- Email: email@example.com
- Registered on:
- Last connection: 06/21/2017
- 11:01 PM GROMACS Bug #2197: Regression (mdrun segfault) after 1ecd43b0034
- You might also want to attach the log file so that we see compiler version, SIMD instructions, and number of threads.
- 10:09 PM Support Platforms Task #1309: Jenkins verification improvements
- It seems that at least for Matrix_PreSubmit we don't have any cmake warnings. I enabled the parser. Test build is her...
- 04:04 PM GROMACS Revision 251611ad: Remove TMPI_ATOMICS from config.h
- TMPI_ATOMICS isn't needed in config.h because
thread_mpi/atomic.h can always be included
and it sets TMPI_ATOMICS bas...
- 09:42 PM GROMACS Bug #1850: data race in gmx_parallel_3dfft_init
- I don't think anything changed about libgomp. Its configure still takes the --disable-linux-futex option. And the gcc...
- 07:13 PM GROMACS Bug #1850: data race in gmx_parallel_3dfft_init
- You build the LLVM OpenMP Runtime with LIBOMP_TSAN_SUPPORT? Which version of the runtime did you use? 3.9, 4.0 or mas...
- 07:07 PM GROMACS Bug #1850: data race in gmx_parallel_3dfft_init
- You never needed no-futex for TSAN. It is a work-around to avoid most false positives with OpenMP. Thus it isn't surp...
- 12:12 AM GROMACS Revision 3ce63cd0: Remove static-intel from default flags
- Isn't guranteed to work with shared libraries. Also inconsistent
with other libraries, which default to shared librar...
- 02:49 AM GROMACS Bug #2177 (Closed): tip4p_continue fails with -ntomp 8 -nt 8
- In the past we always supported running test up to 8 (MPI/OpenMP) of each and all other tests still pass. tip4p_conti...
- 10:08 PM GROMACS Bug #1850: data race in gmx_parallel_3dfft_init
- I quickly asked on their list how these two options compare: https://groups.google.com/forum/#!topic/archer-pruner/Ff...
- 09:37 PM GROMACS Bug #1850: data race in gmx_parallel_3dfft_init
- We used a build of libgomp with -disable-linux-futex for this, correct? But this is somewhat of a hack: https://gcc.g...
Also available in: Atom