Mar 22

OpenCL and Computer Vision Talk at UFMG

The Department of Computer Science of Federal University of Minas Gerais – DCC/UFMG and Khronos Chapter Brazil have been working together to spread and strengthen industrial and scientific use of Khronos’ standards, most notably OpenCL and OpenGL.

On March 12th a talk was held with students and researchers of the Computer Vision laboratory – VeRLAB to present benefits of using GPGPU through OpenCL to accelerate CV algorithms.

Summary:

Machine learning and computer vision have become a reality in people’s daily life through smart wearables (smart glasses, watches phones), vehicles capable of recognizing traffic signs, biometric systems and many others. These technologies increase safety and comfort when using such machines and are currently object of active research. However, development of better algorithms and the possibility of executing them in mobile devices under acceptable time frames and lower energy consumption still remain as open challenges.

This presentation covers topics on how GPU parallel processing allows performance and energy efficiency increases when executing algorithms whose inputs are images. Accelerations up to 800x may be obtained by intelligent use of appropriate parallel algorithms suited to SIMD architectures, explicit cache management and use of texture samplers.

Resources:

Video: Generalized Hough Transform

Video: Dynamic shader:

Video: Heat transfer simulation

Feb 15

Simple CLGL Interop Demo

We have had some requests from users to post a simple OpenCL OpenGL Interoperation example using vertexes and we decided to post a fresh example.

This is the same video that is used in the tutorials. However, the code has been updated to use simple instructions from OpenCLTemplate.

OpenCL/GL Interop is a powerful tool to manipulate OpenGL graphics directly in GPU memory with minimal data transfer. All GL Buffer objects as well as textures can be manipulated.

 Download CLGLInterop demonstration.

Jan 22

SPIR Protects OpenCL C Code

One very important issue with OpenCL code at the moment is that it needs to either be compiled at runtime by vendor’s compilers or be precompiled but also restricted to the hardware it has been precompiled to. This is a problem because programmers cannot protect sensitive parallel code unless it is delivered precompiled to each specific platform, a very tedious task that completely challenges the goals of having an open specification.

Khronos’ SPIR (Standard Portable Intermediate Representation) specification is an important step towards protecting sensitive source code while still maintaining cross-platform capabilities.

This may very well be the last step that gaming industry and multimedia processing companies were waiting to fully incorporate heterogeneous computing into their applications.

Further details can be found at

https://www.khronos.org/news/press/khronos-releases-spir-1.2-specification-for-portable-encoding-of-opencl-dev

Dec 26

Happy New Year

 

Hello everyone! We wish you all a happy new year with faster processing and lower power consumption.

The image below was rendered using Dynamic Shader.

Download Dynamic Shader (beta)

jbells

Nov 30

CMSoft Dynamic Shader Beta Release

CMSoft Dynamic Shader Beta Release

 

Download Dynamic Shader (beta)

 

We are proud to release CMSoft’s Dynamic Shader (beta), a software designed to let artists quickly bring to life their creations by providing a fast and easy way to create high quality shading of 2D pictures, such as the one below:

 

 DynamicShaderrender

 

The following video demonstrates how to create automatic gradient filling for 2D pictures:

 

Dynamic shader aims to be a practical tool for professional art, concept sketches and people who just like to draw and paint alike. The algorithm uses concepts from dynamic programming in order to compute color gradients and perform automatic shading. Due to the large amount of processing power required it is necessary to have an OpenCL-enabled GPU.

Recommended hardware:
- 64-bit Windows with at least 4 Gb RAM
- OpenCL enabled GPU

Please keep in mind that Dynamic Shader is currently in beta version. Please do send us any and all suggestions/comments using the email cmsoft@cmsoft.com.br

 

Many thanks to:

Grand Prix Senai de Inovação 2013, event during which Dynamic Shader was first unveiled.

Tales Vieira (drawing/shading) for the amazing picture and shading.

 

Download Dynamic Shader (beta)

 

 

Video agenda:

- Demonstrate the first beta release of CMSoft’s Dynamic Shader;
- Open a picture which contains an outline of the objects, like an image from a coloring book;

- Click the color picker button to draw color references onto the image;
- Drawing color references – colors get added to the sidebar

- Click render & save to draw image – strokes get saved in the same folder as the picture and are loaded when you open the image again

- Move mouse over color boxes
- Easy to change color – click color and pick a new color – render

- Remove color with right click

- Demonstrate bigger renders

 

Nov 04

OpenCLTemplate 1.165

OpenCLTemplate 1.165

 

OpenCLTemplate has been updated to continue allowing easy use when various OpenCL implementations are available in the same computer.

 

Changelog:

- Fixed issues when more than one ComputePlatorm is available in the same system. OpenCLTemplate default initializer picks the platform which contains the GPUs.

 

Download OpenCLTemplate

Oct 06

Brasil Chapter – Presentations

Brasil Chapter – Presentations

 

Excellent talks and ideas were presented in the first Brasil Chapter meeting.

We’re proud to share some of the resources with the community (only available in Portuguese):

 

Introduction to heterogeneous computing – Profa. Dra. Denise Stringhini

 

Optical measurement system powered by heterogeneous computing – MSc Pedro Buschinelli

 

 

 

 

 

 

Sep 21

Khronos Chapter Brazil Meeting

Khronos Chapter Brazil Meeting

 

Update (28 Sep): Click to download more pictures of the event

 

 

The first Brazil Chapter meeting was held last Friday, Sep 20th.

It was an outstanding encounter where researchers, professionals and students were able to share their thoughts on their high performance applications as well as set goals for Brazil Chapter.

We will soon post more pictures, presentations and videos from the event.

We’d like to thank Khronos Group for making this all possible, all participants for coming and all the community for the interest and support.

 

KhrBrChap Motivation Heterog Computing

 

KhrBrChap Coffe Break

 

 

 

Aug 20

Brazil Chapter Meeting

Brazil Chapter Meeting

We’re pleased to invite the OpenCL community to take part in the first meeting of the Brazil Chapter, scheduled to Sep 20th in Belo Horizonte – MG.

Our discussion will be focused on using OpenCL and parallel processing to increase software industry competitiveness by allowing lower energy consumption and faster software.

If you would like to participate please send us an email.

 

Jul 25

OpenCL 2.0 is coming!

OpenCL 2.0 is coming!

 

OpenCL 2.0 has been presented by Khronos at SIGGRAPH 2013 and has a draft specification and it has many exciting features. At this point the 2.0 spec needs some clarification in some aspects and preferably some examples.

Among the new interesting features are:

Shared virtual memory – clSVMAlloc will be the new base memory allocation function for shared memory that will remain synchronized between host and device. This is going to be a useful function when the two devices share the same physical memory, so that no copy is needed.

Dynamic parallelism – Device kernels will be able to launch its own subkernels in the device. With proper attention this should effectively enable recursive kernels.

Generic address space – At this moment, developers need to declare all buffer types in kernels and functions. If a function does the same operation to a __global or __private memory buffer it has to be duplicated. Generic address spaces should eliminate this need by accepting generic memory qualifiers.

Pipe spaces – This seems to be a pipeline with FIFO characteristics that can be used by workitems and host to allow message passing.

 

Of all thesen new features, dynamic parallelism seems to be the one that will affect the most how developers use OpenCL. Let’s just hope that implementations come soon!

Older posts «