These were taken using OSU Micro benchmarks 5.3
http://mvapich.cse.ohio-state.edu/benchmarks/
For example, in a cluster with 32 nodes each running 24 processes,
Broadcast for bytes 1 to 64 take around 36 us where as the barrier takes
165 us. These were on 40Gbps Infiniband
# OSU MPI Broadcast Latency Test v5.3
# Size Avg Latency(us)
1 33.23
2 34.36
...
# OSU MPI Barrier Latency Test v5.3
# Avg Latency(us)
165.70
On May 30, 2016 9:10 AM, "Dorier, Matthieu" <mdor...@anl.gov> wrote:
> Hi,
>
> How are you measuring these times?
>
> Thanks,
>
> Matthieu
>
> ------------------------------
> *From:* users [users-boun...@open-mpi.org] on behalf of Saliya Ekanayake [
> esal...@gmail.com]
> *Sent:* Monday, May 30, 2016 7:53 AM
> *To:* Open MPI Users
> *Subject:* [OMPI users] Broadcast faster than barrier
>
> Hi,
>
> I ran Ohio micro benchmarks for openmpi and noticed broadcast with smaller
> number of bytes is faster than a barrier - 2us vs 120us.
>
> I'm trying to understand how this could happen?
>
> Thank you
> Saliya
>
> _______________________________________________
> users mailing list
> us...@open-mpi.org
> Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/users
> Link to this post:
> http://www.open-mpi.org/community/lists/users/2016/05/29324.php
>
