- Email: firstname.lastname@example.org
- Registered on: 09/06/2014
- Last connection: 12/19/2017
- 04:38 PM GROMACS Revision 97f9f399: CUDA 9/Volta support for the nonbonded module
- The Volta architecture introduces independent thread scheduling. This
new architectural feature breaks implicit warp ...
- 12:06 PM GROMACS Revision bf4589ee: Updated application clock handling on Pascal+ GPUs
- Starting with Pascal (CC >= 6.0) it is no longer possible to change
application clocks without root privileges. With ...
- 07:50 PM GROMACS Revision 0f541787: Update FindNVML to fix #2061
- Fixes FindNVML to reflect move of the NVML development files from the
GDK to the CUDA Toolkit with CUDA 8.
- 10:17 AM GROMACS Bug #2085: mdrun crashes with segmentation fault if started with more than 32 OpenMP threads.
- Berk Hess wrote:
> I can't reproduce this with GMX_OPENMP_MAX_THREADS=64 on x86.
> Could you run a debugger to see ...
- 11:15 AM GROMACS Bug #2085 (Closed): mdrun crashes with segmentation fault if started with more than 32 OpenMP threads.
- I build GROMACS 2016.1 with CUDA 8 and GCC 5.4.0 using the following configure command:...
- 03:30 PM GROMACS Bug #1991 (Closed): Automatic launch configuration does not work as expected if Hyper Threading is disabled in the Kernel
- When Hyper Threading (HT) is disabled in the Kernel (not BIOS) GROMACS detects that only the physical cores are onlin...
- 10:57 PM GROMACS Bug #1846: NVML management resets GPU application clocks rather than restoring
- Application Clocks is a global setting so the setting will what ever was last set.
- 01:27 PM GROMACS Bug #1846: NVML management resets GPU application clocks rather than restoring
- Sorry for replying late. I will try to clarify some of the discussed questions. As I have some deadlines approaching ...
- 12:22 PM GROMACS Bug #1810: Automatic thread pinning on systems with uncommon core numbering has a very bad effect on performance
- The hardware thread order did not change (see attached files).
- 10:31 AM GROMACS Bug #1810: Automatic thread pinning on systems with uncommon core numbering has a very bad effect on performance
- After the system were this happened was reinstalled the issue could not be reproduced. So I think this can be closed.
Also available in: Atom