CESGA

CESGA stands for "Centro de Supercomputación de Galicia" (The Supercomputing Center of Galicia). It is a high performance computing center in Galicia (Spain).

Its most important features are the supercomputer FinisTerrae and the "Superordenador Virtual Gallego". Finisterrae is nowadays the third most powerful supercomputer in Spain, and it was initially ranked 100th according to the Top500 when installed on November 2007. CESGA provides advanced computing services to the Galician Scientific Community, Galician Universities and to the Spanish National Research Council (Consejo Superior de Investigaciones Científicas - CSIC).

CESGA also runs i-math, a Grid computing project with an initiative to approach Grid technologies to mathematics researchers, and operates the i-math Portal, a Grid Portal based on P-GRADE Portal technology.^[1] (See also: Grid computing)

Most important functions

To promote and spread the use of technologies of high performance computing and advanced communications. One of this examples is GalNIX, a neutral point of Internet traffic interchange for Galicia. The aim of GalNIX is to facilitate the data interchange between the Internet Service Providers which operate inside the Galician region. Some of the companies included here are Jazztel, "R cable y telecomunicaciones", Retegal and Retevisión.
To promote and spread the use of technologies related to the Information Society, including: electronic commerce, e-learning and geographical information systems.

Computer Systems

The following table shows some of the systems installed in CESGA. Since some systems were installed around 10 years ago some information may be outdated.

Computer system	Description	Installation date
Compaq HPC 320	Consists of a cluster of 8 servers hosting 32 Alpha EV68 1 GHz processors	2002
Cluster Beowulf	A cluster consisting of 17 Pentium III 1,13 GHz processors. The nodes are interconnected using a Myrinet network.	2002
CESGA CrossGrid Node	Consists of a cluster of 20 Intel Pentium III 1,13 processors interconnected using a Gigabit network	2002
SVG	The "Supercomputador Virtual Gallego" consists of 54 Intel Pentium III processors from 550 MHz up to 1 GHz interconnected through Myrinet and Fast Ethernet networks.	2000 (first phase)
CheapTB	Consists of 1 Intel Pentium III 1,2 GHz and 4 Pentium IV 2 GHz processors interconnected by a Myrinet network. The storage is made using 32x180 GB disks.	2003
Storagetek 9710	It is a tape storage system consisting of 195x220 GB and 375x80 GB cartridges	1999
HP Integrity Rx5670	Consists of 4 Intel Itanium2 processors interconnected using Fibre Channel.	2004
Storage array EVA 3000	Consists of 112x146 Fibre Channel disks configured in a RAID 5 system.	2003
Sun Microsystems HPC 4500	12 x UltraSPARC II 400 MHz processors	1999
Sun Enterprise 3500	4 x 400 MHz UltraSPARC II interconnected using an Ethernet -Gigabit connection	1999
HP Cluster Superdome	Consists of 2 SMP nodes which host 128 Intel Itanium2 1500 MHz processors. The connection is made using an Infiniband network.	2003

Location

CESGA is located in the University of Santiago de Compostela at the following address:

Avenida de Vigo, s/n Campus Sur 15705 Santiago de Compostela A Coruña - Spain

Tel: +34 981 56 98 10
Fax: +34 981 59 46 16

References

↑ M.T. Sánchez et al. 2008: "imath.cesga.es, the VO for the European mathematicians." In: Fernando Silva et al. (Eds): 2nd Iberian Grid Infrastructure Conference Proceedings, Porto: Universidade do Porto and Netbibilio

External links

Parallel computing
General	Distributed computing Parallel computing Massively parallel Cloud computing High-performance computing Multiprocessing Manycore processor GPGPU Computer network Systolic array
Levels	Bit Instruction Thread Task Data Memory Loop Pipeline
Multithreading	Temporal Simultaneous (SMT) Speculative (SpMT) Preemptive Cooperative Clustered Multi-Thread (CMT) Hardware scout
Theory	PRAM model Analysis of parallel algorithms Amdahl's law Gustafson's law Cost efficiency Karp–Flatt metric Slowdown Speedup
Elements	Process Thread Fiber Instruction window
Coordination	Multiprocessing Memory coherency Cache coherency Cache invalidation Barrier Synchronization Application checkpointing
Programming	Stream processing Dataflow programming Models Implicit parallelism Explicit parallelism Concurrency Non-blocking algorithm
Hardware	Flynn's taxonomy SISD SIMD SIMT MISD MIMD Dataflow architecture Pipelined processor Superscalar processor Vector processor Multiprocessor symmetric asymmetric Memory shared distributed distributed shared UMA NUMA COMA Massively parallel computer Computer cluster Grid computer
APIs	Ateji PX Boost.Thread Charm++ Cilk Coarray Fortran CUDA Dryad C++ AMP Global Arrays MPI OpenMP OpenCL OpenHMPP OpenACC TPL PLINQ PVM POSIX Threads RaftLib UPC TBB
Problems	Embarrassingly parallel Software lockout Scalability Race condition Deadlock Livelock Starvation Deterministic algorithm Parallel slowdown
Category: parallel computing Media related to Parallel computing at Wikimedia Commons

This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.