Hopefully these are easier to understand. The suggested application
for -pinoffset is covered in the new mdrun performance section
of the user guide, on release-5-0 branch.
Change-Id: I7bc6172a70c39c02f6ca6db17e26b08d2ca3b444
{ "-ntomp_pme", FALSE, etINT, {&hw_opt.nthreads_omp_pme},
"Number of OpenMP threads per MPI rank to start (0 is -ntomp)" },
{ "-pin", FALSE, etENUM, {thread_aff_opt},
{ "-ntomp_pme", FALSE, etINT, {&hw_opt.nthreads_omp_pme},
"Number of OpenMP threads per MPI rank to start (0 is -ntomp)" },
{ "-pin", FALSE, etENUM, {thread_aff_opt},
- "Set thread affinities" },
+ "Whether mdrun should try to set thread affinities" },
{ "-pinoffset", FALSE, etINT, {&hw_opt.core_pinning_offset},
{ "-pinoffset", FALSE, etINT, {&hw_opt.core_pinning_offset},
- "The starting logical core number for pinning to cores; used to avoid pinning threads from different mdrun instances to the same core" },
+ "The lowest logical core number to which mdrun should pin the first thread" },
{ "-pinstride", FALSE, etINT, {&hw_opt.core_pinning_stride},
"Pinning distance in logical cores for threads, use 0 to minimize the number of threads per physical core" },
{ "-gpu_id", FALSE, etSTR, {&hw_opt.gpu_opt.gpu_id},
{ "-pinstride", FALSE, etINT, {&hw_opt.core_pinning_stride},
"Pinning distance in logical cores for threads, use 0 to minimize the number of threads per physical core" },
{ "-gpu_id", FALSE, etSTR, {&hw_opt.gpu_opt.gpu_id},