Improving all-reduce collective operations for imbalanced process arrival patterns - Publikacja - MOST Wiedzy

Wyszukiwarka

Improving all-reduce collective operations for imbalanced process arrival patterns

Abstrakt

Two new algorithms for the all-reduce operation optimized for imbalanced process arrival patterns (PAPs) are presented: (1) sorted linear tree, (2) pre-reduced ring as well as a new way of online PAP detection, including process arrival time estimations, and their distribution between cooperating processes was introduced. The idea, pseudo-code, implementation details, benchmark for performance evaluation and a real case example for machine learning are provided. The results of the experiments were described and analyzed, showing that the proposed solution has high scalability and improved performance in comparison with the usually used ring and Rabenseifner algorithms.

Cytowania

0
CrossRef
0
Web of Science
0
Scopus

Jerzy Proficz. (2018). Improving all-reduce collective operations for imbalanced process arrival patterns, 1-22. https://doi.org/10.1007/s11227-018-2356-z

Informacje szczegółowe

Kategoria:
Publikacja w czasopiśmie
Typ:
artykuł w czasopiśmie wyróżnionym w JCR
Opublikowano w:
JOURNAL OF SUPERCOMPUTING strony 1 - 22,
ISSN: 0920-8542
Język:
angielski
Rok wydania:
2018
Opis bibliograficzny:
Proficz J.: Improving all-reduce collective operations for imbalanced process arrival patterns// JOURNAL OF SUPERCOMPUTING. -, (2018), s.1-22

wyświetlono 12 razy

Publikacje, które mogą cię zainteresować

Meta Tagi