CUDA GPGPU Parallel Computing Newsletter - Issue 55

This week’s Spotlight is on John Humphrey of EM Photonics, a pioneer in GPU computing and developer of the CULA GPU-accelerated linear algebra library. Here’s a preview of our interview:

NVIDIA: John, what is your role at EM Photonics?

John: I oversee the technical work for most of our accelerated computing projects, the majority of which employ GPU technology. I have been working with the GPU for over six years, dating back to the pre-CUDA days.

NVIDIA: One of your current projects is an aircraft carrier landing modeling system for the US Navy. Tell us about it.

John: The Navy has a huge desire for CFD (computational fluid dynamics) modeling for a number of reasons. Foremost among these is to be confident of the safety of both aircraft and pilot. For each vessel and aircraft pair, there are tables describing the difficulty of landings and takeoffs based on a large number of variables, such as light conditions, wind speed and direction, and approach angle....

NVIDIA: What are the main advantages of working with CUDA?

John: CUDA allows for very direct expression of exactly how you want the GPU to perform a given unit of work. Ten years ago I was doing FPGA work, where the great promise was the automatic conversion of high level languages to hardware logic. Needless to say, the huge abstraction meant the result wasn't good. In the case of CUDA, we have a direct view into the hardware and can express our ideas in a way that the hardware executes directly and efficiently.

- Read the complete interview here

(Would you like to be in the CUDA Spotlight? Email cuda_week_in_review@nvidia.com)

Tesla M2090 Announced

back to the top

NVIDIA unveiled the Tesla M2090 GPU. Equipped with 512 CUDA parallel processing cores, it delivers 665 gigaflops of peak double-precision performance and 178 GB/sec memory bandwidth. Systems will be available at the end of May from OEMs and system builders, including Appro, ASUS, BULL, HP, IBM, NextIO, SGI, Supermicro and Tyan.
- See: http://www.nvidia.com/object/newsroom.html

New CUDA Research and Teaching Centers
NVIDIA named 35 new CUDA Research and Teaching Centers across 14 countries.
- CUDA Research Centers utilize GPU computing across multiple fields and are at the
   forefront of innovative scientific research.
- CUDA Teaching Centers integrate GPU computing into their mainstream computer
   programming curriculum.
- See: http://yhoo.it/lqNHhk

Wolfram Research’s European Tour - June 2011
Wolfram’s Computational Finance Tour will focus on new technologies for accelerating quantitative analytics. The events are free of charge, but registration is required.
- Dates: June 6, London; June 7, Paris; June 14, Zurich; June 15, Frankfurt
- Speakers: Dr. Andreas Binder, MathConsult GmbH; Dr. Michael Kelly, Wolfram;
   John Ashley, NVIDIA
- See: www.wolfram.com/events/computationalfinance2011

Abaqus v6.11 from Dassault Systemes
Dassault Systemes announced that the new Abaqus v6.11 release is GPU accelerated. The Abaqus product suite from SIMULIA (a Dassault Systemes brand) leverages Quadro and Tesla GPUs to run computer-aided engineering (CAE) simulations twice as fast as traditional processors.
- See: http://www.simulia.com/products/abaqus_fea

Platform Symphony v5.1
Platform Computing, provider of cluster, grid and cloud management software, announced availability of Platform Symphony, v5.1, which includes support for CUDA. Platform Symphony accelerates a wide variety of parallel applications.
- See: http://bit.ly/gUV0eo

NVIDIAN Wins Gold for GPU Ray Tracing Research
Kirill Garanzha of NVIDIA Moscow was awarded a gold medal by the Russian Academy of Sciences’ Keldysh Institute of Applied Mathematics. Kirill’s research focuses on raytracing of complex scenes on GPUs. His demo was created with a Boeing 777 dataset.
- See: http://www.youtube.com/watch?v=mxx9dyPO0js

Forbes.com on CUDA and GPGPU Momentum
Tom Groenfeldt of Forbes authored an article titled "Supercomputing and High Performance See Growing GPU Adoption." He writes: "GPUs are moving from video games into high performance computing in a big way since NVIDIA began focusing on software and revised its hardware designs to make them easier to use."
- See: http://blogs.forbes.com/tomgroenfeldt/

India’s Fastest Supercomputer
The Indian Space Research Organization (ISRO) has built India’s fastest supercomputer. The system uses 400 NVIDIA Tesla C2070 GPUs. Its theoretical peak performance is 220 teraflops while consuming only 150 kilowatts of power.
- See: http://www.isro.org/pressrelease/scripts/pressreleasein.aspx?May02_2011

Meetup Momentum Continues to Grow
New GPU Meetups have formed in Austin, Texas and Melbourne, Australia.
- www.meetup.com/HPC-GPU-Supercomputing-Group-of-Austin/
- www.meetup.com/Melbourne-GPU-Users/

NEW: Each week we highlight sessions from GTC 2010 and SC10. Here are our picks for this week:

back to the top

      Research Posters (GTC 10)
      From Ant Colony Optimization (by Octavian Nitica, Univ. of Delaware) to CUDA-Accelerated
      Face Recognition (by Jayadeep Vijayan, NeST Software)
      http://www.nvidia.com/object/research_summit_posters_2010.html

      Large Scale Distributed GPU Isosurfacing (SC10)
      Paul Navratil - Texas Advanced Computing Center
      http://www.nvidia.com/content/PDF/sc_2010/theater/Navratil_SC10.pdf

SpecTIR is hiring a software engineer based in Reno, Nevada to work with spectral scientists in areas of image processing, data acquisition and command/control interfaces. Requires strong C/C++/VB skills, understanding of Windows/.NET and excellent knowledge of CUDA and parallel programming. Contact: spectir (at) spectir.com. Subject line: Software Engineer.
- See: www.spectir.com

back to the top

- Meetup: Brisbane GPU Users
      May 19, 2011, 6:00 pm, Brisbane, Australia
      http://www.meetup.com/Brisbane-GPU-Users/

- Meetup: HPC & GPU Supercomputing Group of New York
      May 23, 2011, 6:00 pm, New York, New York
      http://www.meetup.com/HPC-GPU-Supercomputing-Group-of-
      New-York/events/16458112/

- Meetup: HPC & GPU Supercomputing Group of Denver/Boulder
      May 25, 2011, 7:00 pm, Boulder, Colorado
      http://www.meetup.com/HPC-GPU-Supercomputing-Group-of-
      Denver-Boulder/

- Meetup: HPC & GPU Supercomputing Group of Boston
      June 2, 2011, 6:00 pm, Boston, Mass.
      http://www.meetup.com/HPC-GPU-Supercomputing-Group-
      of-Boston/events/16953531/

- Meetup: HPC & GPU Supercomputing Group of Silicon Valley
      June 6, 2011, 6:15 pm, Mountain View, Calif.
      http://www.meetup.com/HPC-GPU-Supercomputing-Group-of-Silicon-Valley/

- Meetup: HPC & GPU Supercomputing Group of New Mexico
      June 8, 2011, 6:30 pm, Santa Fe, New Mexico
      http://www.meetup.com/HPC-GPU-Supercomputing-Group-of-New
      -Mexico/events/17220862/

back to the top

May 2011	back to the top

- GPU Computing Overview - Microsoft, Acceleware, NVIDIA

May 19, 2011, 9:00 am-5:00 pm, San Francisco, Calif.

https://msevents.microsoft.com/CUI/EventDetail.aspx?EventID=1032479960&Culture=en-US

- GTC Workshop Taiwan

May 19, 2011, Taipei, Taiwan

Note: Sanford Russell, NVIDIA, to present

http://weekly.ithome.com.tw/seminar/20110519nvidia/in1.html

- GPU Computing Overview - Microsoft, Acceleware, NVIDIA

May 20, 2011, 9:00 am-5:00 pm, Chicago, Ill.

https://msevents.microsoft.com/CUI/EventDetail.aspx?EventID=1032479956&Culture=en-US

- GPGPU Computing for Scientific Applications

May 23-27, 2011, Cordoba, Argentina

Held in FaMAF, National University of Cordoba

Note: Sessions by Robert Strzodka (MPI-Saarbrücken) and Ross Walker (SDSC, CUDA Fellow)

www.famaf.unc.edu.ar/grupos/GPGPU/EscuelaGPGPU2011

- NAFEMS World Congress: Promoting Adoption of HPC for Engineering Simulation

May 23-26, 2011, Boston, Mass.

Note: Session by Stan Posey, NVIDIA, on May 25

http://www.nafems.org/congress

- LS-DYNA 8th European Users Conference

May 23-24, 2011, Strasbourg, France

Note: Paper and talk by Stan Posey and Srinivas Kodiyalam, NVIDIA

http://www.lsdynaeuc.alyotech.fr/

- CUDA/OpenCL Training - Microsoft, Acceleware

May 24-27, 2011, Houston, Tex.

http://acceleware.com/houston-may24

- GPU Technology Summit - Israel

May 30, 2011, Tel Aviv, Israel

Co-sponsored by NVIDIA and Sagivtech

http://sagivtech.com/gpu-technology-summit.htm

- Computer Simulations on GPU - International Symposium

May 30-June 1, 2011, Mainz, Germany

Note: Axel Koehler, NVIDIA, to present

www.cond-mat.physik.uni-mainz.de/~weigel/GPU2011/home/

June 2011

- 25th International Conference on Supercomputing

June 1-4, 2011, Tucson, Ariz.

http://ics11.cs.arizona.edu/

- Intelligent Vehicles Conference - IEEE

June 5-9, 2011, Baden-Baden, Germany

Note: Session by Jeff Ota, NVIDIA, on Parallel Computing in Intelligent Vehicles

www.mrt.uni-karlsruhe.de/iv2011/

- Internat’l. Supercomputing Conference (ISC)

June 19-23, 2011, Hamburg, Germany, booth #630

Tutorial: HPC with CUDA (June 19): http://bit.ly/eEKn7B

Debate: GPUs — Fast Lane on Road to Better Science? (June 21): http://bit.ly/lvtDhz

http://www.supercomp.de/isc11/

- CUDA/OpenCL Training - Microsoft, Acceleware

June 20-23, 2011, Cambridge, Mass.

http://acceleware.com/boston-jun20

- Internat’l. Conference on Computer Systems and Applications

June 27-30, 2011, Sharm El-Sheikh, Egypt

http://aiccsa2011.hpcl.gwu.edu/

July - Sept. 2011

- 2011 World Congress on Engineering (WCE 2011)

July 6-8, 2011, London, England

http://www.iaeng.org/WCE2011/ICPDC2011.html

- Genetic and Evolutionary Computation Conference (GECCO)

July 12-16, 2011 Dublin, Ireland

www.sigevo.org/gecco-2011/index.html

- World Congress in C.S., Computer Engineering, Applied Computing (WORLDCOMP’11)

July 18-21, 2011, Las Vegas, Nevada

www.world-academy-of-science.org/worldcomp11/ws

- Application Accelerators in High Performance Computing (SAAHPC 2011)

(Call for papers: May 6)

July 19-21, 2011, Univ. of Tennessee, Knoxville, Tennessee

http://illinois.edu/lb/article/2100/45663

- Advanced Numerical Methods on GPUs

Mini-symposium at ENUMATH 2011

Sept. 5-9, Univ. of Leicester, Leicester, UK

http://www2.le.ac.uk/departments/mathematics/research/enumath2011/minisymposia

- 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

http://ppam.pl/tutorials/21

- Geospatial Summit

Sept. 13-14, 2011, Herndon, Virginia

http://cfp.foseinstitute.org/gis2011

- SPIE Conference on High-Performance Computing in Remote Sensing

Sept. 19-22, 2011, Prague, Czech Republic

http://spie.org/rs11

- SEG (Society of Exploration Geophysicists) Annual Meeting

Sept 18-23, 2011, San Antonio, Tex.

(Deadline for abstracts: April 6, 2011)

http://www.seg.org/events/annual-meeting/sanantonio2011/am2011techprogram

(To list an event, email: cuda_week_in_review@nvidia.com)

CUDA Downloads	back to the top
– Download CUDA: www.nvidia.com/getcuda – Download Parallel Nsight: www.nvidia.com/object/parallel-nsight.html – Download Parallel Nsight webinars: http://developer.nvidia.com/developer-webinars – Get developer guides and docs: http://developer.nvidia.com/object/gpucomputing.html

CUDA Registered Developer Program

– Sign up: www.nvidia.com/paralleldeveloper

CUDA GPUs

– List of CUDA-enabled GPUs: www.nvidia.com/object/cuda_gpus.html

CUDA Libraries Performance Report

– Download: http://bit.ly/ehR5az

CUDA on the Web

– See previous issues of CUDA: Week in Review: http://is.gd/cBXbg
– Follow CUDA & GPU Computing on Twitter: www.twitter.com/gpucomputing
– Network with other developers: www.gpucomputing.net
– Stayed tuned to GPGPU news and events: www.gpgpu.org
– Learn more about CUDA on CUDA Zone: www.nvidia.com/cuda
– Check out the NVIDIA Research page: www.nvidia.com/research

CUDA Recommended Reading

– Future of Computing Performance: http://bit.ly/hYqH2H
– Supercomputing for the Masses, Part 21: http://is.gd/Fj56gf
– CUDA books: http://www.nvidia.com/object/cuda_books.html

CUDA Recommended Viewing

– Third Pillar of Science: www.nvidia.com/object/race-for-better-science.html

– GTC 2010 presentations: www.nvidia.com/gtc

– SC10 presentations: www.nvidia.com/object/sc10_theater.html

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: cuda_week_in_review@nvidia.com

Click here to opt in specifically to CUDA: Week in Review.