CUDA: Week in Review
Wed, Nov. 17, 2010, Issue #42 - Newsletter Home
Welcome to CUDA: Week in Review, an online news summary for the worldwide CUDA and GPU computing community.
In the Cloud: On Demand GPU Supercomputing from Amazon EC2
For the first time ever, enterprises and start-ups can access the supercomputing power of NVIDIA GPUs via the cloud - through a new service called Amazon Elastic Compute Cloud (EC2).

Why it matters: Supercomputing is increasingly important for technological innovation in everything from medical research and product design to climate modeling and energy exploration. However, the upfront cost of systems has limited their use, especially at the early stages of a project when people want to try out new ideas. By making GPUs available through Amazon EC2, supercomputing will be available to more innovators earlier in the process.

Peter De Santis, general manager of Amazon EC2, comments: "We're excited to help our customers access the raw power of GPU technology and look forward to the innovation this will enable." See Amazon Web Services blog post:
CUDA Toolkit 3.2 Delivers up to 300% Performance Improvement
NVIDIA announced the production release of CUDA Toolkit 3.2, which provides significant performance increases, improved math libraries and advanced cluster management features, including an up to 300% performance improvement in the CUDA BLAS library (CUBLAS) – which is eight times faster than the latest Intel MKL (Math Kernel Library).
  - CUDA Toolkit 3.2 download:
  - CUDA Toolkit 3.2 webinar (Nov. 23):

Mathematica 8 Supports the GPU
Wolfram's Mathematica 8 harnesses GPU devices for general computations using CUDA. A range of Mathematica 8 GPU-enhanced functions are built-in for areas such as linear algebra, image processing, financial simulation and Fourier transforms.
  - Watch the video: (see segment 2:21-3:01)

GPU-Accelerated Statistics in MATLAB with Jacket v1.6
AccelerEyes released version 1.6 of the Jacket GPU programming platform for MATLAB. The new version delivers a new statistics library featuring functions common to life science, defense and financial computing applications.
  - See:

Supercomputing 2010
Upcoming events at this week's SC10 conference in New Orleans include:
      -    Scaling Hierarchical N-Body Simulations on GPU Clusters, Nov. 18
      -    Size Matters: Space/Time Tradeoffs to Improve GPGPU Apps Performance, Nov. 18
      -    Optimal Utilization of Heterogeneous Resources for Biomolecular Simulations, Nov. 18
      -    Disruptive Technologies for Ubiquitous High Performance Computing, Nov. 19

  - For wrap-up of SC10 news and presentations made on the NVIDIA booth,

November 2010

Supercomputing 2010 (SC10)
Nov. 13-19, New Orleans
The NVIDIA GPU Computing Theater at SC10 will feature talks by industry luminaries, scientists and developers. All conference attendees are invited to participate.

Paving the Road to Exascale - Mellanox (at SC10)
Nov. 17, 7:00 p.m., New Orleans

Best-in-Class FSI Solutions (webinar) - ACUSIM
Nov. 18, 5:30 a.m. pacific

Training from CAPS
Nov. 23-25, Rennes, France

Improve Time to Debug (webinar) - Allinea Software
Nov. 24-25. Contact:

Nov. 26, Tokyo

Call for Papers - IEEE/ACM Intl. Symposium on Cluster, Cloud and Grid Computing
Papers deadline: Nov. 30

December 2010

CUDA and Advanced Image Processing - SagivTech
Dec. 12-14, Ramat Gan, Israel

UK GPU Computing Conference - Univ. of Cambridge
Dec. 13-14, Cambridge, UK

Dec. 16-18, Seoul


Scientific Computing in the Americas: The Challenge of Massive Parallelism
Jan. 3-14, 2011, Valparaiso, Chile

IEEE International Parallel & Distributed Processing Symposium
May 16-20, 2011, Anchorage

Intelligent Vehicles Conference - IEEE
June 5-9, 2011, Baden-Baden, Germany

Internat'l. Conference on Computer Systems and Applications
June 27-30, 2011, Sharm El-Sheikh, Egypt

– CUDA Certification:
– GPU Computing Webinars:
– Training from EMPhotonics:

(To list an event, email:

GPU Technology Conference
– See presentations and keynotes from GTC 2010:
– See list of CUDA-enabled GPUs:
CUDA and Parallel Nsight Overview
– See blog post and video:
CUDA Downloads
– Download CUDA Toolkit 3.2:
– Download OpenCL v1.1 pre-release drivers and SDK code samples (Log in or
   apply for an account
– Get developer guides and docs:
CUDA and Academia
– Learn more at
CUDA on the Web
– See previous issues of CUDA: Week in Review:
– 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 Recommended Reading
– Read Kudos for CUDA:
– Read Supercomputing for the Masses, Part 20:
– Read CUDA books:
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:
Stay in Touch with NVIDIA
Twitter   Follow GPU Computing on Twitter
Facebook   Become a fan of NVIDIA on Facebook
NVIDIA online profiles   See list of NVIDIA online profiles

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.