OpenCL™ Programming Webinar Series

Home | Register | Log In

OpenCL Programming Webinar Series

> > > > OpenCL™ Programming Webinar Series

Parallel computing is being taken to the next level by leveraging the GPU for general computing tasks. AMD is fully behind this heterogeneous computing revolution with our hardware, software tools & libraries, and support of open standards. Get trained by OpenCL™ and heterogeneous compute experts on the latest technology advances, standards, and best practices for heterogeneous compute.

Stay tuned on upcoming webinar topics through the AMD Developer Central Newsletter.

View previously recorded webinars

New Live Webinar Topics – Register Today!

Webinar Topics	Registration Links by Region/Date/Time
Advanced OpenCL Debugging using AMD gDEBugger This webinar will cover profiling OpenCL with CodeAnalyst. We will start with an overview of the features, types of analysis performed and include an example.	May 9, 2012 9AM PDT
Heterogenous Compute Features of AMD CodeAnalyst Performance Analyzer Developing robust parallel computing applications is difficult. In this talk we will introduce the audience to gDEBugger, an OpenCL kernel source code debugger. We will display advanced debugging techniques that help locate hard to find OpenCL related bugs.	May 22, 2012 11AM PDT

Previously Recorded Webinars:

Webinar Topics	Videos and Presentations
Coordinating OpenCL Computations on one or more Heterogeneous Devices, presented by guest speaker Rob Farber (3 of 3) This webinar continues the discussion of the nine article OpenCL Portable Parallelism series by Rob Farber on The Code Project. Articles 4, 5, and 8 will be discussed demonstrating how to concisely utilize multiple command queues and to coordinate tasks across multiple heterogeneous devices such as the two GPU + CPU configuration used in the articles. Complete working code samples will be discussed including a massively parallel random number test framework. In combination with a strong scaling execution model, the ability to choreograph asynchronous data movement and overlapped computations on multiple devices makes OpenCL a powerful development tool to consider to incorporate scalable portable parallelism into your applications.	View Video
Accelerate Rendering by an Order of Magnitude with OpenCL plus a View to the Multi-core and Web-enabled Future, presented by guest speaker Rob Farber. (2 of 3) This webinar concludes the discussion of the nine article OpenCL Portable Parallelism series by Rob Farber on the Code Project. Articles 6, 7, and 9 will demonstrate how to use OpenCL to provide high-quality, fast rendering in combination with primitive restart, a new feature added to the OpenGL 3.1 standard. As CPUs add ever more cores, device fission lets OpenCL programmers partition the hardware capability to achieve the best resource usage. Concluding thoughts will include a discussion of webcl, which allows the use of OpenCL inside a web browser.	View Video
Introducing OpenCL Portable Parallelism presented by guest speaker, Rob Farber (1 of 3) This webinar will introduce the nine article OpenCL Portable Parallelism series by Rob Farber on The Code Project. Articles 1, 2 and 3 will be discussed including (1) C and C++ APIs for OpenCL plus building and running applications (2) OpenCL memory spaces and (3) the OpenCL execution model. Complete code examples from each article will be discussed to help get started with OpenCL. In particular, the importance of the OpenCL strong scaling execution model will be highlighted along with other reasons to consider OpenCL for your application development.	View Video
Write Once Run Anywhere This presentation shows how Aparapi, an API for expressing data parallel workloads in Java, can extend Java's promise of 'Write Once, Run Anywhere' to include GPU devices. Existing Java OpenCL bindings require developers to code data parallel algorithms in OpenCL, provide explicit buffer transfers and execution requests at runtime, and if OpenCL were unavailable, code a separate Java implementation and have an appropriate fallback strategy. Aparapi allows developers to code against a simple Java data parallel API. At runtime Aparapi attempts to execute on the GPU by converting bytecode to OpenCL; if OpenCL is unavailable Aparapi will fall back to executing using a Java thread pool. We contrast Aparapi with other OpenCL Java bindings, describe how it works, and walk through some real world examples. We also discuss how to determine whether Aparapi is a viable option for your application.	View Video
Taming GPU Compute with C++ AMP Developers today inject parallelism into their compute-intensive applications in order to take advantage of multi-core CPU hardware. Beyond CPUs, however, compute accelerators such as general-purpose GPUs can provide orders of magnitude speed-ups for data parallel algorithms. How can you as a C++ developer fully utilize this heterogeneous hardware from your Visual Studio environment? How can you benefit from this tremendous performance boost in your Visual C++ solutions without sacrificing developer productivity? The answers will be presented in this session about C++ Accelerated Massive Parallelism.	View Video Slide Deck
Advanced OpenCL™ Debugging using gDEBugger by Yaki Tebeka, AMD Fellow Developing robust parallel computing applications is difficult. In this talk we will introduce the audience to gDEBugger, an OpenCL kernel source code debugger, integrated into Visual Studio™. We will display advanced debugging techniques that help locate hard-to-find OpenCL related bugs. Join Yaki Tebeka, an AMD Fellow, responsible for AMD’s developer tools, for this live webinar. Yaki brings over 13 years of experience in software, focusing on 3D graphics, heterogeneous computing and developer tools.	View Video
Introduction to Parallel and Heterogeneous Computing (1 hour) Learn how heterogeneous computing fits into the parallel computing paradigm, what problems it solves and what opportunities it presents.	Video Slide Deck
Introduction to OpenCL (1 hour) Learn about the benefits of OpenCL, the anatomy and architecture of OpenCL and the tools and drivers available.	Video Slide Deck
GPU Architecture Overview (1 hour) Learn about the modern GPU architectures and place the devices in context of the CPU technologies available today. Get specific insight into the latest AMD hardware including the 5000 and 6000 series GPUs and how this design affects software implementation.	Video Slide Deck
OpenCL Programming in Detail (1.5 hours) Learn about OpenCL application execution, resource setup, kernel programming and compiling, program execution, memory objects and synchronization. This webinar will also get into OpenCL C Language including restrictions, data types, type casting and conversions, qualifiers, and built-in functions in the context of an N-Body example.	Video Slide Deck
Real World Application in OpenCL (1 hour) Walk through the creation of a video processing application developed by one of our engineers and get a sense of what you might be able to do with OpenCL in your own applications.	Video Slide Deck
Device Fission Extensions for OpenCL (1 hour) Learn about the unique advantage that OpenCL has when it comes to Fission extensions.	Video Slide Deck
Smoothed Particle Hydrodynamics (1 hour) This webinar describes a project in computational fluid dynamics targeted for videogame applications. The Smoothed Particle Hydrodynamics (SPH) algorithm is a particle method for simulating viscous fluids like water, syrup and air. It is based on solving the incompressible Navier-Stokes equations of fluid mechanics using a particle formulation. This webinar shows you how to build an SPH simulation in OpenCL and discusses design tradeoffs. Source code for the simulation is available.	Video Slide Deck Download the source code (.rar)
Optimizing a Convolution Algorithm (1 hour) Learn about Debugging OpenCL, performance measurements, general optimization tips and walk through optimizing a convolution algorithm.	Video Slide Deck

OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission by Khronos.