DocumentCode :
1878521
Title :
SymSig: A low latency interconnection topology for HPC clusters
Author :
Brahme, Dhananjay ; Bhardwaj, Onkar ; Chaudhary, Varun
Author_Institution :
High Performance Comput., Tata Consultancy Services, Pune, India
fYear :
2013
fDate :
18-21 Dec. 2013
Firstpage :
462
Lastpage :
471
Abstract :
This paper presents the underlying theory and the performance of a cluster using a new 2-hop network topology. This topology is constructed using a symmetric equation and Singer Difference Sets and is called SymSig. The degree of connections at each node with SymSig is about half compared to previous methods using Singer Difference Sets. A comparison with a cluster of Clos topology shows significant advantages. The worst case congestion in SymSig topology for unicast permutation is 2, where as in Clos it is proportional to the radix of the building block switches used. The number of switches required is smaller by about 25%, the size of the cluster is larger by about 15% and the worst bandwidth is better by about 50% for SymSig. These advantages are retained for peta and exascale systems. Its performance on a set of collectives like exchange-all, shift-all, broadcast-all and all-to-all send/receive shows improvements ranging from 39% to 83%. Its performance on a molecular dynamics application GROMMACS shows improvement of upto 33%. This network is particularly suitable for applications that require global all to all communications. The low latency of this network makes it scaleable and an attractive alternative for building peta and exascale systems.
Keywords :
molecular dynamics method; multistage interconnection networks; network topology; parallel processing; set theory; 2-hop network topology; Clos topology; GROMMACS; HPC clusters; SymSig topology; building block switches; latency interconnection topology; molecular dynamics application; radix; singer difference sets; symmetric equation; unicast permutation; worst case congestion; Bandwidth; Equations; Image color analysis; Network topology; Ports (Computers); Routing; Topology; bandwidth; benchmark; communication library functions; computer architecture; exascale computing; high performance computing; high performance computing applications; latency; network; parallel computer architecture; parallel computing; routing algorithms and techniques; topology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
High Performance Computing (HiPC), 2013 20th International Conference on
Conference_Location :
Bangalore
Type :
conf
DOI :
10.1109/HiPC.2013.6799144
Filename :
6799144
Link To Document :
بازگشت