[Beowulf] Re: Opteron 275 performance

[Mikhail Kuzminsky]

In message from Joe Landman <landman at scalableinformatics.com> (Thu, 28 
Jul 2005 22:25:35 -0400):
>Hi Philippe:
>
>   I don't have an accurate measurement at this moment.  I have been 
>working on measurement using the performance counters.
>
>   What I did not run, but would like to see is a set of streams 
>numbers 
>per core, for 1,2,3,4 on the system.

I performed like tests: for 2p/4c Opteron 275 w/DDR333, w/Linux 2.4.21
SMP kernel.
The results for different compilers (ifort, pgf77, pathf90) said the 
same: scaling of memory throughput from 1 to 2 cores is much more 
worse,
than for single core Opteron 242; "scaling" from 2 cores to 4 cores
of dual Opteron 275 server gives *decrease* of throughput. It looks
that w/o (NUMA+CPU affinity) the results are bad. 

This results w/some other tests, including computational chemistry
benchmarks will be soon published in russian "Open Systems" journal,
but they will be on russian :-)

Yours
Mikhail
>
>Joe
>
>Philippe Blaise wrote:
>> Hopefully, you show that dual core is quite superior to 
>> "hyper"-threading for some scientific programs,
>> and is cost-friendly, very nice ! but page 14 you write
>> 
>> "It is worth noting that since AMBER8 does consume significant 
>>memory 
>> bandwidth, the
>> memory contention issue that could reduce overall performance on a 
>>AMD 
>> Opteron 275
>> processor based 2p/4c system under heavy memory usage shows a small 
>> effect, at most".
>> 
>> Please, what do you mean by "significant memory bandwith" ? may be 
>>no 
>> more than 50 % ?
>> have you got an estimation value ?
>> 
>> Philippe.
>> 
>> Joe Landman wrote:
>> 
>>> Hi Steve:
>>>
>>>   Not knowing the details of your calculations might be an issue, 
>>>but 
>>> you can read about our experiences with a number of chemistry and 
>>> informatics codes on dual core Opteron systems.  See 
>>> http://enterprise2.amd.com/downloadables/Dual_Core_Performance.pdf 
>>>for 
>>> more details.
>>>
>>> Joe
>>>
>>> Steve Cousins wrote:
>>>
>>>> On Thu, 14 Jul 2005 11:25:12 +0100 Igor Kozin wrote:
>>>>
>>>>
>>>>> But now for 4cores/2CPUs per Opteron node to force the using of
>>>>>
>>>>>> only 2 cores (from 4), by 1 for each chip, we'll need to have
>>>>>> cpu affinity support in Linux.
>>>>>
>>>>>
>>>>>
>>>>> Mikhail,
>>>>> you can use "taskset" for that purpose. For example, (perhaps not in 
>>>>> the most elegant form)
>>>>>        mpiexec  -n 1 taskset -c 0 $code : -n 1 taskset -c 2 $code
>>>>> But I doubt you want to let the idle cores to do something else in 
>>>>> the mean time. However small you will generally see an increase in 
>>>>> performance if you use all the cores.
>>>>
>>>>
>>>>
>>>>
>>>> We are considering getting a Dual Dual-Core Opteron system vs. two 
>>>>Dual
>>>> Opteron systems.  We like the ability to use all four cores on one 
>>>>model
>>>> but a lot of what we'll do is have two models running at the same 
>>>>time,
>>>> each using two cores. We are worried that running two models on one 
>>>> system with four cores (each
>>>> model using two cores) will not work as well as using two systems, 
>>>>each
>>>> with two cores/cpu's.  Is this what you were refering to (Igor) when 
>>>>you
>>>> wrote:
>>>>
>>>>
>>>>> But I doubt you want to let the idle cores to do something else
>>>>> in the mean time. 
>>>>
>>>>
>>>>
>>>>
>>>> We have an 8 CPU SGI Origin 3200 that has no problem doing this sort 
>>>>of
>>>> thing.  I'm just curious what the implications are of doing this 
>>>>with 
>>>> the
>>>> Dual Core Opteron cpu's. Thanks,
>>>>
>>>> Steve 
>>>> ______________________________________________________________________
>>>>  Steve Cousins, Ocean Modeling Group    Email: 
>>>>cousins at umit.maine.edu
>>>>  Marine Sciences, 208 Libby Hall 
>>>>       http://rocky.umeoce.maine.edu
>>>>  Univ. of Maine, Orono, ME 04469        Phone: (207) 581-4302
>>>>
>>>>
>>>>
>>>>
>>>> _______________________________________________
>>>> Beowulf mailing list, Beowulf at beowulf.org
>>>> To change your subscription (digest mode or unsubscribe) visit 
>>>> http://www.beowulf.org/mailman/listinfo/beowulf
>>>
>>>
>>>
>
>-- 
>Joseph Landman, Ph.D
>Founder and CEO
>Scalable Informatics LLC,
>email: landman at scalableinformatics.com
>web  : http://www.scalableinformatics.com
>phone: +1 734 786 8423
>fax  : +1 734 786 8452
>cell : +1 734 612 4615
>
>_______________________________________________
>Beowulf mailing list, Beowulf at beowulf.org
>To change your subscription (digest mode or unsubscribe) visit 
>http://www.beowulf.org/mailman/listinfo/beowulf