This is my first blog about my journey into programming; specifically GPU programming. I am a mechanical engineer and was given a funded project to use GPU programming a little over a year ago. Since then, I have had to learn C++, what an IDE was, and how to program in Windows. For all you linux lovers out there... I am seeing a light but more on that later.
Programming is fun. Programming is frustrating. Programming is easy. Programming is hard. GPU programming is even harder. But nothing is fun that is not challenging and a little frustrating at times.
Now I am under some serious pressure to start exploiting the GPU in my research. Having learned enough C++ I am now trying to use graphics concepts and parallel programming via nVIDIA's CUDA (Complete Unified Device Architecture) to accelerate my programs.
So, I am using a laptop with a nVIDIA quadro 2800M to program with. At first I could not get the drivers to install but after a driver hack by a helpful nVIDIA staff member I am up and running. Actually, I had to have the hack to install drivers that supported OpenCL but was not successful in getting them to run... so I am going to stick to CUDA for now and port the code later. The programming architecture and concepts are very similar for both CUDA and OpenCL so it shouldn't be in issue.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment