[HPGMG Forum] HPGMG release v0.1

Vitali A. Morozov morozov at anl.gov
Mon Jun 9 16:05:08 UTC 2014


I see - I am apparently running on a different Cray XC30 with 12 core at 
2.7 GHz and DDR3-1866.

Sorry for confusion.

Vitali

On 06/09/2014 10:59 AM, Sam Williams wrote:
> Preproduction Edison phase I and II evaluated 8 cores @ 2.6GHz and DDR3-1866.  Production Edison (XC30) is 12 cores @ 2.4GHz cores, and the DRAM is DDR3-1666.  This is 460GF/node and about 80-85GB/s of bandwidth (don't recall if we used triad or copy).
>
>
> On Jun 9, 2014, at 8:51 AM, Vitali A. Morozov <morozov at anl.gov> wrote:
>
>> Hello Jed,
>>
>> I am looking at the result page
>>
>> https://hpgmg.org/2014/05/15/fv-results/
>>
>> and see that you provide STREAM-based memory bandwidth for some architectures. I suggest to specify a particular benchmark, let us say "triad", because the result of STREAM is benchmark-dependent.
>>
>> For BG/Q, I have measured 29.3 GB/s/node on "triad". For Cray XC30, I have measured 48.6 GB/s/socket or 97.1 GB/s/node. This is slightly better than the numbers you have reported.
>>
>> For Cray XC30, the flop rate is 518.4 GF per node. For Xeon E5-2697 v2 @ 2.7 GHz, each core can have 8 Flops/cycle - 4 way FMA - or 8 * 2.7 = 21.6 GFlops per core. 12 cores result in 259.2 GFlops per socket, 2 sockets give 518.4 GFlops.
>>
>> Vitali
>>
>>
>>
>>
>> On 06/07/2014 04:27 PM, Jed Brown wrote:
>>> Mark Adams <mfadams at lbl.gov>
>>>   writes:
>>>
>>>> We are please to announce that hpgmg.org and the associated mailing
>>>> list
>>>> hpgmg-forum at hpgmg.org
>>>>   is officially available.
>>>>
>>> Thanks, Mark.  To help kick off the discussion, I would like to call
>>> attention to our recent blog posts describing "results".
>>>
>>> The most recent announces the v0.1 release and includes a Kiviat diagram
>>> comparing the on-node performance characteristics of CORAL apps and
>>> several benchmarks running on Blue Gene/Q.
>>>
>>>    
>>> https://hpgmg.org/2014/06/06/hpgmg-01/
>>>
>>>
>>>
>>> This earlier post shows performance on a variety of top machines:
>>>
>>>    
>>> https://hpgmg.org/2014/05/15/fv-results/
>>>
>>>
>>>
>>> We are interested in better ways to collect and present the comparison
>>> data as well as any characteristics that you think are important.
>>>
>>>
>>> In addition to the general principles on the front page, some further
>>> rationale is given at:
>>>
>>>    
>>> https://hpgmg.org/why/
>>>
>>>
>>> None of this is set in stone and we would be happy to discuss any
>>> questions or comments on this list.
>>>
>>>
>>> Please encourage any interested colleagues to subscribe to this list:
>>>
>>>    
>>> https://hpgmg.org/lists/listinfo/hpgmg-forum
>>>
>>>
>>> _______________________________________________
>>> HPGMG-Forum mailing list
>>>
>>> HPGMG-Forum at hpgmg.org
>>> https://hpgmg.org/lists/listinfo/hpgmg-forum
>> _______________________________________________
>> HPGMG-Forum mailing list
>> HPGMG-Forum at hpgmg.org
>> https://hpgmg.org/lists/listinfo/hpgmg-forum



More information about the HPGMG-Forum mailing list