See for example this thread from last month: http://forums.nvidia.com/lofiversion/index.php?t181562.html More search in the forum should give you more answers, as I assume this is a faq.
On Fri, Oct 29, 2010 at 8:11 PM, Julien Cornebise <julien.corneb...@gmail.com> wrote: >> "In the more expensive "Tesla" configurations, the chip features optional >> ECC protection on the memory, and can perform one double-precision floating- >> point operation per cycle per core; the consumer GeForce cards are >> artificially driver restricted to one DP operation per four cycles. " >> >> So, if I want double-precision float performance, what are my choices? > > I never benchmarked Tesla vs GTX, however you're not looking into the > same price range *at all* (think ten-fold increase). > You may find more specific answers on the nvidia forums dedicated to > CUDA, as this list is more targetted to the specific software toolbox > pyCuda. > http://forums.nvidia.com/ > > Best, > > Julien Cornebise > _______________________________________________ PyCUDA mailing list PyCUDA@tiker.net http://lists.tiker.net/listinfo/pycuda