Computing Sciences masthead Berkeley Lab Computing Sciences Berkeley Lab logo

Accelerator-based Computing and Manycore
Manycore and Accelerator-based Computing for Physics and Astronomy Applications

SLAC National Accelerator Laboratory/ Lawrence Berkeley National Laboratory, Berkeley CA, USA
November 30 – December 2, 2009

SLAC, NERSC, LBNL and UC Berkeley hosted an international workshop on the role of emerging many-core architectures in science and technology. The focus of the workshop is to usher experts and enthusiasts from disparate backgrounds in academia and industry to introduce, explore and discuss the scope and challenges of harnessing the full potential of these novel architectures for high performance computing specially in Physics and Astronomy applications. The developed solutions will have broader impact across science and technology disciplines such as healthcare, energy, aerospace etc. The emerging new techniques open a route for future generations of hardware and software using silicon and electrical power much more efficiently, a necessity on the path to Exaflop/s.

Emerging many-core architectures – Graphics Processing Units (GPUs), Cell, many-core CPUs – offer unprecedented potential for energy efficient high performance computing (HPC) in science and technology. Limited early adoption of such architectures by a broad range of compute and data intensive applications has distinctly demonstrated unmatched gains in acceleration and power consumptions. This workshop strives to set the stage for academic and industry leaders to enable partnerships for growth of research and innovation in the broader community. Early adopting core science teams from Asia, Europe and America have an opportunity to get together to coordinate next steps and establish a regular transcontinental forum in the next years.

The very first confluence for such a group aims to achieve:

· A large footprint of international collaborations
· Educational and training prospects for future researchers, educators and students
· Leadership role for participating institutions and facilities in the cutting-edge technologies
· And Academia-industry partnerships with entrepreneurial opportunities

Agenda

Monday November 30, 2009
8:30–9:00 am Registration / Refreshments
9:00–9:30 am Tom Abel
Hemant Shukla
Introduction
Chair- John Shalf
9:30–10:30 am Kathy Yelick Keynote (LBNL)
10:00–11:00 am Break/ Refreshments served
11:00–11:30 am Alain Bonissent Accelerated image reconstruction on a cluster of two AMD GPUs in X-ray CT with nonuniform detector geometry.
11:30-12:00 pm Keigo Nitadori High Order N-body integrators on GPU
12:00 – 2:00 pm Lunch
Chair- Hemant Shukla
2:30–3:00 pm Joel Primack Supercomputer Simulations, Using GPUs for Visualization
3:00–3:30 pm Dan Werthimer Peta-Scale Computing Challenges in SETI and Radio Telescope Arrays
3:30–4:00 pm John Shalf Hardware and Software Scaling Challenges for Future Systems
4:00–4:30 pm Break/ Refreshments
4:30–5:00 pm Tom Abel KIPAC
5:00–5:30 pm Lyne Jones LSST
6:30 pm Dinner: Chef Chu’s 1067 N San Antonio Road Los Altos, CA 94022-1300

Tuesday December 1, 2009
8:30–9:15 am Refreshments
Chair- Horst Simon
9:15–10:00 am Rainer Spurzem Keynote (CAS) Green Supercomputing
10:00–10:30 am Mike Clark Murchison Wide-field Array (MWA)
10:30–11:00 am Break/ Refreshments served
11:00–11:30 am Don Gavel
Marc Reinig
Challenges in real-time control of adaptive optics systems for high resolution ground based astronomy
11:30-12:00 pm Wang Xiaowei Lattice Boltzmann simulation of porous media on GPU-based parallel systems
12:00 – 2:00 pm Lunch
Chair- Tom Abel
2:30–3:00 pm Chen Feiguo Molecular dynamics simulation of multi-phase flow on micro-scales using CUDA
3:00–3:30 pm Andreas Kugel Neighbour list generation with GPUs for SPH simulations
3:30–4:00 pm His-Yu Schive GAMER: a GPU-Accelerated Adaptive Mesh Refinement Code for Astrophysics
4:00–4:30 pm Break/ Refreshments
4:30 pm
Collaboration Meeting

Wednesday December 2, 2009
8:30–9:00 am Refreshments
Chair- Rainer Spurzem
9:00–10:00 am Billy Dally Keynote (Industry)
10:00–10:30 am Ge Wei Multi-scale discrete simulation on multi-scale HPC system (an overview of the software and hardware)
10:30–11:00 am Break/ Refreshments served
11:00–11:30 am Jun Makino GRAPE-DR and next-generation GRAPE
11:30 – 1:30 pm Lunch
Chair- Masoud Nikravesh
1:30–2:00 pm Khronos OpenCL Overview
2:00–2:30 pm Udeepta Bordoloi Heterogeneous computing on AMD using OpenCL TM
2:30–3:00 pm Bryan Catanzaro SEJITS: Selective Embedded Just-in-Time Specialization for Productive Programming of GPU and Manycore systems
3:00–3:30 pm Break/ Refreshments
3:30–4:00 pm Piyush Mehrotra NASA Ames
4:00–4:30 pm Horst Simon Future and Conclusion


Cick Here for list of Participants

ORGANIZERS
Hemant Shukla
Tom Abel
John Shalf

ADVISORS
Horst Simon
Rainer Spurzem
Katherine Yelick
Masoud Nikravesh
James Siegrist