On Mon, 2020-04-06 at 10:02 -0400, Dong-In Kang via users wrote: > > Thank you Edgar for the information. > > I also tried MPI_File_write_at_all(), but it usually makes the > performance worse. > My program is very simple. > Each MPI process writes a consecutive portion of a file. > No interleaving among the MPI processes. > I think in this case I can use MPI_File_write_at(). > > FWIW, what I do is have each process write its data to node 0 (my term, I think MPI term is rank 0), and that program does nothing but collect those messages (using prompts to get them in order without filling all the buffer space) and write to the file. I have not timed this vs other methods, but might be worth a try. George Reeke
- [OMPI users] Slow collective MPI File IO Dong-In Kang via users
- Re: [OMPI users] Slow collective MPI Fi... Gabriel, Edgar via users
- Re: [OMPI users] Slow collective MP... Dong-In Kang via users
- Re: [OMPI users] Slow collectiv... Collin Strassburger via users
- Re: [OMPI users] Slow colle... Dong-In Kang via users
- Re: [OMPI users] Slow ... Gabriel, Edgar via users
- Re: [OMPI users] S... Dong-In Kang via users
- Re: [OMPI user... Gilles Gouaillardet via users
- Re: [OMPI user... Dong-In Kang via users
- Re: [OMPI users] Slow collectiv... George Reeke via users
- Re: [OMPI users] Slow collective MPI Fi... Gilles GOUAILLARDET via users
- Re: [OMPI users] Slow collective MP... Collin Strassburger via users
- Re: [OMPI users] Slow collectiv... Benson Muite via users