Hi Scott,
thanks for the warning (but I can not afford TeslaC2050 GPUs ).
Fortunately I plan to use the new machine
rather for single GPU jobs however of course I will also try to experiment
with parallel GPU runs but
probably just with 2GPUs per job where the scaling gain is the biggest one
and where the
unstability which you mentioned will be maybe acceptably small. Much more
serious seems to
me in this moment that melting issue and I am really curious about some
additional info from Jodi.
Did you ever experienced any similar problem in some of your multi GPU
system ?
Best wishes,
Marek
Dne Thu, 15 Sep 2011 02:51:33 +0200 Scott Le Grand <varelse2005.gmail.com>
napsal/-a:
> 3 GB GTX 580s rock for single GPU runs (as many as you can do in a single
> system) but are unstable in parallel runs...
>
> On Wed, Sep 14, 2011 at 5:15 PM, Marek Maly <marek.maly.ujep.cz> wrote:
>
>> Hello Jodi,
>>
>> first of all thanks a lot for sharing your experience with "P6T7 WS
>> SuperComputer" + 4 x GPU
>> and providing your benchmarks ! Your benchmark results are nice and as
>> I
>> checked
>> they are very similar to that in Amber web (
>> http://ambermd.org/gpus/benchmarks.htm )
>> which is really positive surprise for me considering some rather more
>> pessimistic prognoses
>> regarding parallel GPU runs ( > 2 GPU) on the single socket systems in
>> this discussion.
>>
>> Of course the melting issue of the power connection is a bit less
>> optimistic information :((
>>
>> Did I understood well, that melting took place just on the ending which
>> is connected with motherboard ?
>>
>> How long it worked well before this "accident" ? Were during this "OK
>> period" successfully
>> done some longer (at least some days) runs during which all 4 GPUs were
>> fully busy ?
>>
>> If it worked well before this problem, what is in your opinion
>> the reason of this actual melting issue ? For example could it be the
>> reason some extremely long
>> run on all 4 GPUs ? Failure of some cooling fan ? Do you have already
>> some
>> indications from "Microway/ASUS" regarding
>> this issue ?
>>
>> Which is specification of your PSU ?
>> (I am thinking about: SilverStone Strider Plus Series SST -ST1500 1500W
>> )
>>
>> BTW just for curiosity regarding GPUs I am finally thinking about "MSI
>> N580GTX Lightning Xtreme Edition"
>> which seems to be actually the most powerful/precise 3GB GTX580 on the
>> market.
>>
>> Thanks in advance for your eventual additional comments !
>>
>> Best wishes,
>>
>> Marek
>>
>>
>>
>>
>>
>>
>>
>> Dne Wed, 14 Sep 2011 17:50:21 +0200 Jodi Ann Hadden <jodih.uga.edu>
>> napsal/-a:
>>
>> > Hi Marek,
>> >
>> > I have a GPU machine with the motherboard you were interested in (ASUS
>> > P6T7 WS SuperComputer, single LGA1366 socket with the Intel X58
>> > chipset). It has an Intel Xeon W3520 Nehalem 2.66 GHz quad core CPU
>> and
>> > 4x NVIDIA Tesla C2070s. Below are some numbers (ns/day) for this
>> machine
>> > running a subset of the official AMBER benchmark suite so you can get
>> an
>> > idea of the speedup we get when going to all 4 GPUs for a single job.
>> >
>> > Benchmark 1xC2070 2xC2070 3xC2070 4xC2070
>> > GB/myoglobin 63.03 77.14 90.69 102.38
>> > GB/nucleosome 1.10 1.34 1.68 1.97
>> > GB/TRPCage 354.40 334.06 330.76 330.75
>> > PME/Cellulose_production_NPT 1.97 2.76 3.29 3.56
>> > PME/Cellulose_production_NVE 2.19 3.06 3.67 3.96
>> >
>> > As for the issue of cooling, this system is housed in a Lian Li
>> chassis
>> > (25x24.9x8.6) with three fans in the front, one in the back, and one
>> on
>> > top. I had also noted that the GPUs were getting extremely hot and
>> > contacted Microway, the company who assembled the machine for us. The
>> > assured me that they'd had experience with 4x Teslas in that chassis,
>> > and that cooling was sufficient.
>> >
>> > I will warn you, however, that we recently experienced a socket burn
>> > with this motherboard, where the 24-pin ATX power connection from the
>> > PSU to the motherboard had the plastic melt off of some of the pins.
>> > Microway/ASUS are replacing it for us under warranty, so hopefully we
>> > just had a lemon.
>> >
>> > Hope this helps,
>> >
>> > Jodi Hadden
>> > University of Georgia
>> >
>> > On Sep 13, 2011, at 1:17 PM, Marek Maly wrote:
>> >
>> > OK,
>> > thanks again ! If anyone has experience with Amber calculations on
>> > a single socket machine with a 4 core CPU equipped with 4 GPUs,
>> > please comment.
>> >
>> > Best wishes,
>> >
>> > Marek
>> >
>> >
>> >
>> > Dne Tue, 13 Sep 2011 19:25:20 +0200 Ross Walker
>> > <ross.rosswalker.co.uk<mailto:ross.rosswalker.co.uk>>
>> > napsal/-a:
>> >
>> > first of all thanks a lot for your complex answer !
>> > In fact I assume mainly independent single GPU jobs. So if I
>> understood
>> > well, in such case there should not be problem considering below
>> > mentioned
>> > motherboard/CPU/4xGPU. Am I right ?
>> >
>> > For single GPU runs (i.e. 4 independent jobs) then things should be
>> fine
>> > assuming the I/O can keep up etc. The caveat with that is that I have
>> not
>> > actually tried 4 GPUs in a single socket machine with a 4 core GPU so
>> am
>> > speaking from a theoretical standpoint here given how the AMBER GPU
>> code
>> > works. Someone else who is running such a system might want to chime
>> in
>> > with
>> > some specific performance numbers if they have them.
>> >
>> > All the best
>> > Ross
>> >
>> > /\
>> > \/
>> > |\oss Walker
>> >
>> > ---------------------------------------------------------
>> > | Assistant Research Professor |
>> > | San Diego Supercomputer Center |
>> > | Adjunct Assistant Professor |
>> > | Dept. of Chemistry and Biochemistry |
>> > | University of California San Diego |
>> > | NVIDIA Fellow |
>> > | http://www.rosswalker.co.uk | http://www.wmd-lab.org/ |
>> > | Tel: +1 858 822 0854 | EMail:-
>> > ross.rosswalker.co.uk<mailto:ross.rosswalker.co.uk> |
>> > ---------------------------------------------------------
>> >
>> > Note: Electronic Mail is not secure, has no guarantee of delivery, may
>> > not
>> > be read every day, and should not be used for urgent or sensitive
>> issues.
>> >
>> >
>> >
>> >
>> >
>> > _______________________________________________
>> > AMBER mailing list
>> > AMBER.ambermd.org<mailto:AMBER.ambermd.org>
>> > http://lists.ambermd.org/mailman/listinfo/amber
>> >
>> > __________ Informace od ESET NOD32 Antivirus, verze databaze 6459
>> > (20110913) __________
>> >
>> > Tuto zpravu proveril ESET NOD32 Antivirus.
>> >
>> > http://www.eset.cz
>> >
>> >
>> >
>> >
>> >
>> > --
>> > Tato zpráva byla vytvořena převratným poštovním klientem Opery:
>> > http://www.opera.com/mail/
>> >
>> > _______________________________________________
>> > AMBER mailing list
>> > AMBER.ambermd.org
>> > http://lists.ambermd.org/mailman/listinfo/amber
>> >
>> >
>> > _______________________________________________
>> > AMBER mailing list
>> > AMBER.ambermd.org
>> > http://lists.ambermd.org/mailman/listinfo/amber
>> >
>> > __________ Informace od ESET NOD32 Antivirus, verze databaze 6462
>> > (20110914) __________
>> >
>> > Tuto zpravu proveril ESET NOD32 Antivirus.
>> >
>> > http://www.eset.cz
>> >
>> >
>> >
>>
>>
>> --
>> Tato zpráva byla vytvořena převratným poštovním klientem Opery:
>> http://www.opera.com/mail/
>>
>> _______________________________________________
>> AMBER mailing list
>> AMBER.ambermd.org
>> http://lists.ambermd.org/mailman/listinfo/amber
>>
> _______________________________________________
> AMBER mailing list
> AMBER.ambermd.org
> http://lists.ambermd.org/mailman/listinfo/amber
>
> __________ Informace od ESET NOD32 Antivirus, verze databaze 6464
> (20110914) __________
>
> Tuto zpravu proveril ESET NOD32 Antivirus.
>
> http://www.eset.cz
>
>
>
--
Tato zpráva byla vytvořena převratným poštovním klientem Opery:
http://www.opera.com/mail/
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Wed Sep 14 2011 - 18:30:02 PDT
