WELCOME |
Welcome to "CUDA: Week in Review," an online news summary for the worldwide CUDA and GPU Computing community.
|
|
CUDA NEWS |
GPUs Boost Supercomputers’ Energy Efficiency |
The Green500 List of the world’s most energy-efficient supercomputers was published this week. Agam Shah of PCWorld writes: "Supercomputers that mix CPUs with graphics processors made their mark on the Green500 list….Two of the top eight green supercomputers are new entrants from China, and combine graphics processors from NVIDIA with Intel’s CPUs." Read Agam’s article here: http://www.pcworld.com/businesscenter/article/200309/gpus_boost_ supercomputers_energy_efficiency.html |
Hot off the Press: GPU Technology Conference - Sessions Preview |
The GTC team has identified a preliminary list of sessions to be presented in September. While we are still reviewing all the submissions, here are a few confirmed presentations to whet your appetite:
– Bridging GPU Computing and Neuroscience to Build Large-Scale Face Recognition on Facebook
Nicolas Pinto, PhD Student, MIT
– Using GPUs to Follow the Sun’s Latest Moves
Mark Cheung, Sr. Physicist, Lockheed Martin Solar & Astrophysics Lab
– Shockingly Fast and Accurate CFD Simulations
Timothy Warburton, Associate Professor, Rice University
– Banking on Monte Carlo… and Beyond
Dr. Ian Reid, Numerical Algorithms Group
– WebGL: Bringing 3D to the Web
Vladimir Vukicevic, Principal Engineer, Mozilla Corporation |
More GTC Info |
GTC 2010 sponsors include Adobe, HP, Microsoft, Supermicro, PNY, Dell, Cooley, Synnex, Next IO, GE Intelligent Platforms, AMAX, SGI, Appro and Sutter Hill Ventures, and media partner Dr. Dobbs.
– Register for GTC today as space is limited (code: GMCUDANEWS10)
– For list of sessions, see the GTC agenda page
– Join the GTC Facebook fan page and GTC email update list |
|
CUDA APPS |
GPUs and Science |
Researchers gathered this week at the University of Pittsburgh’s Center for Simulation and Modeling for a symposium on GPUs in chemistry and materials science. Here they discussed state-of-the-art GPU-enabled applications such as AMBER, VMD, Q-CHEM and Terachem. Dr. Ross Walker of the San Diego Supercomputer Center reviewed the native capabilities of AMBER 11 utilizing GPUs. Dr. Scott Le Grand of NVIDIA gave a presentation on AMBER + MPI performance developments. A related event, the American Chemical Society meeting, will take place on Aug. 22-26 in Boston. For information on NVIDIA and biochemical research, see: http://www.nvidia.com/object/tesla_bio_workbench.html. |
|
CUDA ZONE |
New on CUDA Zone: Software Transactional Memory for GPUs |
Authors: Daniel Cederman, Philippas Tsigas, Muhammad Tayyab Chaudhry; Chalmers University of Technology, Sweden
Application Domain: Programming Tools
Extract: "Software Transactional Memory (STM) allows you to write sequential code that is executed concurrently without using locks. This greatly simplifies the implementation of parallel programs. The simplicity, however, comes at the price of performance. With this work we try to shed some light on the performance price of STMs on CUDA…. The behavior of STMs when the contention to shared data is low might be acceptable. But when the contention is high, it is better to try to design the program to be data parallel, which is where CUDA excels, and/or to use lock-free data structures." See: http://is.gd/daArr |
CUDA Zone: Have a CUDA-related app or paper? Let us know when you post it on CUDA Zone and we’ll send you a CUDA t-shirt! |
|
CUDA JOB OF THE WEEK |
Distinct, a consultancy and outsourcing provider, uses advanced data modeling techniques to improve operational performance and create growth. Clients include banking, insurance and healthcare companies in Ireland and the U.K. The prospective role will involve development of Distinct’s analytical platform using GPU-based architectures. Requirements include experience in GPU programming, architectures and in particular, CUDA. Contact Louise.Walsh@distinctpartners.com. |
|
CUDA EDUCATION |
Microsoft Launches DirectCompute Lecture Series |
Microsoft launched a series of lectures focused on DirectCompute. A component of DirectX, DirectCompute is Microsoft’s GPGPU programming solution for Windows. Videos of the lectures are posted online.
– Robert Hess of Microsoft hosts a roundtable with thought leaders, including Eric Young of NVIDIA http://channel9.msdn.com/posts/gclassy/DirectCompute-Expert-Roundtable-Discussion/
– James Fung of NVIDIA speaks on "DirectCompute GPU Optimizations and Performance" http://channel9.msdn.com/posts/gclassy/DirectCompute-Lecture-Series-210-GPU- Optimizations-and-Performance/
– More info: http://blogs.msdn.com/b/seealso/archive/tags/directcompute+lecture+series/ |
GPU Computing Webinars (CUDA C, OpenCL, Parallel Nsight and more…) |
NVIDIA’s webinars are increasingly popular in the GPU computing community and represent a great way to get up to speed quickly. Here are several coming up in July:
– Intro to OpenCL Application Development with gDEBugger Tuesday, July 6, 9:00 a.m. pacific
– Rapid Prototyping and Visualization with OpenCL Studio Wednesday, July 7, 9:00 a.m. pacific
– Monitoring and Mapping GPU Clusters with Bright Cluster Manager (Presented by CEO and Founder of Bright Computing, Dr. Matthijs van Leeuwen) Thursday, July 8, 9:00 a.m. pacific
|
CUDA and Academia |
– Over 350 universities are teaching CUDA and GPU Computing courses.
– The CUDA Center of Excellence (CCOE) Program recognizes universities expanding the frontier of parallel computing. |
|
CUDA TRAINING |
SagivTech Announces CUDA Course on Image Processing, Following GTC |
SagivTech’s new CUDA course will take place Sept. 27-29 in the San Francisco area, following the GPU Technology Conference. This course is for CUDA developers looking for optimization for image processing on NVIDIA GPUs. Course instructors are Micha Feigin Almon, an experienced developer, mathematician and image processing specialist and Dr. Chen Sagiv, an applied mathematician and expert in image processing algorithms. This is a convenient option for GTC attendees. See http://www.sagivtech.com/36923.html
– Other CUDA training courses from SagivTech:
|
CUDA training from Acceleware |
|
CUDA training from EMPhotonics |
|
CUDA Research and Certification |
For info on NVIDIA programs for GPU Computing developers, see: http://www.nvidia.com/object/io_1275409333119.html
|
|
CUDA CALENDAR |
July 2010
– Programming and Tuning Massively Parallel Systems
– NVIDIA Bio Workbench and AMBER 11
– Hybrid Cloud Computing with NVIDIA GPUs and ProActive Parallel Suite
– Symposium on Application Accelerators in High-Performance Computing (SAAHPC 2010)
– Parallel Symbolic Computation 2010 (PASCO)
– SIGGRAPH
– CUDA Programming on GPUs
August 2010
– Proven Algorithmic Techniques for Many-Core Processors
– Virtual School of Comp. Science & Engineering
– GPU Programming for Molecular Modeling
– Symposium on Chemical Computations on GPGPUs
– Unconventional High Performance Computing 2010 (UCHPC 2010)
September 2010
– GPU Technology Conference (GTC) 2010
Future
– Supercomputing 2010
– IEEE International Parallel & Distributed Processing Symposium
(To list an event, email: cuda_week_in_review@nvidia.com)
|
|
CUDA RESOURCES |
CUDA Articles in Dr. Dobb's |
– Supercomputing for the Masses, Part 18: http://is.gd/cs6b9
– Supercomputing for the Masses, Part 17: http://is.gd/cs6eI
– Supercomputing for the Masses, Part 16: http://is.gd/citaC
– Supercomputing for the Masses, Part 15: http://is.gd/citnJ
|
CUDA Books |
– Programming Massively Parallel Processors by D. Kirk, W. Hwu: http://is.gd/7bNYP
– See additional books here: http://www.nvidia.com/object/cuda_books.html |
CUDA Toolkit |
– Download CUDA Toolkit: http://bit.ly/aKCENp
– OpenCL v1.1 pre-release drivers and SDK code samples are available to GPU Computing registered developers. Log in or apply for an account to download. |
CUDA Documentation |
Download developer guides and documentation: http://developer.nvidia.com/object/gpucomputing.html |
NVIDIA Parallel Nsight |
– Download the Beta: www.nvidia.com/nsight
– Download the Release Notes: http://bit.ly/9iEYMs |
|
CUDA ON THE WEB |
– Check out the NVIDIA Research site: http://research.nvidia.com
– Read 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
– Watch CUDA on YouTube: http://www.youtube.com/nvidiacuda
|
|
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.
Send comments and suggestions to: cuda_week_in_review@nvidia.com |
|
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. |