Open MPI User's Mailing List Archives

Subject: [OMPI users] coll_tuned_decision_fixed.c
From: Andy Georgi (Andy.Georgi_at_[hidden])
Date: 2008-04-24 01:41:35

• Next message: Ingo Josopait: "Re: [OMPI users] Busy waiting [was Re: (no subject)]"
• Previous message: George Bosilca: "Re: [OMPI users] Problem compiling open MPI on cygwin on windows"

Dear all,

to explain the behavior of MPI_Reduce on our cluster i ran through the
source of Open MPI 1.2.6. On line 357 i found a mistake (maybe ;-)). It
should be:

return ompi_coll_tuned_reduce_intra_binary(sendbuf, recvbuf, count,
datatype, op, root, comm, segsize);

instead of

return ompi_coll_tuned_reduce_intra_pipeline (sendbuf, recvbuf, count,
datatype, op, root, comm, segsize);

There are 2 indications:
- the next branch is doing the same (32K pipelining)
- the comment /* Binary_32K */ sounds not like "pipeline" ;-)

Maybe someone is interested in.

Regards,

Andy

-- 
Dresden University of Technology
Center for Information Services
and High Performance Computing (ZIH)
D-01062 Dresden
Germany
Phone:    (+49) 351/463-38783
Fax:      (+49) 351/463-38245
e-mail: Andy.Georgi_at_[hidden]
WWW:    http://www.tu-dresden.de/zih

• Next message: Ingo Josopait: "Re: [OMPI users] Busy waiting [was Re: (no subject)]"
• Previous message: George Bosilca: "Re: [OMPI users] Problem compiling open MPI on cygwin on windows"