Re: [gmx-users] parallelization

I see, thank you. On Fri, Mar 2, 2018 at 3:09 PM, Mark Abraham wrote: > Hi, > > No, GROMACS long pre-dates useful implementations of MPI I/O (which anyway > don't suit GROMACS needs), and handles its own MPI reduction and does I/O > from a single rank per simulation. >

Re: [gmx-users] parallelization

Hi, No, GROMACS long pre-dates useful implementations of MPI I/O (which anyway don't suit GROMACS needs), and handles its own MPI reduction and does I/O from a single rank per simulation. Mark On Fri, Mar 2, 2018 at 3:00 PM Amin Rouy wrote: > sorry Justin, I am familiar

Re: [gmx-users] parallelization

On 3/2/18 8:40 AM, Amin Rouy wrote: Hi I am not so familiar with parallelization. Can some one please tell me if Gromacs use MPI-parallel I/O (MPI-IO), or one should do it by himself for his MPI jobs? Everything you need to know is in the manual:

Re: [gmx-users] parallelization of processors on single system/node using MPI

Yes, you can besides the minor command-line interface differences, using MPI and thread-MPI works essentially the same way. http://www.gromacs.org/Documentation/Acceleration_and_parallelization#MPI.2c.c2.a0Thread-MPI -- Szilárd On Thu, Nov 28, 2013 at 11:07 AM, Richa Singh