#2782

GPU Technology Conference 2010

This year’s GPU Technology Conference is in San Jose which is pretty much my part of the World so I thought I’d talk a busman’s holiday in mid-September and check it out.

There’s several pre-conference tutorials on the basics of CUDA, DirectCompute, OpenCL as well as a whole host of other GPU related programming models. I’m planning to attend some of the CUDA ones and maybe a DirectCompute talk. That’s just Day 1.

There’s so many interesting sessions it’s pretty hard to choose. There’s a couple of interesting N-Body related talks, like Gravitational N-body Simulations: How Massive Black Holes Interact with Stellar Systems, which I’ll definitely be attending. Here are a few of the others that stand out…

Supercomputing for the Masses: Killer-Apps, Parallel Mappings, Scalability and Application Lifespan

Hear the latest on how supercomputing for the masses is changing the world. We will look at some of the one- to three-orders of magnitude faster killer apps and see how they do it.

Copperhead: Data-Parallel Python for the GPU

Learn how to write Python programs that execute highly efficiently on GPUs using Copperhead, a data-parallel Python runtime. Using standard Python constructs like map and reduce, we will see how to construct data-parallel computations and embed them in Python.

I’m also really interested to hear about Thrust, an STL like library for GPGPU programming.

I can’t remember the last time I was this excited about a conference. Probably my first Agile conference in 2006.

What else do I hope to see at GTC? Well an announcement of Parallel Nsight for Visual Studio 2010 would be nice too! I’m currently fighting with a very messy build that uses both VS 2010 for the TPL/PPL based bits and VS 2008 for the CUDA builds.