Transcript siam_10
Exa-Scale Volunteer Computing David P. Anderson Space Sciences Laboratory U.C. Berkeley The potential of volunteer computing • • The volunteer resource pool Current PetaFLOPS breakdown: • Potential: ExaFLOPS by 2010 – 4M GPUs * 1 TFLOPS * 0.25 availability Why did F@h and S@h work? • • • Technology-savvy leaders Technical resources Funding So they were able to develop their own software stack. But few research groups can do this. BOINC • Middleware for volunteer computing – client, server, web • Based at UC Berkeley Space Sciences Lab • Open source (LGPL) • NSF-funded since 2002 • http://boinc.berkeley.edu BOINC: volunteers and projects projects volunteers LHC@home CPDN attachments WCG The Utopian vision resources Scientific research The public education/outreach • Better research gets more computing power • An enlightened public decides what’s better Science areas using BOINC • • • • • • Biology – protein study, genetic analysis Medicine – drug discovery, epidemiology Physics – LHC, nanotechnology, quantum computing Astronomy – data analysis, cosmology, galactic modeling Environment – climate modeling, ecosystem simulation Math Climateprediction.net Einstein@home • Gravitational waves; gravitational pulsars Milkyway@home GPUGRID.net AQUA@home • D-Wave Systems • Simulation of “adiabatic quantum algorithms” for binary quadratic optimization Quake Catcher Network Success: modest at best • Only ~25 significant projects, few new ones • Why? – Even with BOINC, it’s hard to operate a volunteer computing project – Volunteer computing ignored by the HPC world • It doesn’t provide ownership or control Umbrella projects Project publicity web development sysadmin app porting Example: IBM World Community Grid The Berkeley@home model • A university has – – – – – scientists a powerful “brand” PR resources IT infrastructure lots of alumni (UCB: 500,000) Hubs • • nanoHUB: “science portal” for nanoscience – social network + “app store” – sharing of ideas, data, software – computational portal HUBzero: generalization to other areas – • currently ~20 hubs Integration of BOINC with HUBzero – each hub has a volunteer computing project – use VMs to deal with security, heterogeneity issues Conclusion • Volunteer computing + GPUs = Exa-scale • How to increase adoption? • Organizational level matters email me: [email protected]