Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
An Easy Pat...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
Disclaimer
...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
Background
...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
Exascale Re...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
Solution
 ...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
My Proposal...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
My Proposal...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
What About ...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
We May be F...
Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA
U N C L A S S I F I E D
Summary
 E...
Upcoming SlideShare
Loading in …5
×

An Easy Path to Exascale

355 views

Published on

Presented at the 2012 Salishan Conference on High-Speed Computing, "Random Access" session. Gleneden Beach, Oregon, 25 April 2012

Published in: Technology
  • Be the first to comment

  • Be the first to like this

An Easy Path to Exascale

  1. 1. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D An Easy Path to Exascale Scott Pakin Applied Computer Science Group Los Alamos National Laboratory 25 April 2012 Slide 1
  2. 2. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D Disclaimer  The opinions expressed herein definitely do not reflect the positions of Los Alamos National Laboratory, the National Nuclear Security Administration, or the United States Department of Energy Slide 2  Please don’t cut off my funding
  3. 3. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D Background  Many of us have been to lots of exascale meetings  If these meetings forbade the use of the words • energy • resilience • programmability • co-design  the meetings would be a lot shorter Slide 3  (but perhaps more fun)
  4. 4. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D Exascale Refrains  We don’t know how to reduce system power  We don’t have a good way to tolerate frequent faults  As component heterogeneity increases, programmability decreases Slide 4 Exascale is hard!
  5. 5. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D Solution  How can we deal with all of the problems of exascale? Slide 5
  6. 6. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D My Proposal Slide 6  What if instead of building an exascale system, we gave each of 1000 researchers his/her own, private, petascale system? exascale petascale
  7. 7. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D My Proposal  Power problem solved  Resiliency problem solved  Programmability problem solved  Increased productivity  Lower cost Slide 7  What if instead of building an exascale system, we gave each of 1000 researchers his/her own, private, petascale system?  Different locations → distribute load across the power grid  Fewer components → faults occur less frequently  Less complex hardware → can stick with MPI+X (where X=∅)  Dedicated systems → no long queues waiting for job to start  More aligned with vendor roadmaps → no cajoling needed
  8. 8. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D What About Applications that Require Exascale?  Approaching a singularity where we don’t have any applications  (except perhaps LINPACK) Slide 8 Numberofsuitableapps. Sequential Small SMP Large NUMA Distributed memory Heterogeneous architecture Exascale (power, resiliency) Zettascale (quantum decoherence?) Yottascale (inter-D-brane interactions on 11-dimensional M-theoretic superstrings?)
  9. 9. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D We May be Facing a Petascale Performance Asymptote  Parallelism • By Amdahl’s Law, if your application is less than 99.9% parallelized, you’ll see at best only petascale performance on an exascale system  Resilience • Performing the same work three times gives you 1/3 of the remaining performance  Power • To stay within the power budget, some components may have to be turned off or downclocked, lowering performance even further 1E+0 1E+2 1E+4 1E+6 1E+8 1E+10 1E+12 1E+14 1E+16 1E+3 1E+6 1E+9 1E+12 1E+15 1E+18 1E+21 1E+24 Theoretical peak performance Application performance Mega Giga Tera Peta Exa Zetta Yotta
  10. 10. Operated by Los Alamos National Security, LLC for the U.S. Department of Energy’s NNSA U N C L A S S I F I E D Summary  Exascale computing poses numerous challenges • Energy, resilience, programmability  Relatively few applications both require exascale and can be programmed to exploit complex exascale hardware  Many applications can take advantage of petascale • Limited by access to machines • (Long queue if you want the machine for yourself)  Proposition: Buy 1000 research teams their own petascale computer • Increases scientists’ productivity • Why put ourselves through the pain of an exascale before its time? • I’ll wait until I can borrow an exascale cell phone from my grandkids  It’s not like there isn’t still exciting research to be done at petascale Slide 10

×