Premium
Analyzing the impact of communication imbalance in high‐speed networks
Author(s) -
Utrera Gladys,
Gil Marisa,
Martorell Xavier
Publication year - 2017
Publication title -
concurrency and computation: practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.309
H-Index - 67
eISSN - 1532-0634
pISSN - 1532-0626
DOI - 10.1002/cpe.4394
Subject(s) - infiniband , computer science , gigabit ethernet , myrinet , benchmark (surveying) , latency (audio) , interconnection , remote direct memory access , low latency (capital markets) , computer network , gigabit , distributed computing , ethernet , parallel computing , computation , message passing , telecommunications , geodesy , algorithm , geography
Summary In this work we analyze the communication load imbalance generated by irregular‐data applications running in a multi‐node cluster. Experimental approaches to diminish communication load imbalance are evaluated using a hybrid programming model MPI + OpenMP including certain optimizations such as computation‐communication overlap, issuing communications in parallel, and a new proposal based on message fragmentation to take advantage of the eager‐protocol. Performance results show that overlapped versions can obtain a great benefit of this optimization because it avoids switching to rendezvous protocols. However, non‐overlapped versions showed a better performance than overlapped ones. To evaluate also the impact due to network latency, the work has been tested on two high‐speed interconnection networks: Infiniband and 10 Gigabit Ethernet. In this case, the optimizations in the non‐overlapped miniFE benchmark reached and improved up to 7% on Infiniband and 11% on 10 Gigabit.