CULA 2.0 released

July 11th, 2010

EM Photonics announced today the general availability of CULA 2.0, its GPU-accelerated linear algebra library. The new version provides support for NVIDIA GPUs based on the latest “Fermi” architecture.

CULA contains a LAPACK interface comprised of over 150 mathematical routines from the industry standard for computational linear algebra, LAPACK. EM Photonics’ CULA library includes many popular routines including system solvers, least squares solvers, orthogonal factorizations, eigenvalue routines, and singular value decompositions. CULA offers performance up to a magnitude faster than highly optimized CPU-based linear algebra solvers. There is a variety of different interfaces available to integrate directly into your existing code. Programmers can easily call GPU-accelerated CULA from their C/C++, FORTRAN, MATLAB, or Python codes. This can all be done with no GPU programming experience. CULA is available for every system equipped with GPUs based on the NVIDIA CUDA architecture. This includes 32- and 64-bit versions of Linux, Windows, and OS X.

More information is available at

Introductory OpenCL Tutorial

July 8th, 2010

This tutorial by Benedict R. Gaster from AMD provides a detailed introduction to OpenCL. Covered topics include:

  • Using platform and device layers to build robust OpenCL™ applications
  • Program compilation and kernel objects
  • Managing buffers
  • Kernel execution
  • Kernel programming – basics
  • Kernel programming – synchronization
  • Matrix multiply – a case study
  • Kernel programming – built-ins

gDEBugger V5.6 – Introducing iPhone and iPad on-device debugging and profiling

July 8th, 2010

Graphic Remedy is proud to announce the release of gDEBugger Version 5.6 for Windows, Linux, Mac OS X, iPhone and iPad. This version introduces iPhone and iPad on-device debugging and profiling abilities, letting developers optimize their apps in real-time on actual iPhone and iPad hardware, while viewing invaluable inside information such as the device’s GPU, CPU, graphics driver and operating system performance counters.

gDEBugger is an OpenGL, OpenGL ES and OpenCL debugger and profiler that traces application activity on top of the OpenGL API, and lets programmers see what is happening within the graphics system implementation to find bugs and optimize OpenGL application performance. gDEBugger runs on Windows, Mac OS X, iPhone and Linux operating systems.

Learn CUDA in Sydney or Canberra Next Week

July 7th, 2010

For our Australian readers interested in GPU computing.  Next week there will be two free workshops on GPU Computing with CUDA.  The workshops will both include a tutorial on CUDA C/C++ programming along with additional presentations by local speakers.  Topics will include an overview of NVIDIA Tesla and the latest  Fermi architecture GPUs, CUDA programming, debugging and profiling tools, and optimization strategies.

Follow the links above for full details.  Space is limited, so be sure to RSVP to the addresses provided.

Image Processing with CUDA Courses following the GTC

July 4th, 2010

SagivTech plans to offer a 3-days course that deals with Image Processing with CUDA in the USA this September. This is an advanced course that is intended for experienced CUDA developers looking for optimization methods for image processing applications implemented on NVIDIA GPUs.

The course will be held in the San Francisco area, 9am to 5pm September 27-29.

Read the rest of this entry »

OpenCL 1.1 specification released

June 18th, 2010

The OpenCL OpenCL Logo1.1 specification, including header files and documentation, has been released. It includes significant new functionality:

  • Host-thread safety, enabling OpenCL commands to be enqueued from multiple host threads
  • Sub-buffer objects to distribute regions of a buffer across multiple OpenCL devices
  • User events to enable enqueued OpenCL commands to wait on external events
  • Event callbacks that can be used to enqueue new OpenCL commands based on event state changes in a non-blocking manner
  • 3-component vector data types
  • Global work-offset which enable kernels to operate on different portions of the NDRange
  • Memory object destructor callback
  • Read, write and copy a 1D, 2D or 3D rectangular region of a buffer object
  • Mirrored repeat addressing mode and additional image formats
  • New OpenCL C built-in functions such as integer clamp, shuffle and asynchronous strided copies
  • Improved OpenGL interoperability through efficient sharing of images and buffers by linking OpenCL event objects to OpenGL fence sync objects
  • Optional features in OpenCL 1.0 have been bought into core OpenCL 1.1 including: writes to a pointer of bytes or shorts from a kernel, and conversion of atomics to 32-bit integers in local or global memory

Workshop on GPU Programming for Molecular Modeling, August 6-8,2010, University of Illinois

June 18th, 2010
GPU-Accelerated Ion Placement

GPU-Accelerated Ion Placement

The Theoretical and Computational Biophysics Group, NIH Resource for Macromolecular Modeling and Bioinformatics ( at the University of Illinois at Urbana-Champaign, presents a Workshop on GPU Programming for Molecular Modeling to be held August 6-8, 2010, at the Beckman Institute for Advanced Science and Technology, on the University of Illinois campus in Urbana, Illinois, USA. Application, selection, and notification of participants is on-going through July 29, 2010.

Note: Participants are encouraged to attend the multi-site “Proven Algorithmic Techniques for Many-core Processors” workshop the preceding week (August 2-6) at the location of their choice. Registration for this workshop is required for participants without equivalent GPU-programming training or experience.

OpenCurrent v1.1.0 released

June 18th, 2010

OpenCurrent version 1.1.0 has been released. OpenCurrent is a library for solving certains types of PDEs over 3D cartesian grids. It supports single and double precision, and includes solvers for Poisson equations, diffusion, and incompressible Navier-Stokes.

New features:

  • Multi-GPU communication library
  • Multi-GPU versions of Multigrid solver, Incompressible Navier-Stokes solver, and more
  • NetCDF support now optional
  • Support for Fermi/CUDA 3.0
  • Numerous bug fixes and enhancements

Get it here:

ViennaCL: Linear Algebra on GPUs using OpenCL

June 15th, 2010

The Vienna Computing Library (ViennaCL) is a scientific computing library written in C++ and based on OpenCL. It allows simple, high-level access to the vast computing resources available on parallel architectures such as GPUs and is primarily focused on common linear algebra operations (BLAS level 1 and 2) and the solution of large systems of equations by means of iterative methods. The following iterative solvers are implemented:

  • Conjugate Gradient (CG)
  • Stabilized BiConjugate Gradient (BiCGStab)
  • Generalized Minimum Residual (GMRES)

Read the rest of this entry »

3 New Rugged GPGPU products from GE

June 15th, 2010

GE has introduced three new rugged computing products featuring integrated GPGPU technology using NVIDIA CUDA-capable GPUs.  The first is the IPN250 Rugged 6U OpenVPX Single Board Computer (SBC).  The second is the 6U OpenVPX NPN240 multi-processor. The NPN240 features two NVIDIA® CUDA-capable GT240 96-core GPUs, enabling it to deliver up to 750 GFLOP/S peak per card slot (depending on the application). Multiple NPN240s can be linked to one or more hosts to create multi-node CUDA GPU clusters capable of thousands of GFLOP/S.  The third is the OpenVPX-compatible GRA111 high performance graphics board, which is the first rugged implementation of a CUDA-capable GPU.

Page 20 of 41« First...10...1819202122...3040...Last »