[gmx-developers] NVIDIA misrepresenting simulation package performance
David van der Spoel
spoel at xray.bmc.uu.se
Tue May 24 08:47:44 CEST 2016
my attention was brought to this page by a colleague:
Here, NVIDIA gives the relative performance of different codes on their
GPUs. As we know, GROMACS is very efficient on CPUs and therefore the
scale-up is not as impressive as other codes.
Should we try to have NVIDIA post a fairer picture (ns/day)?
Or debunk it on our own website?
David van der Spoel, Ph.D., Professor of Biology
Dept. of Cell & Molec. Biol., Uppsala University.
Box 596, 75124 Uppsala, Sweden. Phone: +46184714205.
spoel at xray.bmc.uu.se http://folding.bmc.uu.se
More information about the gromacs.org_gmx-developers