1 / 6

Strategies for preparing for PetaScale computing

Strategies for preparing for PetaScale computing. Group II (Baldridge). Consider a 20 year outlook. 2007 - CFP 2011 - PetaFlop machine delivered 2016 - PhDs 2016 - first pass for production applications 2021 - optimized production applications 2026 - end of 20 years; exaflops?.

amaya-mejia
Télécharger la présentation

Strategies for preparing for PetaScale computing

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. Strategies for preparing for PetaScale computing Group II (Baldridge)

  2. Consider a 20 year outlook • 2007 - CFP • 2011 - PetaFlop machine delivered • 2016 - PhDs • 2016 - first pass for production applications • 2021 - optimized production applications • 2026 - end of 20 years; exaflops?

  3. Reaching for PetaFlops Significant time investment for each 10-fold increase in parallelism Some apps are “Peta Ready” today Which will be ready tomorrow? We may not know which ones they are Peta Scale Flagship app Covers of science 100 TF Tera Scale (2006)

  4. Scope Focused vs. large scale efforts Different kinds of goals Level of funding and selection criteria Team User base Appropriateness for resources Scientific Merit and impact Significance Risk FocusedLarge scale

  5. Strategies for longer term preparation for potentially new PetaScale apps • Training programs, workshops, summer school - to create efficient codes. • Funds to be identified for parallel biological application development • Run time systems • Libraries • Biological Petaflop Computing Initiative, on the model of NMI • Specialized programs to capture the specific biology subfields for development

  6. Classification • Biological applications are difficult to classify • Different from classic PDEs • But inroads should be made to classification to enable communication and exchange of ideas

More Related