UMA hardware resourcesNavigation : Computational servers | Cluster | GPGPU | Members and users
The computational servers
- 1 computer : Proc. 64 logical cores with Hyperthreading activé / 32 physical cores - 1 To de RAM - 300 Go HD (2014)
- 2 computers : Proc. 32 logical cores with Hyperthreading activé / 16 physical cores - 128 Go de RAM - 935 Go HD (2013 - 2014)
- 2 computers : Proc. Intel Sandy Bridge XEON E3-1280 at 3,49 GHz / 4 coeurs - 32 Go RAM - 500 Go HD (2011)
- 2 computers : Bi-pro. Intel Nehalem XEON 5670 at 2,93 GHz / 6 coeurs - 24 Go de RAM - 500 Go HD (2010)
- 2 computers : Bi-pro. Intel Nehalem XEON 5570 at 2,93 GHz - 24 Go de RAM - 160 Go HD (2009)
Following the significant reduction in the cost of the hardware in recent years and in order to meet the needs of high performance computing and scalable algorithms, in 1999 the UMA adopted a cluster consisting of several interconnected PCs via a bi-processor standard network layer. This cluster consisting of 32 heterogeneous machines (three generations of machines) is renewed every third year thereby maintaining a degree of investment. Today, the UMA has 64 processors with 532 cores interconnected by a Gigabit network layer.
- **fait** ftta: achat balles baby de compét pour FTTA (et pour les élèves) This type of configuration, with a cost of a few tens of thousands of Euros, can offer a significant computational power in a context of parallel code execution and scaling. The cluster now utilizes a Linux operating system which is relatively simple platform to implement thereby reducing the cost of administration.
The graphic unit (GPGPU)UMA also has a GPGPU Machine:
- Nvidia Tesla S1070-500 16G (4 x Nvidia Tesla C1060).
Members and users
All UMA hardware resources are fully administered and managed by Christophe Mathulik.
The computational power of the cluster is notably implemented and used by the "Gravitational Dynamical Systems" team. In connection with this method of calculation, the UMA provides the infrastructure and parts of a third year course module at ENSTA which is devoted to distributed computing. These course material are implemented via projects on the cluster.