CUDA: Week in Review
Fri., August 12, 2011, Issue #59 - Newsletter Home
Welcome to CUDA: Week in Review, an online news summary for the worldwide CUDA, GPU computing and parallel programming ecosystem.
Dr. Denis Bastieri, University of Padua
Forrester on JP Morgan, NVIDIA
New Video: Intro to CUDA
Upcoming CUDA Webinars
New CUDA Courses
CUDA in Academia
Sign up to be a CUDA Registered Developer
Follow @GPUComputing on Twitter
CUDA Spotlight
GPU-Accelerated Astronomy
This week’s Spotlight is on Denis Bastieri of the University of Padua, Italy, and co-founder of Mimesis HPC.

Dr. Bastieri leads the NASA Fermi Large Area Telescope (LAT) team for the National Institute of Nuclear Physics (INFN) in Padua. Here’s a preview of our interview:
NVIDIA: Denis, tell us about the Fermi Space Telescope.
Denis: The Fermi mission is part of NASA’s focus on the theme of "Structure and Evolution of the Universe." I specifically work with one of the two instruments aboard the Fermi spacecraft -- the Large Area Telescope (LAT), which observes gamma rays, the electromagnetic radiation with the highest energy.
NVIDIA: Which organizations are involved in the project?
Denis: Fermi is a joint project between NASA, the U.S. Department of Energy and academic and research institutions across France, Germany, Japan, Italy and Sweden. The spacecraft was built by General Dynamics. Institutions in the LAT collaboration are listed at
NVIDIA: What role does NVIDIA technology play?
Denis: Parallel computing is the only viable solution when dealing with many different aspects of astrophysics, and GPUs perform parallel computing at a tenth of the cost of conventional systems. Proof of the momentum behind GPUs can be seen in the exponentially growing number of astrophysics papers with "GPU" listed in the abstract!
NVIDIA: What are the benefits of working with CUDA?
Denis: We started looking at parallel computing on GPUs back during the time of Cg (C for Graphics). The subject looked tantalizing: different textures for positions and velocities and we could model the evolution of a particle population in an external field. The results were quite promising, but Cg was not ideal for astrophysical modeling and we were almost going to dismiss the project entirely.

Then, CUDA was released in late 2006. We found programming in CUDA to be quite straight forward for any good C programmer. Our students demonstrated that they could become independent within a semester.

And now, CUDA 4.0 is even better! We utilize the Thrust algorithms library. We leverage Unified Virtual Address (UVA) to extend GPU memory capabilities. The CURAND library replaced our own version of a random number generator. CUDA allows us to fully exploit the performance of our 16 GPU cluster.
NVIDIA: What’s next in the field of astronomy? What are you most excited about?
Denis: We are gaining more and more confidence in our modeling of the high-energy gamma ray emission of the universe. We understand by now what is the contribution from standard sources: pulsars, known galaxies, etc. But we are not able to explain all the data we collected! Something is missing and we have to understand what. Hints of a new population of gamma-ray emitters? The elusive Dark Matter starting to show up? Quoting Sherlock Holmes: "Whatever remains, however improbable, must be the truth!"

But this is just the "near" future: developing new, fast techniques to analyze data and find the improbable. The real future? We still have to shape it! We want to expand our GPU cluster, hire people, start new projects; in a word, we want to understand what it takes to build next-generation observatories. For a taste of what’s to come, keep an eye on the DARPA/NVIDIA exascale computing project!
  - Read the complete interview here

  (Would you like to be in the CUDA Spotlight? Email
CUDA Developer News
Forrester on JP Morgan Chase, NVIDIA back to the top
Analyst Rich Fichera of Forrester recently blogged about the use of Tesla GPUs in JP Morgan Chase’s Equity Derivatives Group. The bank’s hybrid GPU/CPU systems achieved a 40X acceleration in risk calculation times combined with a sizable cost savings. Fichera writes: "Implicit in the speedup of 40X, from multiple hours to several minutes, is the implication that these calculations can become part of a near real-time business-critical analysis process instead of an overnight or daily batch process."
- See:
New Video: Intro to CUDA
NVIDIA’s Cliff Woolley provides an introduction to CUDA in this new five minute video posted on GPUGenius:

Upcoming CUDA Webinars
- NVIDIA’s Justin Luitjens will discuss CUDA Libraries on Tues., Aug. 16, including a live Q&A: (CUDA Registered Developer Series)
- NVIDIA’s Nathan Bell will present "Rapid Problem Solving Using Thrust" on Wed., Sept. 14, 2011: (GTC Express Series)

New CUDA Courses
- SagivTech is offering a three-day CUDA course on Sept. 18-20 in Ramat Gan, Israel. The class will be conducted in a hands-on computer lab:
- Tech-X Corporation will present a three-day workshop on GPU computing with CUDA on Sept. 19-21 in Boulder, Colorado:

CUDA in Academia
- Congrats to Francisco Igual, Universitat Jaume I, Spain, on publication of his Ph.D. thesis on matrix computations and GPUs:
- Dr. Manuel Carcenac is teaching a course on CUDA at the European University of Lefke in North Cyprus:
- The Russian-German School on High Performance Computing will hold a series of courses on Sept. 19-30 in Novosibirsk:
- A one-month CUDA programming course is being taught by Ph.D. student Christopher Cooper at the Universidad Técnica Federico Santa María in Chile:
- Learn about NVIDIA’s Academic Partnership Program:
Replays of the Week
And the Winners of the NVART Competition Are..., by Will Park
NVIDIA Photorealistic Rendering Demo at SIGGRAPH, by Phil Miller
J.P. Morgan Achieves 40X Speed-up in Risk Computation, by George Millington
GPU Technology Conference: 1000 Strong in Tokyo, by Victoria Crimmins
An Inspiring Morning, by Hector Marinez
back to the top
Replays of the Week
NEW: Each week we highlight sessions from GTC 2010 and ISC 2011. Here are our picks for this week: back to the top
      GPU Cluster Computing: Accelerating Scientific Discovery (GTC 10)
      John Taylor - CSIRO

      Real-time Visualization of Medical Images (ISC 2011)
      Erik Steen - GE Ultrasound
NEW: Ion Torrent, a subsidiary of Life Technologies in South San Francisco, CA, is seeking an exceptional software engineer with extensive high performance computing experience, one who is highly creative, loves to code, and wants to build and ship software for a disruptive technology. Reference REQ# 5549. See: and
back to the top
If you are travelling to any of these locations, feel free to drop in. Visitors are welcome. Note: The Washington DC Meetup will feature a presentation by David Luebke of NVIDIA Research.

- United States
        Silicon Valley GPU Meetup – Aug. 15, 6:15 pm
        Wash. DC GPU Meetup – Aug. 18, 4:00 pm (inaugural meeting!)
        Austin GPU Meetup – Aug. 19, 6:00 pm
        New York GPU Meetup – Aug. 22, 6:00 pm
        South Florida GPU Meetup – Aug. 29, 6:30 pm (inaugural meeting!)
        Boston GPU Meetup – Sept. 1, 6:00 pm

- Australia
        Brisbane GPU Meetup – Aug. 18, 6:00 pm
        Sydney GPU Meetup – Sept. 15, 6:00 pm
CUDA Calendar
August 2011 back to the top
- Par Lab Boot Camp (Short Course on Parallel Computing)
Aug. 15-17, 2011, UC Berkeley, Berkeley, California

- Proven Algorithmic Techniques for Manycore Processors (Hands-On Course)
Aug. 15-19, 2011 (at multiple locations via videoconferencing)
Note: Sponsored by the Virtual School of Computational Science and Engineering (VSCSE)

- NEW: CUDA Libraries (Webinar)
Presented by Justin Luitjens, NVIDIA
Aug. 16, 2011

- NEW: In-Depth CUDA Training (Presented by Acceleware, with Microsoft)
Aug. 30-Sept. 2, 2011, Chicago, Illinois
September 2011

- Advanced Numerical Methods on GPUs
Mini-symposium at ENUMATH 2011
Sept. 5-9, 2011, Univ. of Leicester, Leicester, UK

- Parallel Processing and Applied Mathematics (PPAM 2011)
Sept. 11-14, 2011, Torun, Poland
Note: Scientific Computing with GPUs tutorial, incl. session by Tim Schroeder, NVIDIA

- Geospatial Summit
Sept. 13-14, 2011, Herndon, Virginia

- Rapid Problem Solving Using Thrust (Webinar)
Sept. 14, 2011
Presented by Nathan Bell, NVIDIA
Note: Thrust is a library that enables programmers to develop high-performance applications on CUDA with minimal effort.

- NEW: CUDA Course (Presented by SagivTech)
Sept. 18-20, 2011, Ramat Gan, Israel
Hands-on sessions and optimization techniques.

- NEW: CUDA Course (Presented by Tech-X)
Sept. 19-21, Boulder, Colorado

- NEW: Russian-German HPC School
Sept. 19-30, Novosibirsk

- SPIE Conference on High-Performance Computing in Remote Sensing
Sept. 19-22, 2011, Prague, Czech Republic

- SEG (Society of Exploration Geophysicists) Annual Meeting
Sept. 18-23, 2011, San Antonio, Tex.

(To list an event, email:

CUDA Resources
Downloads back to the top
– CUDA 4.0:
– Parallel Nsight:
– Parallel Nsight:
CUDA Registered Developer Program
– Sign up:
– List of CUDA-enabled GPUs:
CUDA on the Web
– See previous issues of CUDA: Week in Review:
– Follow CUDA & GPU Computing on Twitter:
– Network with other developers:
– Stayed tuned to GPGPU news and events:
– Learn more about CUDA on CUDA Zone:
– Check out the NVIDIA Research page:
CUDA Recommended Reading
– Future of Computing Performance:
– Supercomputing for the Masses, Part 21:
– CUDA books:
CUDA Recommended Viewing
– The Third Pillar of Science:
– GTC 2010 presentations:
– SC10 presentations:
About CUDA
CUDA is NVIDIA’s parallel computing hardware architecture. NVIDIA provides a complete toolkit for programming on the CUDA architecture, supporting standard computing languages such as C, C++ and Fortran as well as APIs such as OpenCL and DirectCompute. Send comments and suggestions to:
You are receiving this email because you have previously expressed interest in NVIDIA products and technologies. Click here to opt in specifically to CUDA: Week in Review. NVIDIA

Copyright © 2011 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050.