Terapix Star Formation Region IC 1396, © 2002 CFHT
The TERAPIX cluster
Last content update May 23rd, 2003

The key to getting more computing power at a modest price is to operate several machines in parallel. The implementation of choice is traditionally a cluster of Linux PCs ("Beowulf").

However, the requirements of TERAPIX for massive data processing are quite different from those of programs that make explicit use of parallel code like numerical simulations, where low latency is of utter importance, and CPU time exceeds by a large factor time spent in data transfers.

In our case, latencies are not an issue, because data are always transfered in large chunks (several Megabytes), and the pipeline parallelism is very coarse-grained. What is important is to have as much aggregate bandwidth as possible between storage areas and the processors.

This is why both computing power (the CPUs) and mass storage (the disks) are distributed in the Terapix cluster.

The Terapix Cluster is funded by the french CNRS INSU agency and the european contract Astrophysical Virtual Observatory (AVO).

More information
-  diagram of TERAPIX network
-  picture of TERAPIX cluster (big view)

Latest News
4 new nodes have been added to the cluster
February 19th, 2003
Gigabit switch
October 7th, 2002
Hardware ready
March 6th, 2002
Hardware instability
February 11th, 2002
ICC Compiler
February 1st, 2002
section News
section Recipes

Site Map  -   -  Contact
© Terapix 2003-2011