Cycle Computing

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Cycle Computing is a company offering high-performance computing clusters on rent at an hourly rate to clients, allowing people to have access to virtual supercomputers for short periods of time.[1] It uses Amazon Web Services and is part of the AWS Partner Network.[2]

History[edit]

In September 2011, a Cycle Computing HPC cluster called Nekomata (Japanese for "Monster Cat") was renting out at $1279/hour, offering 30,472 processor cores with 27TB of memory and 2PB of storage. An unnamed pharmaceutical company used the cluster for 7 hours, paying $9000, for a molecular modeling task.[3][4][5]

In April 2012, Cycle Computing announced that, working in collaboration with scientific software-writing company Schrödinger, it had screened 21 million compounds in less than three hours using a 50,000-core cluster.[6]

In November 2013, Cycle Computing announced that, working in collaboration with scientific software-writing company Schrödinger, it had helped Mark Thompson, a professor of chemistry at the University of Southern California, sort through about 205,000 compounds to search for the right compound to build a new generation of inexpensive and highly efficient solar panels. The job took less than a day and cost $33,000 in total. The computing cluster used 156,000 cores spread across 8 regions and had a peak capacity of 1.21 petaFLOPS.[7][8][9][10][11]

Media coverage[edit]

Cycle Computing has been covered by GigaOm,[6][9] Ars Technica,[5] ExtremeTech,[3] CNet,[10] and Phys.org.[8]

Cycle Computing was also mentioned by Amazon CTO Werner Vogels in the 2013 Day 2 Keynote of AWS re:Invent.[12]

External links[edit]

References[edit]

  1. ^ "About". Cycle Computing. Retrieved January 26, 2014. 
  2. ^ "AWS Case Study: Varian". Amazon Web Services. Retrieved January 26, 2014. 
  3. ^ a b Anthony, Sebastian (September 20, 2011). "Rent the world’s 30th-fastest, 30,472-core supercomputer for $1,279 per hour". ExtremeTech. Retrieved January 26, 2014. 
  4. ^ "New CycleCloud HPC Cluster Is a Triple Threat: 30000 cores, $1279/Hour, & Grill monitoring GUI for Chef". Cycle Computing. September 19, 2011. Retrieved January 26, 2014. 
  5. ^ a b Brodkin, Jon (September 20, 2011). "$1,279-per-hour, 30,000-core cluster built on Amazon EC2 cloud A supercomputer built on Amazon's cloud is used for pharma research". Ars Technica. Retrieved January 26, 2014. 
  6. ^ a b Darrow, Barb (April 19, 2012). "Cycle Computing spins up 50K core Amazon cluster". GigaOm. Retrieved January 26, 2014. 
  7. ^ "Back to the Future: 1.21 petaFLOPS(RPeak), 156,000-core CycleCloud HPC runs 264 years of Materials Science". Cycle Computing. November 12, 2013. Retrieved January 26, 2014. 
  8. ^ a b Yirka, Bob (November 12, 2013). "Cycle Computing uses Amazon computing services to do work of supercomputer". Phys.org. Retrieved January 26, 2014. 
  9. ^ a b Darrow, Barb (November 12, 2013). "Cycle Computing once again showcases Amazon’s high-performance computing potential". GigaOm. Retrieved January 26, 2014. 
  10. ^ a b Shankland, Stephen (November 12, 2013). "Supercomputing simulation employs 156,000 Amazon processor cores: To simulate 205,000 molecules as quickly as possible for a USC simulation, Cycle Computing fired up a mammoth amount of Amazon servers around the globe.". CNet. Retrieved January 26, 2014. 
  11. ^ Brueckner, Rich (November 13, 2013). "Slidecast: How Cycle Computing Spun Up a Petascale CycleCloud". Inside HPC. Retrieved January 26, 2014. 
  12. ^ Vogels, Werner. "AWS re:Invent 2013 Day 2 Keynote with Werner Vogels". AWS re:Invent 2013. Retrieved January 30, 2014.