addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupsimageimagesinstagramlinklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1outlookpersonJoin Group on CardStartprice-ribbonImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruseryahoo

GTC and AFDS Recap + WebCL

Come for Table discussions, Member Self-Intro, What's New, Application Showcase, and Advanced Application Development Techniques! Exchange ideas, meet experts, share code... all HPC & GPU, all practical, all cutting-edge.

 

Agenda:

General Discussions:

6:15-6:30pm What’s new in HPC & GPU Supercomputing

6:30-6:45pm Member self-intros: 30 seconds for each member

 

Main Program:

7:45-7:40pm GTC and AFDS Recap and Discussions

7:40-8:30pm Graphics programming on the web with WebCL (Mikael Bourges-Sevenier, Motorola Mobility)

 

Refreshments sponsored by PathScale, High Performance Compilers.

 

Title: Graphics programming on the web with WebCL.

Abstract:
In this presentation, we will introduce WebCL, a new international standard under development by Khronos Group. WebCL is a JavaScript API over OpenCL designed to run on web browsers. We will review key similarities and differences between the two APIs and we will detail how WebGL shaders can be converted to WebCL for improved performance.

About the Presenter:
Mikael Bourges-Sevenier is a Software Architect on Advanced Projects at Motorola Mobility. He is also co-editor of WebCL specification. His interests include multi-media processing and rendering on heterogeneous (mobile) devices.

 


Join or login to comment.

  • Chris J.

    Speculation over vendor strategy dominated conversation during the GTC and AFDS Recap. This is interesting as it may reflect wider changes in technology markets and culture. An amusing anecdote is that David Perry of Gaikai gave keynotes at both GTC and AFDS12 - Nvidia did not know! Awesome. The WebCL presentation by Mikael Bourges-Sevenier of Moto was very good. He gave a live demo and even ran off script when challenged by an audience question.

    June 19, 2012

  • Krishna K.

    We want to convert an existing CPU-based image-manipulation C++ set of algorithms into CPU+GPGPU algorithms for high speed. Our current algo has a lot of loops. The main core of the algo uses Gaussian elimination recursive algo to solve a sparse matrix of size 50,000 x 50,000. Since matrix is sparse, diagonal elements are present. The current implementation takes 20 - 200 seconds depending on size of image. How do we improve performance by orders of magnitude? Contact:[masked]

    June 18, 2012

32 went

Our Sponsors

  • NVIDIA

    Ongoing; Host for 2015 Meetups

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy