Lionel London (CRA) – GPU Computing in Matlab
- Matlab Parallel Computing Toolbox (PCT) vs. Jacket
- PCT allows for multi-cpu and GPU computing. Limited to 12 cores on the local machine. Very high level.
- GPU computing with PCT requires an nVidia card with v1.3 compute capabilities. GPGPU with Jacket has relaxed requirements but is very expensive ($4k for 5 licenses!)
- PCT GPU can run external .cu files.
- Jacket has 10x more CUDA-enabled functions than Matlab. It’s cluster capable.
2 thoughts on “GPU Meeting (04 Oct 2011)”
I’m one of the AccelerEyes developers — and a GT alumnus!
Glad you got to dig into Jacket some. Here’s some clarifications on the above:
Georgia Tech has a site license (managed through http://software.oit.gatech.edu) — so you guys get free access.
Where you’re quoting the “get 20% off” price, keep in mind that academic is significantly less than commercial. Academic would be about $1400 for five base licenses (compared to $3996).
Hi James, thanks for the clarification! I’ll have to pass the news on to the rest of the group.