Quasi-supercomputing

Some types of large-scale distributed computing for embarrassingly parallel problems take the clustered supercomputing concept to an extreme. The fastest, Folding@home, reported over 8.1 petaflops of processing power as of April 8, 2009. Of this, 2.5 petaflops of this processing power is contributed by clients running on PlayStation 3 systems and another 5.3 petaflops is contributed by their newly released GPU2 client.[4] Another distributed computing project BOINC platform, a host for a number of distributed computing projects. As of February 2009[update], BOINC recorded a processing power of over 1.7 petaflops through over 530,000 active computers on the network.[5] One such project, SETI@home, reported processing power of over 508 teraflops through almost 317,000 active computers.[6] As of May 2008[update], GIMPS's distributed Mersenne Prime search achieves currently 29 teraflops.[citation needed] Also a “quasi-supercomputer” is Google's search engine system with estimated total processing power of between 126 and 316 teraflops, as of April 2004.[7] In June 2006 the New York Times estimated that the Googleplex and its server farms contain 450,000 servers.[8] According to recent estimations, the processing power of Google's cluster might reach from 20 to 100 petaflops.[9] The PlayStation 3 Gravity Grid uses a network of 16 machines, and exploits the Cell processor for the intended application which is binary black hole coalescence using perturbation theory.[10][11] The Cell processor has a main CPU and 6 floating-point vector processors, giving the machine a net of 16 general-purpose machines and 96 vector processors. The machine has a one-time cost of $9,000 to build and is adequate for black-hole simulations which would otherwise cost $6,000 per run on a conventional supercomputer. The black hole calculations are not memory-intensive and are highly localizable, and so are well-suited to this architecture.