UMA hardware resources

The computational servers

• 1 fast computer (Frequ > 4 GHz) : 32 logical cores with Hyperthreading / 16 physical cores - 384 GB RAM - 2.5 TB SSD (2017 - 2018)
• 3 fast computer (Frequ > 4 GHz) : 16 logical cores with Hyperthreading / 8 physical cores - 256 GB RAM - 1 TB SATA HD + 256 GB SSD (2017 - 2018)
• 1 computer : Proc. 24 logical cores with Hyperthreading / 12 physical cores - 256 GB RAM - 1 TB SATA HD + 256 GB SSD (2015)
• 1 computer : Proc. 8 logical cores with Hyperthreading / 16 physical cores - 768 GB RAM - 1 TB SATA HD + 256 GB SSD (2015)
• 1 computer : Proc. 64 logical cores with Hyperthreading / 32 physical cores - 1 TB RAM - 300 GB HD (2014)
• 2 computers : Proc. 32 logical cores with Hyperthreading / 16 physical cores - 128 GB RAM - 935 GB HD 1 TB SATA HD + 256 GB SSD (2013 - 2014)
• 2 computers : Proc. Intel Sandy Bridge XEON E3-1280 at 3,49 GHz / 4 cores - 32 GB RAM - 500 GB HD (2011)

The cluster

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 is renewed every four year thereby maintaining a degree of investment. Today, the UMA has 64 processors with 512 cores interconnected by a Gigabit network layer.

This type of configuration 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 (GPU)

• Compute Node Hybride CPU/GPU CUDA 4220 (8 Intel cores XEON E5-2637 / 1 x Tesla K80) - 128 GB RAM 1 TB SATA HD + 256 GB SSD (2015)

Support

All UMA hardware resources are fully administered and managed by Christophe Mathulik.

top