On Wed, 10 Nov 2010 23:06:30 -0000, "Daniel White" <twinbe...@skytopia.com> wrote: > Hi Andreas, > > > I'm not meaning to tell you that you should use CL, I'm just trying to > > make sure you base your decision on accurate information. > > [...] > > > MS have released a GPGPU language, it's called DirectCompute, and mainly > > for use with DirectX in games. (Were they planning on releasing another > > one?) > > Remind me next time I research A vs B vs C... that I use Google's > new "Past year/month" filter :) Thanks for the heads up. I'll > at least consider OpenCL now. I heard horror stories of > 10x slower, but I probably need a larger sample size ;) > > Actually, just one thing I'd like clarified: > > Maybe it doesn't matter that I can't really redistribute > nvcc with my program, because using PyCUDA, I can utilize > run-time generated code anyway.
Yes, but in that case you have to generate PTX. PyCUDA's run-time code generation facility uses nvcc behind the scenes. Andreas
pgpJReL4w2oND.pgp
Description: PGP signature
_______________________________________________ PyCUDA mailing list PyCUDA@tiker.net http://lists.tiker.net/listinfo/pycuda