SHARCNET Multicomputer Systems r A multicomputer system comprises

  • Slides: 12
Download presentation
SHARCNET

SHARCNET

Multicomputer Systems r A multicomputer system comprises of a number of independent machines linked

Multicomputer Systems r A multicomputer system comprises of a number of independent machines linked by an interconnection network. r Each computer executes its own program which may access its local memory and may send and receive messages over the network. r The nature of the interconnection network has been a major topic of research for both academia and industry. r Distributed systems is one type of multicomputer system. What about others?

Multiprocessor Usage • Scientific and engineering applications often require loops over large vectors e.

Multiprocessor Usage • Scientific and engineering applications often require loops over large vectors e. g. , matrix elements or points in a grid or 3 D mesh. Applications include • • Computational fluid dynamics Scheduling (airline) Health and biological modeling Economics and financial modelling (e. g. , option pricing)

Multiprocessor Usage r It should be noted that people have been developing “clusters” of

Multiprocessor Usage r It should be noted that people have been developing “clusters” of machines that are connected using Ethernet for parallel applications. r The first such cluster (developed by two researchers at NASA) had 16 486 machines and was connected using 10 Mb Ethernet. r This is known as the Beowulf approach to developing a parallel computing and the clusters are sometimes called Beowulf clusters.

Sharcnet r UWO has taken a leading role in Canada in exploiting the concepts

Sharcnet r UWO has taken a leading role in Canada in exploiting the concepts behind the Beowulf cluster. r High performance clusters: “Beowulf on steroids” m m Powerful “off the shelf” computational elements Advanced communications r Geographical separation (local use) r Connect clusters: emerging optical communications r This is referred to as Shared Hierarchical Academic Research Computing Network or Sharcnet

Sharcnet r One cluster is called “Great White” r Processors: m 4 alpha processors:

Sharcnet r One cluster is called “Great White” r Processors: m 4 alpha processors: 833 Mhz (4 p-SMP) m 4 Gb of memory m 38 SMPs: a total of 152 processors r Communications m 1 Gb/sec ethernet m 1. 6 Gb/sec quadrics connection r November 2001: #183 in the world m Fastest academic computer in Canada m 6 th fastest academic computer in North America

Sharcnet Great White (in Western Science Building)

Sharcnet Great White (in Western Science Building)

Sharcnet r Extend “Beowulf” approach to clusters of high performance clusters r Connect clusters:

Sharcnet r Extend “Beowulf” approach to clusters of high performance clusters r Connect clusters: “clusters of clusters” m Build on emerging optical communications m Initial configuration used optical equipment from telecommunications industry r Collectively a supercomputer!

Sharcnet GUELPH 108 Optical communication UWO 48 MAC 128 152 Clusters across Universities (initial

Sharcnet GUELPH 108 Optical communication UWO 48 MAC 128 152 Clusters across Universities (initial cluster)

Sharcnet r In 2004, UWO received an investment of 56 million dollars from the

Sharcnet r In 2004, UWO received an investment of 56 million dollars from the government and private industry (HP) to expand Sharcnet. r With the new capabilities, Sharcnet could be in the top 100 or 150 of supercomputers. r Will be the fastest supercomputer of its kind – I. e. , a distributed system where nodes are clusters.

Sharcnet

Sharcnet

Sharcnet Applications running on Sharcnet come from all sorts of domains including m Chemistry

Sharcnet Applications running on Sharcnet come from all sorts of domains including m Chemistry m Bioinformatics m Economics m Astrophysics m Material Science and Engineering