Intel® MPI Library Developer Reference for Windows* OS

ID 768734
Date 6/24/2024
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Autotuning

If an application spends significant time in MPI collective operations, tuning might improve its performance.

Tuning is very dependent on the specifications of the particular platform. Autotuner searches for the best possible implementation of a collective operation during application runtime. Each collective operation has its own presets, which consist of the algorithm and its parameters, that the autotuning function goes through and then evaluates the performance of each one. Once autotuning has evaluated the search space, it chooses the fastest implementation and uses it for the rest of the application runtime, and this improves application performance. The autotuner search space can be modified by the I_MPI_ADJUST_<opname>_LIST variable (see I_MPI_ADJUST Family Environment Variables).

Autotuner determines the tuning parameters and makes them available for autotuning using I_MPI_TUNING_MODE and the I_MPI_TUNING_AUTO family environment variables to find the best settings (see Tuning Environment Variables and I_MPI_TUNING_AUTO Family Environment Variables).

NOTE:
I_MPI_TUNING_MODE and the I_MPI_TUNING_AUTO family environment variables support only Intel processors, and cannot be used on other platforms.

The collectives currently available for autotuning are: MPI_Allreduce, MPI_Bcast, MPI_Barrier, MPI_Reduce, MPI_Gather, MPI_Scatter, MPI_Alltoall, MPI_Allgatherv, MPI_Reduce_scatter, MPI_Reduce_scatter_block, MPI_Scan, MPI_Exscan, MPI_Iallreduce, MPI_Ibcast, MPI_Ibarrier, MPI_Ireduce, MPI_Igather, MPI_Iscatter, MPI_Ialltoall, MPI_Iallgatherv, MPI_Ireduce_scatter, MPI_Ireduce_scatter_block, MPI_Iscan, and MPI_Iexscan.

Using autotuner involves these steps:

  1. Launch the application with autotuner enabled and specify the dump file that stores results:

    I_MPI_TUNING_MODE=auto

    I_MPI_TUNING_BIN_DUMP=tuning-results.dat

  2. Launch the application with the tuning results generated at the previous step:

    I_MPI_TUNING_BIN=./tuning-results.dat

    Or use the -tune Hydra option.

If you experience performance issues, see I_MPI_TUNING_AUTO Family Environment Variables.

Examples

  • > export I_MPI_TUNING_MODE=auto
    > export I_MPI_TUNING_AUTO_SYNC=1
    > export I_MPI_TUNING_AUTO_ITER_NUM=5
    > export I_MPI_TUNING_BIN_DUMP=tuning_results.dat
    > mpirun -n 128 -ppn 64 IMB-MPI1 allreduce -iter 1000,800 -time 4800
  • > export I_MPI_TUNING_BIN=./tuning_results.dat
     > mpirun -n 128 -ppn 64 IMB-MPI1 allreduce -iter 1000,800 -time 4800
NOTE:
To tune collectives on a communicator identified with the help of Application Performance Snapshot (APS), execute the following variable at step 1: I_MPI_TUNING_AUTO_COMM_LIST=comm_id_1, … , comm_id_n.