b89f8fabc9
The project includes following components and frameworks: - ML Collective component - NETPATTERNS and COMMPATTERNS common components - BCOL framework - SBGP framework Note: By default the ML collective component is disabled. In order to enable new collectives user should bump up the priority of ml component (coll_ml_priority) ============================================= Primary Contributors (in alphabetical order): Ishai Rabinovich (Mellanox) Joshua S. Ladd (ORNL / Mellanox) Manjunath Gorentla Venkata (ORNL) Mike Dubman (Mellanox) Noam Bloch (Mellanox) Pavel (Pasha) Shamis (ORNL / Mellanox) Richard Graham (ORNL / Mellanox) Vasily Filipov (Mellanox) This commit was SVN r27078.
149 строки
4.2 KiB
Plaintext
149 строки
4.2 KiB
Plaintext
##################################
|
|
# ML collective configuration file
|
|
##################################
|
|
# NOTE (by Pasha):
|
|
# Since ML configuration infrastructure is limited on this stage we do not support some tunings, even so parser
|
|
# understands this values and keys, but we do not have place to load all this values.
|
|
# threshold - ML infrastructure does not handle multiple thresholds.
|
|
# fragmentation - ML infrastructure does not fragmentation tuning per collective.
|
|
##################################
|
|
|
|
# Defining collective section
|
|
[BARRIER]
|
|
# Defining message size section. We will support small/large. In future we may add more options. Barrier is very specific case, because it is only collective that does not transfer any data, so for this specific case we use small
|
|
<small>
|
|
# Since ML does not define any algorithm for BARRIER, we just use default. Later we have to introduce some algorithm name for Barrier
|
|
algorithm = ML_BARRIER_DEFAULT
|
|
|
|
# Hierarchy setup:
|
|
#
|
|
# full_hr - means all possible levels of hierarchy (list of possible is defined by user command line)
|
|
# full_hr_no_basesocket - means all possible levels of hierarchy (list of possible is defined by user command line)
|
|
# except the basesocket subgroup.
|
|
# ptp_only - only ptp hierarchy
|
|
# iboffload_only - only iboffload hierarhcy
|
|
hierarchy = full_hr
|
|
|
|
[IBARRIER]
|
|
<small>
|
|
algorithm = ML_BARRIER_DEFAULT
|
|
hierarchy = full_hr
|
|
|
|
[BCAST]
|
|
<small>
|
|
# bcast supports: ML_BCAST_SMALL_DATA_KNOWN, ML_BCAST_SMALL_DATA_UNKNOWN, ML_BCAST_SMALL_DATA_SEQUENTIAL
|
|
algorithm = ML_BCAST_SMALL_DATA_KNOWN
|
|
hierarchy = full_hr
|
|
<large>
|
|
# bcast supports: ML_BCAST_LARGE_DATA_KNOWN, ML_BCAST_LARGE_DATA_UNKNOWN, ML_BCAST_LARGE_DATA_SEQUENTIAL
|
|
algorithm = ML_BCAST_LARGE_DATA_KNOWN
|
|
hierarchy = full_hr
|
|
|
|
[IBCAST]
|
|
<small>
|
|
algorithm = ML_BCAST_SMALL_DATA_KNOWN
|
|
hierarchy = full_hr
|
|
<large>
|
|
algorithm = ML_BCAST_LARGE_DATA_KNOWN
|
|
hierarchy = full_hr
|
|
|
|
[GATHER]
|
|
<small>
|
|
# gather supports: ML_SMALL_DATA_GATHER
|
|
algorithm = ML_SMALL_DATA_GATHER
|
|
hierarchy = full_hr
|
|
<large>
|
|
# gather supports: ML_LARGE_DATA_GATHER
|
|
algorithm = ML_LARGE_DATA_GATHER
|
|
hierarchy = full_hr
|
|
|
|
[IGATHER]
|
|
<small>
|
|
# gather supports: ML_SMALL_DATA_GATHER
|
|
algorithm = ML_SMALL_DATA_GATHER
|
|
hierarchy = full_hr
|
|
<large>
|
|
# gather supports: ML_LARGE_DATA_GATHER
|
|
algorithm = ML_LARGE_DATA_GATHER
|
|
hierarchy = full_hr
|
|
|
|
[ALLGATHER]
|
|
<small>
|
|
# allgather supports: ML_SMALL_DATA_ALLGATHER
|
|
algorithm = ML_SMALL_DATA_ALLGATHER
|
|
hierarchy = full_hr
|
|
<large>
|
|
# allgather supports: ML_LARGE_DATA_ALLGATHER
|
|
algorithm = ML_LARGE_DATA_ALLGATHER
|
|
hierarchy = full_hr
|
|
|
|
[IALLGATHER]
|
|
<small>
|
|
# allgather supports: ML_SMALL_DATA_ALLGATHER
|
|
algorithm = ML_SMALL_DATA_ALLGATHER
|
|
hierarchy = full_hr
|
|
<large>
|
|
# allgather supports: ML_LARGE_DATA_ALLGATHER
|
|
algorithm = ML_LARGE_DATA_ALLGATHER
|
|
hierarchy = full_hr
|
|
|
|
[ALLTOALL]
|
|
<small>
|
|
# alltoall supports: ML_SMALL_DATA_ALLTOALL
|
|
algorithm = ML_SMALL_DATA_ALLTOALL
|
|
hierarchy = ptp_only
|
|
<large>
|
|
# alltoall supports: ML_LARGE_DATA_ALLTOALL
|
|
algorithm = ML_LARGE_DATA_ALLTOALL
|
|
hierarchy = ptp_only
|
|
|
|
[IALLTOALL]
|
|
<small>
|
|
# alltoall supports: ML_SMALL_DATA_ALLTOALL
|
|
algorithm = ML_SMALL_DATA_ALLTOALL
|
|
hierarchy = ptp_only
|
|
<large>
|
|
# alltoall supports: ML_LARGE_DATA_ALLTOALL
|
|
algorithm = ML_LARGE_DATA_ALLTOALL
|
|
hierarchy = ptp_only
|
|
|
|
[ALLREDUCE]
|
|
<small>
|
|
# allreduce supports: ML_SMALL_DATA_ALLREDUCE
|
|
algorithm = ML_SMALL_DATA_ALLREDUCE
|
|
hierarchy = full_hr
|
|
<large>
|
|
# allreduce supports: ML_LARGE_DATA_ALLREDUCE
|
|
algorithm = ML_LARGE_DATA_ALLREDUCE
|
|
hierarchy = full_hr
|
|
|
|
[IALLREDUCE]
|
|
<small>
|
|
# allreduce supports: ML_SMALL_DATA_ALLREDUCE
|
|
algorithm = ML_SMALL_DATA_ALLREDUCE
|
|
hierarchy = full_hr
|
|
<large>
|
|
# allreduce supports: ML_LARGE_DATA_ALLREDUCE
|
|
algorithm = ML_LARGE_DATA_ALLREDUCE
|
|
hierarchy = full_hr
|
|
|
|
[SCATTER]
|
|
<small>
|
|
# scatter supports: ML_SCATTER_SMALL_DATA_SEQUENTIAL
|
|
algorithm = ML_SCATTER_SMALL_DATA_SEQUENTIAL
|
|
hierarchy = full_hr
|
|
<large>
|
|
# scatter supports: ML_SCATTER_SMALL_DATA_SEQUENTIAL
|
|
algorithm = ML_SCATTER_SMALL_DATA_SEQUENTIAL
|
|
hierarchy = full_hr
|
|
|
|
[ISCATTER]
|
|
<small>
|
|
# scatter supports: ML_SCATTER_SMALL_DATA_SEQUENTIAL
|
|
algorithm = ML_SCATTER_SMALL_DATA_SEQUENTIAL
|
|
hierarchy = full_hr
|
|
<large>
|
|
# scatter supports: ML_SCATTER_SMALL_DATA_SEQUENTIAL
|
|
algorithm = ML_SCATTER_SMALL_DATA_SEQUENTIAL
|
|
hierarchy = full_hr
|