add-memberalign-toparrow-leftarrow-rightbellblockcalendarcamerachatchevron-leftchevron-rightchevron-small-downchevron-upcircle-with-crosscomposecrossfacebookflagfolderglobegoogleimagesinstagramkeylocation-pinmedalmoremuplabelShape 3 + Rectangle 1pagepersonpluspollsImported LayersImported LayersImported LayersshieldstartwitterwinbackClosewinbackCompletewinbackDiscountyahoo

Python on an NVIDIA GPU

Presented by Mark Ebersole, a trainer at NVIDIA.

For most of the existence of Python, the idea of running actual performance optimized or production code natively in Python has been un-heard of. That is until Continuum Analytics introduced their Anaconda Accelerate product. Not only does it allow one to achieve speeds close to, if not equal to, native C/C++/Fortran while staying in Python; it allows you to fully utilize the awesome massively parallel power of an NVIDIA GPU using CUDA Python. This talk will briefly cover how the Accelerate product allows you to run performant code from Python on the CPU. We'll then touch on the "Why?" of GPU Computing, and dig into you can use the Accelerate software stack to program for an NVIDIA GPU in Python either directly with CUDA Python, or letting the Python SW do the parallelization for you.

Hope you can make it!




Join or login to comment.

  • Mark E.

    All, thanks again for attending my presentation on Python and GPUs. I'm in the process of working on a more hands-on workshop, and will let everyone know when it's ready and planned.

    I'd appreciate it if anyone who attended my talk could fill out this quick survey:

    Thanks again!

    June 3, 2013

  • James C.

    Thanks for the presentation Mark, really cool stuff! Hopefully there's a follow up session with some python programming?

    May 31, 2013

    • Mark E.

      That's the plan! I'll work with Monte on a good date for a hands-on session. It'll be a bring-your-own-computer type of session and we'll use Amazon GPU instances as our compute units.

      May 31, 2013

  • Elchin

    Great, exciting stuff. I would like to learn more how program and compile gpu parallel fortran and python codes.

    May 31, 2013

  • Larry R.

    Great presentation, thanks Mark. (I would be interested in a subsequent session that focused on programming.)

    May 30, 2013

  • john r.

    Very good. Very interesting

    1 · May 30, 2013

  • Mark E.

    Looking forward to presenting tomorrow! Let me know if you have any questions before the talk.

    May 29, 2013

  • Neal M.

    Working map link for TLC, the telecom center:

    May 28, 2013

  • Larry R.

    Location check for this? I thought we lost Koelbel S110 for the summer.

    May 24, 2013

    • Monte L.

      Thanks for the reminder, Larry. I've updated the location.

      May 28, 2013

Our Sponsors

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