1 / 12

The Future of Supercomputing

The Future of Supercomputing. Dr. Peg Williams SVP, HPC Systems. Simple View of the World of Computing. The Bifurcation “Problem” In HPC. Will all HPC Move to the Cloud?.

cato
Download Presentation

The Future of Supercomputing

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. The Future of Supercomputing Dr. Peg Williams SVP, HPC Systems

  2. Simple View of the World of Computing

  3. The Bifurcation “Problem” In HPC

  4. Will all HPC Move to the Cloud? “Overall results indicate that EC2 is six times slower than a typical mid-range Linux cluster, and twenty times slower than a modern HPC system. The interconnect on the EC2 cloud platform severely limits performance and causes significant variability.” ̶ United States Department of Energy. Performance Analysis of High Performance Computing Applications on the Amazon Web Services Cloud. http://www.nersc.gov/news/reports/technical/CloudCom.pdf A three generation old Cray supercomputer is more scalable and 20x faster than Amazon’s current cloud—limiting its productivity on today’s HPC applications (This independent study used only 3,500 cores out of over 38,000 on the Cray system)

  5. Scalability: Moore’s Law2 Average Number of Processor Cores per Supercomputer (Top 20 of Top 500) Source: www.top500.org

  6. So What Will Supercomputing Look Like… The flattening of per-core performance has renewed interest in novel processing architectures Supercomputing will become almost solely focused on scalability

  7. Cray Perspective on Accelerated Computing

  8. Key Challenges to Get to Exascale

  9. Concept Exascale System • ~ 250 cabinets • ~12-14 TF processor • ~5 PF per cabinet • >1 EF peak • >100,000 sockets (~ Billion threads) • 6.5 PB on-socket memory (512 GBs/socket) • 50 PB off-socket memory (64 GBs/socket) • 20-30 MW

  10. The Supercomputing Evolution…

  11. Seymour Cray June 4, 1995 "The future is seldom the same as the past"

More Related