CUDA Week in Review Newsletter Homepage
Fri., June 8, 2012, Issue #76
Welcome to CUDA: WEEK IN REVIEW, a news summary for the worldwide CUDA, GPGPU and parallel programming community.


CHOLMOD, a publicly-available sparse direct solver developed by Dr. Timothy Davis of the University of Florida, is now GPU-accelerated. Sparse direct solvers are at the heart of many scientific and manufacturing programs. CHOLMOD is a component of SuiteSparse, a suite of C, Fortran and MATLAB functions for manipulating sparse matrices. SuiteSparse is used for a variety of applications (for example, in Google’s Ceres Solver for the positioning of Google Street View photos.)

- Download CHOLMOD here:


A flurry of GPU computing events are happening across Europe over the next few months, from Hamburg, Amsterdam and Barcelona to Rome, Paris and Madrid. Here are several examples (additional events listed in the CUDA Calendar):

Hamburg: ISC 2012, June 17-21
NVIDIA will host talks and tutorials on how Kepler, OpenACC, and CUDA on ARM can accelerate applications.

   -  June 17: ISC-sponsored tutorial on Programming Accelerators with OpenACC & CUDA C/Fortran
   -  June 19: A full day of technology talks about the Kepler architecture and HPC
      application development platforms
      To register, see:

Amsterdam: GPGPU Day, June 28
SARA and StreamComputing are sponsoring a day focused on GPGPU and parallel programming. Presentations include:

   -  Tour of LLVM, by Paul Keir, CodePlay
   -  GPGPU in Radio Astronomy, by Rob van Nieuwpoort, VU Amsterdam
   -  Sparse Octrees and GPGPU, by Evghenii Gaburov, SARA

Barcelona: PUMPS 2012, July 2-6
The PUMPS Summer School offers students the opportunity to improve their parallel programming skills. PUMPS is organized by the Barcelona Supercomputing Center, University of Illinois at Urbana-Champaign, Universitat Politecnica de Catalunya and HiPEAC Network of Excellence. Lecturers include:

   -  Wen-mei Hwu, University of Illinois at Urbana-Champaign
   -  David Kirk, NVIDIA Fellow, NVIDIA
   -  Manuel Ujaldon, CUDA Fellow, University of Malaga
   -  Isaac Gelado, Rosa Badia, Xavier Martorell, Jesus Labarta, and Nacho Navarro (BSC and UPC)


The GROMACS development team is looking for exceptionally talented programmers to develop highly parallel GPU code for the largest scientific clusters in the world, as well as an overall project manager. GROMACS is a popular molecular dynamics program, primarily designed for biochemical molecules like proteins, lipids and nucleic acids with complex bonded interactions. Since GROMACS is also extremely fast at calculating nonbonded interactions (that usually dominate simulations), many groups are also using it for research on non-biological systems, e.g. polymers. See


Expressive Algorithmic Programming with Thrust, by Mark Harris (Note: Subscribe to the Parallel For all blog here:


Open Genomics Engine A New Weapon in Battle Against Cancer, by Will Ramey
OpenACC Compiler: Fast, Portable, by Denis Gerrer, CAPS
Take Adobe Workflows to the Max, by David Helmley, Adobe
GPU Computing Experts Join CUDA Fellow Ranks, by Chandra Cheij


June 11 - GPU Meetup, Rome (NEW)
June 18 - GPU Meetup, Silicon Valley
June 19 - GPU Meetup, Paris
June 20 - GPU Meetup, New Mexico
June 25 - GPU Meetup, New York
June 27 - GPU Meetup, Boston
June 28 - GPU Meetup, Brisbane, Australia
June 28 - GPU Meetup, Sydney, Australia
June 30 - GPU Meetup, India

(Want to start a GPU Meetup? Contact


back to the top

International Mathematica Symposium (University College, London)
June 11-13, 2012, London, UK

IWOMP (International Workshop on OpenMP)
June 11-13, 2012, Rome, Italy

CUDA and OpenACC Training at CASPUR
June 12-13, 2012, Rome, Italy
Contact: massimo.bernaschi (at) gmail (dot) com

ISC '12
June 17-21, 2012, Hamburg, Germany

Aquila (NVIDIA Webinar)
June 20, 2012, 9:00 am pacific
Presenter: Martin Peniak
Note: Aquila is an open-source toolkit for cognitive and neuro-robotics

Micromethods in Protein Chemistry
June 25-27, 2012, Ruhr-University Bochum, Germany

International Congress of Quantum Chemistry
June 25-30, 2012, Boulder, Colorado

NCT-500 PGI Accelerator with OpenACC Directives
June 27-28, 2012, Houston, Texas (MicroTek Training)

June 28, 2012, Amsterdam
Note: Hosted by StreamComputing and SARA

CUDA Tutorial at IEEE HPCS

July 2, 2012, Madrid, Spain

Parallel Computing Summer School (CINECA)
July 2-13, 2012 (in Italian), Bologna, Italy

PUMPS Summer School (BSC)
July 2-6, 2012, Barcelona, Spain

CUDA Tutorial at IEEE ISPA
July 10, 2012, Madrid, Spain

4-Day CUDA Training Course (Acceleware)
July 17-20, 2012, Irvine, California

Computational Chemistry (Gordon Research Conferences)
July 22-27, 2012, West Dover, Vermont

Summer School of Advanced Computing (CASPUR)
Aug. 27-Sept. 7, 2012, Rome, Italy

Parallel Computing Summer School (CINECA)
Sept. 3-14, 2012 (in English), Bologna, Italy

4-Day CUDA Training Course (Acceleware)
Sept. 18-21, 2012, Washington, DC

(To list an event, email:


back to the top

Special Offers

Computational chemistry researchers: Take a free test drive on a remotely-hosted GPU cluster
For a limited time, purchase an OpenACC compiler from CAPS Enterprise for $199


– Nsight, Eclipse Edition:
– Nsight, Visual Studio Edition:
– CARMA (pre-register):


– List of CUDA-enabled GPUs:

CUDA Registered Developer Program

– Sign up:

CUDA on the Web

– Learn more about CUDA on CUDA Zone:
– See previous issues of CUDA: Week in Review:
– Follow CUDA & GPU Computing on Twitter:
– Network with other developers:
– Stay tuned to GPGPU news and events:
– Check out the NVIDIA Research page:

CUDA Recommended Reading

– CUDA books:


CUDA® is a parallel computing platform and programming model invented by NVIDIA. It enables dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU). NVIDIA provides a complete toolkit for programming on the CUDA architecture, supporting standard computing languages such as C, C++ and Fortran. Send comments and suggestions on the newsletter 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 - World Leader in Visual Computing Technologies