Hi Ian,
thanks for your info and maybe the "new light" to this story.
My Titans are both from EVGA and moreover superclocked version
(EVGA GTX TITAN Superclocked Signature ). Would be nice to know
GPU specifications of all the other "members of the club".
Anyway Scott confirmed that in NVIDIA were able to reproduce cuFFT/Titan
errs. I would assume that they perhaps tried to reproduce it on more GPUs
also including more producers (EVGA, Gigabyte, ASUS, GAINWARD or ZOTAC) to
better/more easily understood the root of all these problems.
BTW did you tried to test the reproducibility of the results (using your
own molecular systems
or those from Amber benchmarks here especially JAC NVE/NPT ones ?).
Best,
Marek
Dne Wed, 19 Jun 2013 20:34:15 +0200 Gould, Ian R <i.gould.imperial.ac.uk>
napsal/-a:
> Dear All
>
> I am running 4 stock Titan Gigabyte GTX TITAN's and have not had any
> problems with them and they have been running flat out for a while. From
> all the bandwidth on this issue could it be something specific to the
> EVGA? Does anyone have experience with the ASUS, GAINWARD or ZOTAC
> Titans?
>
> Cheers
> Ian
>
> Women love us for our defects. If we have enough of them, they will
> forgive us everything, even our intellects.
> Oscar Wilde
--
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 Jun 19 2013 - 13:00:03 PDT
