Archiwum dla Styczeń, 2011

Tygodniowy newsletter “CUDA: Week in Review.” – 25.01.2011

Napisany przez e-on w Aktualności dnia 25.01.2011

CUDA: Week in Review

Tues., Jan. 25, 2011, Issue #46
WELCOME
Welcome to CUDA: Week in Review, an online news summary for the worldwide CUDA, GPU computing and parallel programming ecosystem.
CONTENTS
CUDA SPOTLIGHT
Simulating Waves in Denmark
This week’s CUDA Spotlight is on Allan P. Engsig-Karup, assistant professor in scientific computing at the Technical University of Denmark (DTU). Allan’s research includes the OceanWave3D model, which he presented at GTC 2010 in San Jose, California. Here are highlights of our interview with him:

NVIDIA: Allan, tell us about your work at DTU.
Allan: I am responsible for teaching and research related to scientific computing. I teach on the order of 200 BSc, MSc and PhD students every year.

My collaborative research is focused on GPUs for applications requiring efficient PDE (partial differential equation) solvers and optimization algorithms, as well as development of performance profiling tools.

A project I am currently involved in, with my colleague Associate Professor Harry Bingham, is the continued development of a tool referred to as OceanWave3D – for simulation of nonlinear and dispersive free surface flow in marine settings.
NVIDIA: How can this research be used in the real world?
Allan: Coastal and ocean engineers need to estimate the flow kinematics and design loads on human-made structures in the ocean, such as ships, oil platforms, offshore windmills and energy devices. [Ed. note: Windmills produce approx. 20% of Denmark's energy requirements].
NVIDIA: What kind of results have you achieved with CUDA?
Allan: Recently, working with one of my MSc students, we achieved impressive scalability results for the parallel GPU implementation of OceanWave3D. These results were achieved by careful redesign of algorithms and implementation on the hardware (using CUDA C), leading to a conservative estimate of at least a 42X speedup compared to an optimized sequential code.

- Read the full interview with Allan: http://blogs.nvidia.com.

(Would you like to be featured in the CUDA Spotlight? Email us at
cuda_week_in_review@nvidia.com)
CUDA DEVELOPER NEWS
CUDA Libraries Performance Report Now Available
This new report covers all the performance improvements in the latest CUDA Toolkit 3.2 release, and compares CUDA parallel math library performance vs. commonly used CPU libraries. Learn about the performance advantages of using the CUDA parallel math libraries for FFT, BLAS, sparse matrix operations and random number generation.
- See: http://bit.ly/ehR5az

ANSYS Acceleration on Tesla GPUs
ANSYS’ engineering simulation software predicts how product designs will behave and how manufacturing processes will operate in real-world environments. ANSYS is working closely with NVIDIA to develop GPU-accelerated solvers and algorithms.
- To learn more, see: http://www.nvidia.com/object/tesla-ansys-accelerations.html

Note: A seminar on “Performance Benefits of NVIDIA GPUs for ANSYS Mechanical” will be held Thursday, February 17, at noon pacific time: https://www2.gotomeeting.com/register/290222514
REPLAYS OF THE WEEK
NEW: Each week we highlight a session from GTC 2010 and SC10. Here are our picks for this week:

GPU-Accelerated Internet Technologies & Trends (GTC 2010)
Chris Pedersen – NVIDIA (video – 45 mins.)
http://nvidia.fullviewmedia.com/gtc2010/0921-a5-2019.html

First Look at the World’s Fastest Supercomputer (SC10)
Andy Keane – NVIDIA (pdf)
http://www.nvidia.com/content/PDF/sc_2010/theater/Keane_SC10.pdf
CUDA JOBS
Microsoft is seeking a Software Development Engineer to help drive the parallel revolution in personal and technical computing. Requirements: 6+ years of software development in C++/C# with experience in commercial product release cycles. Experience with DirectX, data parallelism, CUDA and/or OpenCL is a plus. Location: Redmond, WA; Division: Server & Tools Business.
- See: http://is.gd/A1ox68

Note: In future issues of CUDA: Week in Review, we will highlight people who are seeking careers, internships, academic positions and contract work related to CUDA and parallel programming. To be included, email: cuda_week_in_review@nvidia.com.
CUDA CALENDAR
January 2011

– Optimizing Financial Modeling/Chicago – Wolfram Research

Jan. 25, 2011, Chicago (Featured Speaker: Dr. Michael Kelly)
www.wolfram.com/events/chicago2011/

– Optimizing Financial Modeling/New York – Wolfram Research

Jan. 27, 2011, New York (Featured Speaker: Dr. Michael Kelly)
http://www.wolfram.com/events/newyork2011/

February – July 2011

– Symposium on Principles and Practice of Parallel Programming – ACM

February 12-16, 2011, San Antonio, TX
http://www.ppopp.org/

– NEW: Performance Benefits of NVIDIA GPUs for ANSYS Mechanical –
Seminar/Webinar

February 17, 2011, noon-1:00 pm pacific
Hosted at Ozen Engineering, 1210 E. Arques Ave #207, Sunnyvale, CA 94085
Note: Pizza will be served
https://www2.gotomeeting.com/register/290222514

– GPU Computing Session, German Physical Society Conference

March 13-18, 2011, Dresden, Germany
http://dresden11.dpg-tagungen.de/index.html

– ASIM Workshop 2011 – ASIM and Technische Universitat Munchen (TUM)

March 14-16, 2011, Leibniz, Germany
Theme: Trends in Computational Science & Engineering: Foundations of Modeling & Simulation
http://www5.in.tum.de/asim2011.html

– Computational Intelligence on Consumer Games and Graphics Hardware (CIGPU)

July 12-16, 2011, Dublin, Ireland (GECCO Workshop)
http://www.sigevo.org/gecco-2011/workshops.html#cigpu

– Application Accelerators in High Performance Computing (SAAHPC 2011)

Call for papers: May 6, 2011
Event: July 19-21, 2011, Univ. of Tennessee, Knoxville, Tennessee
http://illinois.edu/lb/article/2100/45663

– Workshop on High Performance Computational Biology – IEEE

May 16, 2011, Anchorage, Alaska
Note: Held with International Parallel & Distributed Processing Symposium
http://www.hicomb.org/

– Intelligent Vehicles Conference – IEEE

June 5-9, 2011, Baden-Baden, Germany
www.mrt.uni-karlsruhe.de/iv2011/

– Internat’l. Supercomputing Conference

June 19-23, 2011, Hamburg, Germany
http://www.supercomp.de/isc11/Take-Part/Call-for-Papers

– Internat’l. Conference on Computer Systems and Applications

June 27-30, 2011, Sharm El-Sheikh, Egypt
http://aiccsa2011.hpcl.gwu.edu/

– NEW: Genetic and Evolutionary Computation Conference (GECCO)

July 12-16, 2011 Dublin, Ireland
http://www.sigevo.org/gecco-2011/index.html/

Ongoing

– CUDA Training from EMPhotonics: www.emphotonics.com/services/cuda-training
– CUDA Training from Acceleware: http://www.acceleware.com/events
– CUDA Certification: www.nvidia.com/certification
– GPU Computing Webinars: www.nvidia.com/webinars

(To list an event, email: cuda_week_in_review@nvidia.com)
CUDA RESOURCES
GPU Technology Conference
– Presentations from GTC 2010: www.nvidia.com/gtc
SC10 Conference
– Presentations from SC10: www.nvidia.com/object/sc10_theater.html
CUDA GPUs
– List of CUDA-enabled GPUs: www.nvidia.com/object/cuda_gpus.html
Video Recommendation
– The Third Pillar of Science: www.nvidia.com/object/race-for-better-science.html
CUDA GPU Computing Forum
– Link to forum: http://forums.nvidia.com/index.php?showforum=62
CUDA and Parallel Nsight Overview
– Blog post and video: http://is.gd/gbGen
CUDA Downloads
– Download CUDA Toolkit 3.2: http://bit.ly/aKCENp
– Download OpenCL v1.1 pre-release drivers and SDK code samples (Log in or
apply for an account)
– Get developer guides and docs: http://developer.nvidia.com/object/gpucomputing.html
CUDA and Academia
– Learn more at http://research.nvidia.com/
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
CUDA Recommended Reading
– Read Kudos for CUDA: www.hpcwire.com/features/Kudos-for-CUDA-97889444.html
– Read Supercomputing for the Masses, Part 20: http://is.gd/f9o6o
– Read CUDA books: http://www.nvidia.com/object/cuda_books.html
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.

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

Brak komentarzy

Tygodniowy newsletter “CUDA: Week in Review.” – 14.01.2011

Napisany przez e-on w Aktualności dnia 14.01.2011

CUDA: Week in Review

Tues., Jan. 14, 2011, Issue #45
WELCOME
Happy New Year! Welcome to CUDA: Week in Review, an online news summary for the worldwide CUDA and GPU computing ecosystem.
CONTENTS
CUDA SPOTLIGHT
Molecular Research + GPUs + Crowd Funding
This week’s CUDA spotlight is on Joshua Adelman, a University of Pittsburgh researcher who studies biological phenomena in order to better understand diseases such as diabetes and epilepsy. Joshua’s project is funded with the help of FundScience, which enables the public to support pilot research projects.

NVIDIA: Joshua, tell us about your research.
Joshua: I am interested in understanding how proteins that sit in the cell membrane selectively transport small molecules across the membrane. Specifically, I study two transporters – one removes a neurotransmitter from the synapse and is critical in proper nervous system function; the other is responsible for absorption of sugar in the intestines and kidneys. Both are potential targets for treating a number of diseases including ALS, epilepsy and type 2 diabetes.
NVIDIA: What kind of results are you achieving [with GPU computing]?
Joshua: For simple representations of the protein, we typically get a several hundred-fold increase in simulation throughput compared to a CPU implementation running on a single core. In this regard, GPUs running CUDA have been an enabling technology. They have allowed us to perform calculations that would have been completely unfeasible just a couple of years ago.
NVIDIA: How can people learn more about your research?
Joshua: My FundScience project page can be found at http://apply.fundscience.org/project.59.html and information about our lab’s efforts can be found at http://mgrabe1.bio.pitt.edu.

- Read the full interview with Joshua here: http://blogs.nvidia.com.

(Would you like to be featured in the CUDA Spotlight? Email us at
cuda_week_in_review@nvidia.com)
CUDA DEVELOPER EVENTS
Microsoft is offering two one-hour sessions on GPU supercomputing and finance on Monday, Jan. 24 in Manhattan. The sessions are “Supercomputing with Excel” and “GPUs for Finance.” The speaker is Andrew Sheppard, a financial consultant with extensive experience in quantitative financial analysis and trading-desk software development. On the evening of Jan. 24, Microsoft will host a meetup for people interested in HPC and GPU computing across all industries. (See CUDA Calendar for details)

Wolfram Research is hosting seminars on “Optimizing Financial Modeling,” featuring Dr. Michael Kelly and other industry experts. The seminars will be held in Chicago on Tuesday, Jan. 25 and in Manhattan on Thursday, Jan. 27. Dr. Kelly was formerly a quant with firms in the Chicago Board of Trade and a senior lecturer at the University of Western Sydney. (See CUDA Calendar for details)
CUDA DEVELOPER NEWS
MATLAB is making the pre-release of MATLAB R2011a available to existing MATLAB PCT licensees. R2011a adds a host of new GPU features.
- See: http://www.nvidia.com/object/tesla-matlab-accelerations.html

MainConcept released CUDA H.264/AVC Encoder SDK 1.1, updating its popular video codec with support for Mac OS X and Linux 32-bit/64-bit. V1.0 for CUDA shipped in Sept. 2010 as the first GPU-accelerated product by MainConcept. Leading video software developers are implementing CUDA support now (including Microsoft, with its upcoming Expression Encoder 4 with GPU acceleration).
- See: www.mainconcept.com/products/sdks/gpu-acceleration/cuda-h264avc.html

The NVIDIA Foundation’s Compute the Cure RFP is open for researchers in gene sequencing. Compute the Cure is an initiative to identify opportunities where NVIDIA technology and other resources can have a dramatic impact in the battle against cancer.
- See: www.computethecure.org
REPLAYS OF THE WEEK
NEW: Each week we will highlight a session from GTC 2010 and SC10. Here are our picks for this week:

Evolution of GPUs for General Purpose Computing (GTC 2010)
Ian Buck – NVIDIA (video – 40 mins.)
www.nvidia.com/object/gtc2010-presentation-archive.html#session2275

GPU Computing: To ExaScale and Beyond (SC10)
Bill Dally – NVIDIA (pdf)
www.nvidia.com/content/PDF/sc_2010/theater/Dally_SC10.pdf
CUDA JOBS
PensionsFirst of London provides advanced risk management analytics/advisory services and has grown rapidly to over 70 people. The company is looking to use GPUs to bring even more innovative products to its customers and is recruiting an experienced CUDA developer to join its team. Email recruitment@pensionsfirst.com or visit www.pensionsfirst.com.
CUDA CALENDAR
January 2011

– CUDA/OpenCL Training – Acceleware and Colfax

Jan. 17-21, 2011, Sunnyvale, Calif.
For more info, contact: services@acceleware.com
http://www.acceleware.com/jan17sunnyvale

– NEW: HPC and GPU Supercomputing in Finance – Hosted by Microsoft

Jan. 24, 2011, New York, NY (Microsoft offices: 1290 Avenue of the Americas)
Schedule
11:00 am – 12:00 noon: Session 1 – Supercomputing with Excel
12:00 noon – 1:00 pm: Session 2 – GPU Supercomputing with Microsoft HPC
1:00 – 2:00 pm: Repeat of Session 1 – Supercomputing with Excel
2:00 – 3:00 pm: Repeat of Session 2 – GPU Supercomputing with Microsoft HPC

– NEW: Meetup for HPC and GPU Enthusiasts – Hosted by Microsoft

Jan. 24, 2011, New York, NY (Microsoft offices: 1290 Avenue of the Americas)
6:00 – 8:30 pm: Meetup for people interested in HPC and GPU computing
To sign up, go to: – http://www.meetup.com/HPC-GPU-Supercomputing-Group-of-New-York

– Optimizing Financial Modeling/Chicago – Wolfram Research

Jan. 25, 2011, Chicago
Featured Speaker: Dr. Michael Kelly
www.wolfram.com/events/chicago2011/

– Optimizing Financial Modeling/New York – Wolfram Research

Jan. 27, 2011, New York
Featured Speaker: Dr. Michael Kelly
http://www.wolfram.com/events/newyork2011/

February – June 2011

– GPU Computing Session, German Physical Society Conference

March 13-18, 2011, Dresden, Germany
http://dresden11.dpg-tagungen.de/index.html

– ASIM Workshop 2011 – ASIM and Technische Universitat Munchen (TUM)

March 14-16, 2011, Leibniz, Germany
Theme: Trends in Computational Science & Engineering: Foundations of Modeling & Simulation
http://www5.in.tum.de/asim2011.html

– Application Accelerators in High Performance Computing (SAAHPC 2011)

Call for papers: May 6, 2011
Event: July 19-21, 2011, Univ. of Tennessee, Knoxville, Tennessee
http://illinois.edu/lb/article/2100/45663

– Workshop on High Performance Computational Biology – IEEE

May 16, 2011, Anchorage, Alaska
Note: Held with International Parallel & Distributed Processing Symposium
http://www.hicomb.org/

– Intelligent Vehicles Conference – IEEE

June 5-9, 2011, Baden-Baden, Germany
www.mrt.uni-karlsruhe.de/iv2011/

– Internat’l. Supercomputing Conference

June 19-23, 2011, Hamburg, Germany
http://www.supercomp.de/isc11/Take-Part/Call-for-Papers

– Internat’l. Conference on Computer Systems and Applications

June 27#45;30, 2011, Sharm El#45;Sheikh, Egypt
http://aiccsa2011.hpcl.gwu.edu/

Ongoing

– CUDA Training from EMPhotonics: www.emphotonics.com/services/cuda-training
– CUDA Training from Acceleware: http://www.acceleware.com/events
– CUDA Certification: www.nvidia.com/certification
– GPU Computing Webinars: www.nvidia.com/webinars

(To list an event, email: cuda_week_in_review@nvidia.com)
CUDA RESOURCES
GPU Technology Conference
– Presentations from GTC 2010: www.nvidia.com/gtc
SC10 Conference
– Presentations from SC10: www.nvidia.com/object/sc10_theater.html
CUDA GPUs
– List of CUDA-enabled GPUs: www.nvidia.com/object/cuda_gpus.html
Video Recommendation
– The Third Pillar of Science: www.nvidia.com/object/race-for-better-science.html
CUDA GPU Computing Forum
– Link to forum: http://forums.nvidia.com/index.php?showforum=62
CUDA and Parallel Nsight Overview
– Blog post and video: http://is.gd/gbGen
CUDA Downloads
– Download CUDA Toolkit 3.2: http://bit.ly/aKCENp
– Download OpenCL v1.1 pre-release drivers and SDK code samples (Log in or
apply for an account)
– Get developer guides and docs: http://developer.nvidia.com/object/gpucomputing.html
CUDA and Academia
– Learn more at http://research.nvidia.com/
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
CUDA Recommended Reading
– Read Kudos for CUDA: www.hpcwire.com/features/Kudos-for-CUDA-97889444.html
– Read Supercomputing for the Masses, Part 20: http://is.gd/f9o6o
– Read CUDA books: http://www.nvidia.com/object/cuda_books.html
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.
Copyright © 2010 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050.

Brak komentarzy