Back in December 2011 we reported on an early developer version of the newly started CUDA/Ada project, and now a mere 2 months later the codelabs.ch guys have officially released version 0.1 of the CUDA/Ada binding to Nvidia’s CUDA platform:
CUDA/Ada is an Ada binding to NVIDIA’s CUDA parallel computing platform and programming model. This project was developed during the course of the master seminar “Program Analysis and Transformation” at the University of Applied Sciences Rapperswil.
There’s a nice benchmark chart on the website, which really shows of the power of CUDA/Ada, and there’s also an interesting paper (PDF) available with lots of information about the project.
You can download the latest version here and you can read the release announcement here.
If you’re into parallel computing, then you might’ve heard about Nvidia’s CUDA platform:
CUDA™ is a parallel computing platform and programming model invented by NVIDIA. It enables dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU).
With a new binding from codelabs.ch you can utilize CUDA using your favorite programming language: Ada. The binding is called CUDA/Ada, and it does just what the name implies:
CUDA/Ada is an Ada binding to NVIDIA’s CUDA parallel computing platform and programming model.
At the time of writing there’s no official release of CUDA/Ada, so you’re going to have to rely on the developer version. There’s a neat little usage example on the project page, so be sure to go check it out. Obviously you need a CUDA aware GPU for this binding to work.