one is computer simulation. Informatics is a new me
Externí odkaz:
https://doaj.org/article/7457d1c1101d4ae28dd740bf76b31511
Publikováno v:
Workshop Proceedings of the 51st International Conference on Parallel Processing.
Autor:
Osamu Tatebe, Hiroki Ohtsuji
Publikováno v:
2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).
Autor:
Sohei Koyama, Osamu Tatebe
Publikováno v:
2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).
Publikováno v:
International Conference on High Performance Computing in Asia-Pacific Region.
Publikováno v:
Proceedings of the VLDB Endowment. 13:3531-3544
This paper presents yet another concurrency control analysis platform, CCBench. CCBench supports seven protocols (Silo, TicToc, MOCC, Cicada, SI, SI with latch-free SSN, 2PL) and seven versatile optimization methods and enables the configuration of s
Publikováno v:
Journal of Computer Science and Technology. 35:61-71
Burst buffer has become a major component to meet the I/O performance requirement of HPC bursty traffic. This paper proposes Gfarm/BB that is a file system for a burst buffer efficiently exploiting node-local storage systems. Although node-local stor
Publikováno v:
IEEE BigData
This paper proposes and examines the three in-memory shuffling methods designed to address problems in MapReduce shuffling caused by skewed data. Coupled Shuffle Architecture (CSA) employs a single pairwise all-to-all exchange to shuffle both blocks,
Publikováno v:
International Journal of Networking and Computing. 9:339-353
A transactional system consists of a concurrency control system and a recovery system. TicToc is one of the state of the art concurrency control protocols today, but it lacks recovery system. We studied the ways to integrate TicToc and recovery syste