As you noticed the ID of the algorithms are not in any header file, so installing the devel-headers will not help with this particular issue. Hiding the ID of the algorithms has been done in purpose, to prevent people fiddling with one of the most critical pieces in the collective performance (the dynamic rules).
The only way to know the number of supported algorithms and their ID is to read the output of the "ompi_info --param coll tuned" once the "coll_tuned_use_dynamic_rules = 1" has been added to your .openmpi/mca-config.param file. George. On Apr 5, 2013, at 15:11 , Ralph Castain <r...@open-mpi.org> wrote: > You can get the headers installed by adding --with-devel-headers to the > configure line. > > On Apr 5, 2013, at 5:10 AM, chandan basu <cb...@nsc.liu.se> wrote: > >> Hi, >> >> I want to use OpenMPI dynamic collective algorithm selection using rules >> file, e.g. >> >> mpirun --mca coll_tuned_use_dynamic_rules 1 >> --mca_coll_tuned_dynamic_rules_file rules.txt ./myexe >> >> I can see some examples in earlier discussions (given below). My question is >> how do I know the ID for the different collectives. I do not see >> coll_tuned.h in the installation folder . Is there any command to find the >> ID of an algorithm. I am particularly interested in Alltoallv. I have >> checked that coll_tuned_alltoallv_algorithm 1 and >> coll_tuned_alltoallv_algorithm 2 has lot of performance difference depending >> on data size and comm size. So I think giving a rules file can improve the >> performance over a range of data sizes and comm size. Any help in this >> regard will be appreciated. >> >> With regards, >> >> -Chandan >> ---------------------------------------- >> Dr. Chandan Basu >> National Supercomputer Center >> Linköping University >> S-581 83 Linköping >> email: cb...@nsc.liu.se >> ----------------------------------------- >> >1 # num of collectives >> >3 # ID = 3 Alltoall collective (ID in coll_tuned.h) >> >2 # number of com sizes >> >1 # comm size 1 >> >1 # number of msg sizes 1 >> >0 1 0 0 # for message size 0, linear 1, topo 0, 0 segmentation >> >8 # comm size 8 >> >4 # number of msg sizes >> >0 1 0 0 # for message size 0, linear 1, topo 0, 0 segmentation >> >32768 2 0 0 # 32k, pairwise 2, no topo or segmentation >> >262144 1 0 0 # 256k, use linear 1, no topo or segmentation >> >524288 2 0 0 # message size 512k+, pairwise 2, topo 0, 0 segmentation >> ># end of first collective >> >> >> -- >> >> _______________________________________________ >> users mailing list >> us...@open-mpi.org >> http://www.open-mpi.org/mailman/listinfo.cgi/users > > _______________________________________________ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users
