January 19, 2012
Last year, South Africa's Centre for High Performance Computing's (CHPC) upgraded its number one supercomputer, known as known as Tsessebe, with the latest Dell PowerEdge 6100 server, increase its Linpack performance to 61 teraflops. That was enough to earn it the number 329 spot on the November 2011 TOP500 list.
According to an article in Creamer Media's Engineering News, the upgrade was initiated to "cater for the increased demand for high performance computing by various universities and science council teams, bringing utilisation to nearly 100 percent." The work, which cost 9 million Rand (just under $1.14 million), was facilitated with the help of the Cambridge High Performance Computing Centre, Dell and Eclipse Holdings, a local datacenter facilities management firm.
Tsessebe was first deployed in 2009 as a Sun Microsystems (now Oracle) blade server cluster, which at the time placed it at number 313 on the TOP500 list. The Sun blades sport both Intel Nehalem (4-core) and Westmere (6-core) Xeon CPUs. The Dell PowerEdge 6100 servers that were added last year are also equipped with Westmere parts. The cluster is hooked together with InfiniBand and runs as a single, if somewhat heterogeneous, cluster.
Tsessebe is currently the most powerful supercomputer in South Africa. In fact it's the most powerful system on the entire content. Tanzania and Egypt are the only other two African nations known to have HPC clusters, and they are in the single-digit teraflop range.
The need for more high performance computing is acute. The region's problems related to drought, climate change, HIV and malaria are all application areas that can benefit from the HPC-level simulations and analytics. South African industry is also in need of HPC capability to help maintain its competitive edge in the global marketplace. According to the Engineering News report, there are plans in place at CHPC to add another supercomputer next year to help meet some of that unmet demand.
Radware Joins OpenStack Community
Zunicore Offers Bare Metal by the Hour
Red Hat Celebrates 10 Years of Red Hat Enterprise Linux, Reaffirms Strategic Direction
Bright Computing Brings Data Aware Scheduling to Cloud Bursting into Amazon EC2
NVIDIA Introduces Virtualized GPU, Accelerating Graphics for Cloud Computing
There are 0 discussion items posted.
|
Join the Discussion |
Higher education involves many collaborative projects that lend themselves to cloud services, however often those services are not tailored to the uniqueness of an academic environment. That's where the Internet2 NET+ project comes in. By partnering with 16 major cloud providers, the networking consortium is seeking to expedite the delivery of cloud services and by doing so advance research and innovation in the United States.
Read more...
It's been a little over a year since Univa took over stewardship of the open source workload manager and acquired the founding Sun Grid Engine team from Oracle, and the company just announced its third production release. CEO Gary Tyreman discusses the latest enhancements as well as the company's plans around cloud, big data and the enterprise.
Read more...
04/05/2012 | Appro | Designed to meet the growing global demand for HPC solutions, Appro's Xtreme-X™ Supercomputer delivers superior performance-per-watt and reduced I/O latency while bringing significant flexibility to HPC workload configurations including capacity, hybrid, data intensive and capability computing.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.