CUDA: Week in Review
Friday, May 21, 2010, Issue #22 Newsletter Home
Welcome to this week’s issue of "CUDA: Week in Review," a weekly newsletter for the worldwide CUDA and GPU Computing community. Contact us at: Follow us on Twitter:

*Reminder: The GPU Technology Conference (GTC), Sept. 20-23, is accepting proposals for GPU-related sessions. The deadline is June 1. Submit your topic proposals today! Learn more: See this week’s press release:
CUDA and…Dance!
We recently came across a video on YouTube that listed "CUDA" as a keyword but is, well, different than videos usually associated with parallel computing! The video shows "Form Constant," a collaboration between dancer/choreographer Hope Goldman and visual artist/programmer Andrew Moffat. It was recently performed live as Goldman’s Master’s thesis show at the University of Illinois at Urbana Champaign. To create the real-time tracking and effects, the piece uses infrared lighting, a webcam and custom software running on an NVIDIA GPU. We wanted to learn more about this union of art and technology so we contacted the creators. Here is the note we received from Moffat:

    "Form Constant was inspired primarily by the fluid motions of dance, but also out of a strong desire to collaborate across disciplines and experiment with technologies like real-time motion tracking and general purpose GPU programming. To create the visuals, we tied together a CUDA-based fluid solver to some motion tracking code that captured the position and speed of the dancer from a camera. The GPU fluid simulation code was adapted from the CUDA SDK fluid demo code samples NVIDIA has made available online. Additions and changes to the code for this performance included adding collisions and velocity generation from the dancer. The online GPU Gems series was an enormously helpful resource in understanding the theory behind what we wished to achieve.... We have bigger ideas for future pieces, so we hope to keep developing and collaborating together to create more interesting performances. CUDA has been a blast to learn."

- See the video here: (if you only have a minute, watch from the 2:00 mark to the 3:00 mark)
New 3D Electromagnetic Simulation Software from Agilent
Agilent Technologies has announced Electromagnetic Professional (EMPro) 2010, a new release of its 3D electromagnetic (EM) modeling and simulation software. Used in the development of high-frequency and high-speed electronic devices, the new release features improvements in simulation speed and design efficiency, including built-in acceleration of "finite difference time domain" (FDTD) simulations utilizing CUDA C and Tesla GPU-based systems. EMPro was demonstrated earlier this year at CUDA Day in San Francisco by Amolak Badesha of Agilent, who noted that with CUDA, a week of simulation can now be accomplished in a few hours. For real-time 3D analysis, EMPro utilizes NVIDIA 3D Vision. See a video about EMPro here:
CUDA Development in the Cloud for Structured Financial Instruments
Reval, a leader in derivative risk management solutions, is using SciFinance from SciComp to accelerate development of its cloud-based Software-as-a-Service (SaaS) solution. Using SciFinance to automatically generate CUDA source code, Reval has achieved an immediate 50-300x speed improvement for Monte Carlo-based derivatives pricing. SciComp, a leader in automated code generation software, exhibited at the annual ICBI Global Derivatives & Risk Management Conference in Paris this week. Learn more:
New on CUDA Zone: Medical Image Registration
Extract: "A surgeon is performing a potentially life-saving pancreatectomy on a patient in early stages of pancreatic cancer. Two small incisions of no more than half an inch allow laparoscopic tools including a video camera and an ultrasound probe to be guided inside the abdominal cavity. A third, larger incision, is occupied by a hand-access device that facilitates the operation. The surgeon is able to locate the tumor in the ultrasound view with ease. This is largely possible due to a newly installed 3D navigation and visualization system that virtually renders the patient transparent." Authors: R. Shams, P. Sadeghi, R.A. Kennedy, R.I. Hartley, College of Engineering and Computer Science, Australian National University (ANU). Paper published in IEEE Signal Processing Magazine, March 2010. See:

CUDA Zone Submissions: Have a CUDA-related paper, research, or app? Show it on CUDA Zone:
Mercury Computer Systems is seeking an engineer for its algorithms optimization team to deliver optimized, high performance, computational solutions to market. Experience with CUDA or OpenCL and detailed understanding of GPU architectures is required, as well as experience optimizing signal processing algorithms. See:
Update from Oil & Gas Seminar in Houston
Over 70 Oil & Gas developers convened on May 12 in Houston at the GPU Computing seminar offered by Microsoft and NVIDIA. HeadWave, a seismic analysis software company, showed a CUDA C-powered application that processes seismic data in real time. Solutions provider Acceleware shared tips on using GPUs to turbocharge applications. Additionally, there was a demo and Q&A session about NVIDIA Parallel Nsight for Visual Studio. In June, Microsoft and NVIDIA will present a joint briefing on GPU Computing for the financial services community in New York. See:
CUDA Training Courses
- NEW: CUDA training from Acceleware
        July 26-30, Cambridge, Mass: (with Microsoft)
        August 2-6, New York City: (with Microsoft)
        Sept. 13-17, Calgary:
        See press release:
- CUDA training from SagivTech
        CUDA course: July 12-14, Ra’anana, Israel
        GPU/Image Processing course: Aug. 2-4, Ra’anana, Israel
GPU Computing Webinars (CUDA C, OpenCL, Parallel Nsight and more…)
See webinar schedule:
CUDA and Academia
Over 350 universities are teaching CUDA and GPU Computing courses.
- See the list:

– ISC ´10 GPU Computing Workshops
May 30, Hamburg, Germany

– European Association of Geoscientists & Engineers (EAGE) Conference
June 14-17, Barcelona

– Parallel Execution of Sequential Programs on Multi-Core Architectures
June 20, France

– GPGPU Briefing for Financial Services (Microsoft/NVIDIA)
June 21, NYC

– GPUs in Chemistry and Materials Science
June 28-30, Univ. of Pittsburgh

– Parallel Symbolic Computation 2010 (PASCO)
July 21-23, France

– Symposium on Chemical Computations on GPGPUs
Aug. 22-26, Boston

– Unconventional High Performance Computing 2010 (UCHPC 2010)
Aug. 31-Sept. 1, Italy

– GPU Technology Conference 2010
Sept. 20-23, San Jose, Calif. (now accepting proposals from industry and academia)

– Supercomputing 2010
Nov. 13-19, New Orleans, LA

(To list an event, email:

NVIDIA Parallel Nsight
Download the Parallel Nsight Beta:
CUDA Toolkit
Download CUDA Toolkit 3.0:
CUDA Documentation
Download developer guides and documentation:
CUDA Books
– Programming Massively Parallel Processors by D. Kirk, W. Hwu:
– See additional books here:
CUDA Articles
– Supercomputing for the Masses, Part 16 (by Rob Farber in Dr. Dobb’s):
– Supercomputing for the Masses, Part 15 (by Rob Farber in Dr. Dobb’s):
– Follow CUDA & GPU Computing on Twitter:
– Network with other developers:
– Stayed tuned to GPGPU news and events:
– Learn more about CUDA on CUDA Zone:
– CUDA on YouTube:
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.

See previous issues of CUDA: Week in Review:

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.

Copyright © 2010 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050.