On Tue, 28 Jun 2011 10:45:06 +0200, Patric Holmvall <[email protected]> wrote: > Hi, > I have a problem that only occurs on nVidia platforms. I have managed to > trace the problem to a certain piece of my code, i.e. the calling of two > functions. The code works under all circumstances on my ATI card, and fails > at the same time/place on two nVidia cards. The error arises during the > build of the kernel. The strange thing is, that when I greatly reduce the > amount of calculations in the functions (less terms in the return statement > - see code below), it might work some times. If i reduce the calculations > slightly but reduce other calculations outside the two functions, it might > work too. > > Worthy to note is that the code worked when the elements that the functions > operate on are private memory. The error started to occur when I implemented > work groups and made the elements that it operates on to local (this still > works on ATI). > > I tried updating drivers, and have tried both 2011.1beta3 and 2011.1.1, but > the error still occurs.
Looks like an Nv bug. Not sure there's anything we can do from the PyOpenCL side. Andreas
pgpNz2vkdqxbp.pgp
Description: PGP signature
_______________________________________________ PyOpenCL mailing list [email protected] http://lists.tiker.net/listinfo/pyopencl
