[mpiwg-rma] [EXTERNAL] Re: MPI_WIN_CREATE for intercommunicators
Thomas Jahns
jahns at dkrz.de
Wed Jan 22 15:17:42 CST 2014
Hello,
On Jan 22, 2014, at 19:56 , Jeff Hammond wrote:
> On Wed, Jan 22, 2014 at 12:16 PM, Barrett, Brian W
> <bwbarre at sandia.gov> wrote:
>> On 1/22/14 11:09 AM, "Jeff Hammond" <jeff.science at gmail.com> wrote:
>>
>>> On Wed, Jan 22, 2014 at 11:53 AM, Barrett, Brian W <bwbarre at sandia.gov
>>> >
>>> wrote:
>>>> On 1/22/14 3:41 AM, "Thomas Jahns" <jahns at dkrz.de> wrote:
>>>>
>>>>> Hello Maik,
>>>>>
>>>>> On 01/22/14 10:14, maik peterson wrote:
>>>>>> thomas, today you should start thinking about other possibilities
>>>>>> to solve your problem. this mpi rma stuff is crappy.
>>>>>
>>>>> I guess that very much depends on your kind of machine. We've
>>>>> found it
>>>>> to
>>>>> work
>>>>> very nice with MVAPICH, not so great with PE and OpenMPI.
perhaps I should qualify my very brief original statement before it
becomes more flammable: MVAPICH gave the best out-of-the-box
performance on that particular system (IBM xSeries with FDR IB) and
while OpenMPI (on the same machine) did give the desired performance
improvements with RMA, base-line performance was lower for some yet
undiscovered reason, but system adminstration will look into it. I
have no doubt this could have been different. For PE we asked IBM what
to do differently but have no final answer so far.
Regards, Thomas
--
Thomas Jahns
DKRZ GmbH, Department: Application software
Deutsches Klimarechenzentrum
Bundesstraße 45a
D-20146 Hamburg
Phone: +49-40-460094-151
Fax: +49-40-460094-270
Email: Thomas Jahns <jahns at dkrz.de>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpi-forum.org/pipermail/mpiwg-rma/attachments/20140122/8ece8828/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 2199 bytes
Desc: not available
URL: <http://lists.mpi-forum.org/pipermail/mpiwg-rma/attachments/20140122/8ece8828/attachment-0001.bin>
More information about the mpiwg-rma
mailing list