PGI has some very nice CUDA support in the latest version of their fortran compiler. Here’s the article. [www.pgroup.com] This may be old news to some of you, but I’m impressed. Hopefully CUDA support is in the pipeline for the other fortran vendors as well, and something of a standard can emerge from this.
My first impression is that this is an ideal sweet spot, allowing the usage of nice high-level fortran array expressions on the host when convenient, and dropping into CUDA code where speed is a must. Granted the host-device bandwith is painfully slow, so there is a significant overhead, but ideally it would allow incremental speedups, all within fortran.
I’m glad to see Fortran adapting to the latest technology, as it has done every generation or so; brings to mind the quip:
“What language will they be using 30 years from now?”
“I don’t know, but they’ll call it ‘Fortran’.”
And yet the standard is still backwards compatible with code from almost 35 years ago. AFAICT, it’s the combination of adaptibility and backwards compatibility that keeps Fortran around.
Now if they would only get better I/O syntax, named goto labels (not ‘assign 10 to n’, more like C’s goto), etc…