TOP 10 MUST-SEE SESSIONS AT THE GPU TECHNOLOGY CONFERENCESeptember 4, 2009
With the GPU Technology Conference less than a month away just down the road in San Jose, I took a look through the sessions catalog today and realized I’m going to have a hard time deciding what to attend.
As a product manager for our GPU Computing technologies and a former software engineer, I’m interested in a wide variety of topics and technologies, so I’ll be spreading my time between sessions on developer tools, programming techniques and research topics.
In addition to the pre-conference tutorial I’m presenting on the first day, there are more than a dozen tutorials and over 100 sessions covering everything from algorithms to visualization.
Looking through the sessions for the Developer Summit and Research Summit, here are my Top 10 so far, in no particular order:
* Reconstructing the Brain: Extracting Neural Circuitry with CUDA and MPI (1075)
I’ve always wanted to know more about how my brain works, and this Harvard researcher is modeling the brain using MPI on a CUDA cluster. Way cool.
* Advances in GPU-based Image Processing and Computer Vision (1020)
The whole idea of software being able to recognize objects and decipher information in the physical world fascinates me.
* Large-Scale Text Mining on the GPU (1025)
I want to learn more about the kinds of database operations benefit from GPU computing.
* Performance Primitives for Video Codec and Image Processing (1028)
Sounds like collection of GPU-optimized Lego blocks that can be used to build tons of different image filters, video codecs, etc. Who doesn’t love Lego?
* You Might Also Like: A Multi-GPU Recommendation System (1034)
Sifting through tons of data to provide me with a personal recommendation for a new book, movie or food I’m likely to enjoy sounds like a good thing. But how do they figure out what I’ll like?
* Mapping Satellite Imagery on the GPU: Fast Orthorectification and Pan-Sharpening (1037)
I want to know how soon they’re going to be able to read my license place from space. This one makes me just a tiny bit anxious but it’s better to face your fears head-on, right?
* NEXUS: A Powerful IDE for GPU Computing on Windows (1023)
This new tool integrates support for GPU debugging & profiling in Visual Studio and is getting rave reviews from the developers participating in the preview program. There’s a hand-on lab (1098) running all day Thursday and Friday, so you can give it a try too.
* OPLib: A GPL Library of Elementary Pricing Functions in CUDA/OpenCL and OpenMP (1005)
I’ve been wanting to learn more about how OpenMP applications can take advantage of the CUDA architecture, and maybe I’ll learn how to make some money in the stock market at the same time. 🙂
* Interactive Ray Tracing with the OptiX Ray Tracing Engine (1048)
I saw some of their amazing demos of interactive ray tracing several months ago, and hear they have even more realistic demos ready for GTC.
* Zombies on Tegra: A Case Study in Mobile Augmented Reality (1069)
This one sounds like a fun session that will raise my expectations for gaming on mobile platforms. Did you know that the Tegra processor is powering the new Zune HD?
* Face Recognition for Photographs and Video (1070)
I’ve been playing with the face recognition features in Picasa web albums, and it’s pretty good most of the time. I wonder how long until my camera can name the people (and places) in my pictures as I take them.
* Driving on Mars: Simulating Tracked Vehicle Operation on Granular Terrain (1106)
Designing semi-autonomous robots for a Mars mission? Count me in!
* Convolution Soup: A Case Study in CUDA Optimization (1401)
When it comes to image processing, Joe is one of the smartest guys I know so I’m sure I’ll learn something new in this session.
* Directing Experiments in the International Space Station with GPU-Assisted Image Analysis (1437)
I’ve always wanted to learn more about the kinds of experiments they do at the international space station. What kinds of experiments can only be done in zero-g anyway?
* Languages, APIs, and Developer Tools for GPU Computing
This is the tutorial I’m presenting, so I can’t miss this one! You shouldn’t either if you want to get your arms around the basics of GPU Computing before attending the more advanced sessions later in the conference.
OK, that’s more than 10, but it’s the best I can do for now. I’ll have to whittle down the list later.
There are also a bunch of interesting companies presenting at the Emerging Companies Summit, but I’ll let you explore that on your own since everyone with a Full Conference Pass or Research Summit Pass can attend these sessions as well. The full sessions catalog is available here.
If you’d like to share your own Top10 GTC sessions or ask questions about the conference, please post them in our developer forums.
Hope to see you in San Jose on Sept. 30!