HackingTheUniverse

You are browsing the archives of supercomputer.

The University of Texas at Austin is building a new supercomputer called Stampede, which will be housed in the Texas Advanced Computing Center (TACC). Dell servers, Intel coprocessors, and NVIDIA GPUs will comprise the hardware for the linux cluster, which is expected to reach a performance level of over 10 quadrillion calculations per second (petaflop). [...]

It’s no surprise any more that we expect computers to get both smaller and more powerful every year. Most sugar cubes measure about 1 cubic centimeter. Scientists at IBM are working on a cooling system that they think will enable supercomputing capability in a very small form factor. Supercomputers the size of sugar cubes – [...]

Early lasers “pumped” ruby rods with light from flash tubes creating a photon cascade that eventually produced a beam of coherent light. Recently, lasers have been developed that can produce a coherent beam of light from a silicon chip. Raman lasers are a particular type of silicon lasers. Simulations done on supercomputers have shown that [...]

Red Storm is a massively parallel processing supercomputer developed by Sandia Labs and Cray for the Department of Energy to do advanced simulation and modeling in nuclear weapons research. It is now being rededicated to national security problems including cyber defense, vulnerability assessments, situational awareness and more. NNSA Dedicates National Security Computing Center at Sandia [...]

Intel’s promise to deliver computers with thousands of processing cores takes a big step forward with the announcement of a 48 core CPU that they call the Single-chip Cloud Computer (SCC). It claims to use better power management, high speed internal communications and provide good software compatibility. Single-chip Cloud Computer – [intel.com] Overview Intel Labs [...]

FutureGrid is a high speed network connected to clusters of high performance computers and linked to Teragrid. TeraGrid is the worlds largest distributed cyber-infrastructure that integrates high performance computers, data resources and experimental facilities. While TeraGrid is designed to provide computing resources, FutureGrid is oriented toward developing tools and technologies. What is FutureGrid? – [teragrid.org] [...]

Sandia computer scientists successfully boot one million Linux kernels as virtual machines – [sandia.gov] Computer scientists at Sandia National Laboratories in Livermore, Calif., have for the first time successfully demonstrated the ability to run more than a million Linux kernels as virtual machines. The achievement will allow cyber security researchers to more effectively observe behavior [...]

Wolfram Mathematica allows you to model and visualize mathematical algorithms. It integrates a computational engine, graphics, a programming language, and an interface to a wide variety of external tools. It includes access to a very large set of mathematical and engineering functions. The Mathematica Grid system now extends this computational power across many systems using [...]

The National Center for Computational Sciences (NCCS) is part of Oak Ridge National Laboratory in Tennessee that is run by the Department of Energy (DOE). The function of the NCCS is to provide state of the art high-performance computing resources for scientific research. The center hosts the “Jaguar” supercomputer which is based on Cray XT4 [...]

Grid Appliance is a virtual appliance (a virtual machine system application) that enables grid computing across multiple hardware platforms using an IPOP virtual network and Condor grid scheduling software. The software is linux based, open source and runs on VMWare workstation, player or server. VirtualBox and KVM images are also supported. The appliance can be [...]