Debuggers
» Ocl-emu
OpenCL Emulator-debugger allows one to compiler and to debug OpenCL kernels as C++ procedures.
| Additional Details |
The goal of the project is to provide OpenCl developers with the full support of MS Visual Studio C++ development and debugging environment. The emulator intends to help at least 2 kinds of developers. First group are novices who do not like to learn intricacies of the OpenCl run-time and would like to get “Hello World” kernel as an one line call (as it should be). The second group is algorithm developers who also do not like to know idiosyncrasies of OpenCl run-time but need to concentrate on intricacies of their massive parallel algorithm(s). |
| Author(s) |
A Nopouet |
| API Used |
OpenCL™ |
| Software License |
Open Source |
| Available Content |
Website |
DVD Authoring
» ArcSoft ShowBiz 5.0.1
Create and edit videos like a pro. ShowBiz 5 provides advanced technology features including stereoscopic 3D support, up-scaling of SD video to near HD quality with SimHD, video stabilization, Blu-ray Disc burning, and much more.
| Additional Details |
- Import files from the built-in media library, or from external devices
- Enhance photos, videos, and audio files before making the movie
- Liven up your movie by adding a variety of cool effects
- Provides both Storyboard and Timeline modes for users of all levels
- Simultaneously produce your movies to the web, mobile devices, and discs
|
| Author(s) |
A Nopouet, ArcSoft |
| API Used |
OpenCL™, UVD |
| Software License |
Open Source |
| Available Content |
Website |
Image Processing
» ArcSoft Panorama Maker Pro 6
Create perfect panorama images with your photos and videos
| Additional Details |
- Stitch photos and videos into panoramas – now in 3D!
- Includes five professional stitch modes
- Powerful one-click enhancement tools and built-in online Print Service
- Various export options including 3D MPO
|
| Author(s) |
ArcSoft |
| API Used |
OpenCL™ |
| Software License |
Proprietary |
| Available Content |
Website |
» Viewdle Photo Uploader
Viewdle Uploader instantly tags your friends and uploads all of your photos to Facebook straight from the folders on your desktop.
| Additional Details |
- Real-time face recognition
|
| Author(s) |
Viewdle |
| API Used |
OpenCL™ |
| Software License |
Proprietary |
| Available Content |
|
Libraries
» libstdcl – The Standard Compute Layer Library
The standard compute layer library (libstdcl) provides a simple interface to the OpenCL™ API for parallel programming of heterogeneous platforms with co-processor devices. libstdcl is designed to support the most typical use-cases in a style inspired by familiar and traditional UNIX APIs for C programming.
| Additional Details |
The libstdcl library provides the following features and support:
- Default managed OpenCL contexts
- Dynamic OpenCL program loader support
- Management of OpenCL kernel and memory operations
- Utilities for linking, tracing and timing
|
| Author(s) |
David Richie |
| Organization Type |
Commercial |
| Organization |
Brown Deer Technology |
| API Used |
OpenCL |
| Software License |
LGPLv3 |
| Available Content |
Website
Source Code |
» GPU Systems Libra SDK
Cross processor, cross platform, cross language – standard math library and runtime API – for software application development.
| Organization Type |
|
| Organization |
Gpu Systems |
| API Used |
OpenCL™ |
| Software License |
Proprietary |
| Available Content |
Website
Video
Examples |
» MainConcept H.264/AVC Pro Encoder
MainConcept is making it even easier by providing software developers with a flexible yet powerful software development kit to add OpenCL™ accelerated encoding to their own solutions. The MainConcept OpenCL™ H.264/AVC Encoder SDK allows powerful encoding into the H.264/AVC Baseline,.
| Additional Details |
- Baseline, Main and HighProfiles
- I, P and B frames support
- CABAC/CAVLC entropy
- Deblocking filter
- Intra-blocks in P-frames
- 4×4 intra partitioning
- CBR (Constant Bitrate) support
- HRD model maintenance
- VBR rate control
- Support for bitrates of up to 100 Mbit/sec
- Interlaced mode support
- Input resolution up to 1920×1080
- Performance is ~100fps for 1080p video on a top ATI hardware (strongly depends on the host PC performance and H.264 settings)
|
| Organization Type |
Commercial |
| Organization |
MainConcept |
| API Used |
OpenCL™ |
| Software License |
Revenue based licensing model |
| Available Content |
Performance Sheet
Website |
» ViennaCL
A linear algebra library for computations on GPUs and multicore CPUs
| Additional Details |
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 levels 1, 2 and 3) and the solution of large systems of equations by means of iterative methods with optional preconditioner. |
| Author(s) |
Primary Contact: Karl Rupp |
| Organization Type |
Academic |
| Organization |
Institute for Microelectronics, TU Wien |
| API Used |
OpenCL™ |
| Software License |
Open Source |
| Available Content |
Website |
Numerical Simulator
» LAMMPS Molecular Dynamics Simulations
Computational chemistry employs molecular dynamics simulations to simulate the motions of interacting atoms and molecules. An existing production code used for molecular dynamics simulations (LAMMPS) was modified using OpenCL and STDCL to provide a single implementation capable of running on heterogeneous architectures with CPUs, GPUs, and APUs. OpenCL devices are used for both pair potential and nearest neighbor calculations that comprise the bulk of the computation for the targeted benchmark (Embedded Atom Model). The code can utilize multiple devices across multiple nodes transparently with the existing MPI parallelization and STDCL device management features.
Physics
» “PowderToy” Particle & Fluid Simulation Application
The “PowderToy” particle & fluid simulation application was the first public demonstration of OpenCL functionality. It was presented by AMD at Siggraph Asia 2008.
| Additional Details |
This demonstration shows how OpenCL can be used to extract and implement high performance parallel computing on multi-core CPUs. |
| Author(s) |
Advanced Micro Devices, Inc. |
| Organization Type |
Commercial |
| Organization |
Advanced Micro Devices, Inc. |
| API Used |
OpenCL |
| Software License |
Proprietary |
| Available Content |
Video |
» Optimized Executions of Havok Middleware on AMD Platforms
AMD and Havok demonstrated new, optimized executions of Havok’s physics middleware on AMD platforms at the 2009 Game Developers Conference. The demonstration included the first OpenCL supported execution of Havok Cloth™.
Programming Model
» Aparapi
Extends Java’s ‘Write Once Run Anywhere’ to include GPU devices.
| Additional Details |
Aparapi is an API for expressing data parallel workloads in Java and a runtime component capable of converting the Java bytecode of compatible workloads into OpenCL™ so that it can be executed on a variety of GPU devices. |
| Sponsor |
Advanced Micro Devices, Inc. |
| Organization |
Open Source |
| API Used |
OpenCL™ |
| Software License |
Open Source |
| Available Content |
Website
Video
White Paper |
» JavaCL
JavaCL wraps OpenCL in a nice Java API with goodies
| Additional Details |
Parallel random, FFT, BLAS, reduction utils, code generators…
 |
| Organization |
Open Source |
| API Used |
OpenCL™ |
| Software License |
BSD-licensed |
| Available Content |
Website |
» Clyther
CLyther is a Python language extension that makes writing OpenCL code as easy as Python itself.
| Additional Details |
CLyther is a Python tool similar to Cython and PyPy. CLyther is a just-in-time specialization engine for OpenCL. The main entry points for CLyther are its clyther.task and clyther.kernel decorators. Once a function is decorated with one of these the function will be compiled to OpenCL when called. |
| Author(s) |
Sean Ross-Ross |
| Organization |
Open Source |
| API Used |
OpenCL™ |
| Software License |
Open Source |
| Available Content |
Website |
» PyOpenCL
PyOpenCL lets you access GPUs and other massively parallel compute devices from Python
| Author(s) |
Andreas Kloeckner |
| Organization Type |
Open Source |
| API Used |
OpenCL™ |
| Software License |
MIT License |
| Available Content |
Website |
Ray Tracing
» Fast KD-Tree and Ray Tracing on OpenCL™
A demo of GPU-accelerated ray tracing implemented in OpenCL™ achieving up to 50x speedup using an ATI Radeon™ HD 5870 GPU compared to an Intel Core2 6300 CPU.
| Additional Details |
This demo adopts a BFS manner to build a KD-tree. The quality of the KD-tree built on the GPU is comparative with the quality of the tree built on the CPU but the construction is faster when performed on the GPU. The KD-restart and KD-backtrack algorithm performance is improved by a simulated stack. The overall KD-tree traversal algorithm is completely stack-based.
|
| Author(s) |
Jiayin Cao
Qian Zhang |
| Organization Type |
Academia |
| Organization |
University of Tongji (Shanghai, China) |
| API Used |
OpenCL™ |
| Software License |
Free to use. Source code on request. |
|
* Configuration: Intel Core2 6300 CPU 1.86 GHz), Microsoft® Windows® XP, ATI Radeon™ HD 5870 GPU, ATI Stream SDK v2.0-beta4 (and associated display driver) |
Science
» N-Body Simulations using OpenCL™
An N-Body simulation models the motion of particles subject to a force due to the particle-particle interactions between all particles in the system. Brown Deer has developed an N-Body simulation code accelerated with GPUs using OpenCL.
| Additional Details |
A typical example (shown above) is the simulation of stars in a galaxy subject to the gravitational force. |
| Author(s) |
David Richie |
| Organization Type |
Commercial |
| Organization |
Brown Deer Technology |
| API Used |
OpenCL™ |
| Software License |
GPLv3 |
| Available Content |
Website
Source Code |
Seismic Imaging
» Finite-Difference Time-Domain Solvers for Modeling Velocity-Stress Wave Propagation
Finite-difference time-domain solvers are used to model velocity-stress wave propagation for seismic applications. A direct solution of the time-dependent velocity vector and stress tensor is solved on a staggered three-dimensional grid.
| Additional Details |
The image shown represents the propagating seismic pressure wave in a three-dimensional seismic model of the earth’s surface (1500m x 750m x 750m) with a 40m cubic high-velocity blocky inclusion.The simulation was performed entirely on the AMD FireStream™ 9250 GPU co-processor. The velocity vector and stress tensor values were modeled on a 256 x 128 x 128 grid. The propagating wave was generated by a Ricker wavelet applied to the z-component of the velocity field at the center of the simulation domain. |
| Author(s) |
David Richie |
| Organization Type |
Commercial |
| Organization |
Brown Deer Technology |
| API Used |
OpenCL™ |
| Software License |
GPLv3 |
| Available Content |
Website
Source Code |
Video Processing
» Cyberlink PowerDirector 10
PowerDirector 10 is video editing software with 2nd generation TruVelocity rendering engine that’s faster than ever, along with a rich end-to-end 3D editing suite.
| Additional Details |
- Faster Rendering with TrueVelocity 2 – 2nd gen. native 64-bit video engine delivers even more rendering speed.
- OpenCL for Optimal Video Effect Speed — Harnesses GPU power for greatly improved video effect speed.
- Intelligent Rendering with SVRT — Analyzes an entire project, chooses best output profile for production speed.
|
| Author(s) |
Cyberlink |
| API Used |
OpenCL™, UVD, UVD3 |
| Software License |
Proprietary |
| Available Content |
Website |
» Sony Vegas Pro 11 and 10.0d
The Vegas™ Pro 11 collection — Vegas Pro 11, DVD Architect™ Pro 5.2, and Dolby® Digital Professional Encoder — provides an efficient, intuitive and integrated content creation environment for video and broadcast professionals. Now featuring GPU-accelerated performance with OpenCL™-supported devices, Vegas Pro 11 powers through video processing and rendering tasks with ease.
| Additional Details |
Vegas Pro 11 leverages GPU acceleration for video FX, transitions, compositing, pan/crop, track motion and encoding, providing a significantly faster workflow. The addition of GPU acceleration streamlines the video editing experience in Vegas Po 11 by providing playback performance gains and faster rendering times, ideal for industry professionals who work on tight deadlines where every second counts. |
| Company |
Sony |
| API Used |
OpenCL™ |
| Software License |
Proprietary |
| Available Content |
Website |
» MotionDSP vReveal 3.0
Free software to organize, fix, edit, and share your videos. Great looking results in seconds, not hours. Now with GPU-accelerated H.264 video encoding.
| Additional Details |
Fix poor lighting, colors, shaky video, organizes all videos into one viewer, and clean’s the camera noise and compression artifacts. It can also take a panned video footage and create a panorama image. |
| Company |
MotionDSP |
| API Used |
OpenCL™ |
| Software License |
Proprietary |
| Available Content |
Website |
» Sony Movie Studio HD 11
Entry-level media production tools are powerful, easy to use, and loaded with features and extras. Perfect for the new digital media creator, these products deliver exceptional power at affordable prices.
| Additional Details |
Vegas™ Movie Studio HD is the easiest way to make your own professional-looking movies. Simply import your video footage or digital photos, edit out the parts you don’t want and enhance the rest with transitions, titles, and more. Sharing your creation is simple. Export to popular portable devices or publish online. |
| Company |
Sony |
| API Used |
OpenCL™ |
| Software License |
Proprietary |
| Available Content |
Website |
Visualization
» Geoweb3d Desktop
High fidelity 3D GIS visualization for the geospacial community
| Additional Details |
The 3D engine maximizes use of the GPU to remove conventional barriers with respect to size, resolution, and complexity. |
| Company |
Geoweb3d |
| API Used |
OpenCL™ |
| Software License |
Proprietary |
| Available Content |
Website |
|
