[mpich-discuss] Time distribution of Intel MPI Benchmark (PingPong)

[Klaus Philip]

Hi,
I tested mpich2 3.1.1 with the Intel MPI Benchmark, more precisely the  "PingPong"-Benchmark.
It uses the MPI_Send and MPI_Recv function to send one message from Process 1 to Process 2 and back.
While the benchmark was running, I executed the Sysprofiler (sysprof) to check the time distribution (Picture below).

My question is now, if the two marked Processes (MPID_nem_lmt_shm_progress and poll) are parts of MPICH or the Intel-PingPong-Benchmark, because they are both consuming much time (49,03% and 19,99%).

[cid:image001.jpg at 01CF9547.D1869AF0]
Greetings,
Philip
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20140701/82a87b37/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.jpg
Type: image/jpeg
Size: 44398 bytes
Desc: image001.jpg
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20140701/82a87b37/attachment.jpg>