CUDA, should'a, - didn't.

Sorry. Please don't hit me.

Hi Wilgard,
I have not heard of any projects being considered with unusual platforms. Some upcoming projects use Fortran and we have to go looking for people qualified to help us support Fortran. When I started out long ago, I was surprised at the paucity of support for Fortran. Even then, people were trying to get away from it. But it sticks because it is so easy for scientists to learn while concentrating on their research rather than on computer science. This is not a digression. I suspect that most projects will be programmed on old stodgy platforms rather than on the cutting edge. The researchers are not interested in computer science and it will show in their projects.

Lawrence

Wilgard, for features like this to take off, we need a science project that wants to exploit it.

Unfortunately, that's not the way most computational biology seems to work. FORTRAN seems to be the language of choice, and most software has a long history and established codebase. Porting to an entirely new platform is a massive undertaking.

So, we either need a brand new program with developers willing to try targeting a new platform (and for most scientists, trying something like distributed computing is a big leap just by itself), or we need an established program that has the resources to expand to new platforms.

Hello,

Does anybody know if there is a project to create a GPU client fir GRID?

Or can we install the Folding@home gpu client and by any solution totalize points for the GRID team?