CUDA Week in Review Newsletter Homepage
Tues., Aug. 14, 2012, Issue #77 Newsletter Home 


A news summary for the worldwide CUDA, GPGPU and parallel programming community.


NVIDIA salutes NASA on Curiosity’s historic mission. Recommended reading:
Our blog on Curiosity and 3D Vision | Gizmodo interview with Brian Cooper | 3D images of the Mars surface


Odeint is a modern C++ library for numerically solving Ordinary Differential Equations (ODEs). It is developed in a generic way using template metaprogramming, which leads to extraordinarily high flexibility at top performance. Odeint can solve ODEs on your CUDA GPU by using the Thrust Library. Simply use thrust::device_vector as state type and thrust_algebra/thrust_operations when defining the stepper and ODEINT runs all computations on the GPU:
typedef thrust::device_vector state_type;
runge_kutta4< state_type, double, state_type, double, thrust_algebra, thrust_operations > rk4;
For details, see the chapter on CUDA and Thrust in the ODEINT documentation.


GPUs for Green Urban Planning
This week’s Spotlight is on Pete Willemsen of the University of Minnesota Duluth.

In our interview with Pete, you’ll learn how GPU computing is helping to provide new tools to urban planners and architects, with the goal of improving sustainability and health in cities around the world.
Pete Willemsen


Save the Date: GTC 2013
The GPU Technology Conference will take place March 18-21, 2013 in San Jose, Calif. Mark your calendars and stay tuned for info on papers, posters and registration. Sign up for GTC news at

Kepler-Powered Maximus
The next generation of NVIDIA Maximus technology for workstations - based on the Kepler architecture - debuted last week at SIGGRAPH. Design News writes: “With the latest Maximus release, compute work is assigned to run on the new NVIDIA Tesla K20 GPU architecture, while the new NVIDIA Quadro K5000 GPU takes care of graphics functions. It is the Maximus technology that automatically assigns visualization, simulation and rendering work to the appropriate Kepler-based processor.” See:

New Release from PGI
Version 12.6 is the first PGI compiler release with comprehensive support for the OpenACC 1.0 spec, including the acc cache construct and the entire OpenACC API library. For a features list, see:

Rootbeer + Java + GPGPU
Bit-tech reports that Phil Pratt-Szeliga, an instructor at Syracuse University, has "released the source code for the Rootbeer compiler - a tool he and colleagues Jim Fawcett and Roy Welch claim makes it significantly easier to write code for execution on a GPU." Rootbeer allows programmers to access the power of the GPU directly within Java. See:

Genomics Acceleration with GPUs + OpenACC
Researchers at Shanghai Jia Tong University are using GPUs to accelerate the DNADist genomics application, used in development of treatments for genetic conditions such as cystic fibrosis. Using the CAPS enterprise OpenACC compiler, researchers accelerated the application by 16x by adding four simple hints - known as “directives”- to the application code. See:


Update from NVIDIA India
The CUDA ecosystem is growing in India! New CUDA Teaching Centers include:
   • Rajarshi Shahu College of Engineering, Pune
   • Amrita University, Kollam
   • Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded

New Academic Partners include:
   • Prof. Manisha Nene, Defense Institute of Advanced Technology
   • Prof. Nagendra Gajjar, Nirma University
   • Prof. Swapna Banerjee, IIT Kharagpur

In addition, a GPU Meetup group was launched earlier this year and has over 220 members. To join, visit


Stanford University’s Simbios team is seeking a software engineer with expertise in molecular dynamics simulations and high performance computing to support and extend the OpenMM and Folding@Home projects. To learn more, visit


In this new section, we’ll highlight graduate and undergraduate theses focused on GPU computing topics. Congrats to Samir Patel, Harvard University, on his B.S thesis titled "aeroCuda: The GPU-Optimized Immersed Solid Code." Advisor: Dr. Cris Cecka. Date: June 2012. Read it here:


back to the top
Stay up to date by reading the NVIDIA blog:
NASA Team Drives Mars Rover Like 3D Game, by Ken Brown
Inner Geek, by Andrea Hutchison
BioDigital Navigates Human Anatomy, by Gary Rainville
Exploring the Science of Ice Cream, by Andy Walsh
GPU Computing Show in Brazil, by Arnaldo Tavares
GPUs Put London in Palm of Your Hand, by Michael Steele
GPU Computing Developer Forum Barnstorms Brazil, by Leo De Biase
New Top 500 List: 4X More GPUs, by Sumit Gupta
GPUs for Financial Markets, by Pierre Spatz


back to the top
LinkedIn groups offer a great way to liaise with fellow GPU computing users:
High Performance & Super Computing: 13,000+ members
High Performance Computing (HPC): 8000+ members
Multicore & Parallel Computing: 5000+ members
GPGPU Users: 3000+ members
CUDA Developers: 2000+ members
CUDA Users Group: 1500+ members


back to the top
Find a GPU Meetup in your location, or start one up. Upcoming meetings include:
Silicon Valley GPU Meetup, Aug. 20 (featuring NVIDIA Software’s Stephen Jones)
Brisbane, Australia GPU Meetup, Aug. 23
Sydney, Australia GPU Meetup, Aug. 28
Paris GPU Meetup, Sept. 5

(Want to start a GPU Meetup? Contact


back to the top


- Algorithmic Techniques Summer School (VSCSE)
Aug. 13-17, 2012 (online)

- OpenACC Directives with PGI Accelerator Compilers, Part 2 (Webinar)
Aug. 21, 2012, 9:00 a.m. PT

- Introducing CUDA 5 (Webinar)
Aug. 22, 2012, 10:00 a.m. PT

- INT Summer School on Lattice QCD for Nuclear Physics (Webcast)
Aug. 23-24, 2012
Dr. Mike Clark from NVIDIA will present “Intro to GPU Computing” and “Intro to QUDA.” A live webcast will be open to the public. To register, contact Professor Huey-Wen Lin

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

- Nsight Eclipse Edition: High Productivity IDE (Webinar)
Aug. 28, 2012, 10:00 a.m. PT

- Latin America Conference on HPC (CLCAR)
Aug. 27-31, 2012, Panama

- Introducing CUDA 5 (Webinar)
Aug. 29, 2012, 9:00 a.m. PT


- GPU Object Linking: Usage and Benefits (Webinar)
Sept. 5, 2012, 10:00 a.m. PT

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

- Computational Genomics… Using OpenACC (Webinar)
Sept. 6, 2012, 9:00 a.m. PT

- Running Risk on GPUs (Webinar)
Sept. 19, 2012, 9:00 am PT

- 4-Day CUDA Training Course (Acceleware)
Oct. 2-5, 2012, San Jose, Calif.

(To list an event, email:


Cloud-Hosted GPUs

– Try your applications on cloud-hosted GPUs. Sign up today at


– Nsight:
– CARMA (pre-register):

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® 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
Copyright © 2012 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050.