[RC5] Cuda client

Matt Ruthenbeck toffuuu at gmail.com
Fri Feb 1 01:27:22 EST 2013


i will say this tho and have encountered similar arguments with other
things NVIDIA that i myself use em, dont really mind current stuff as it
is, but then again *keep in mind im not a programmer* do at times think
programming for specific hardware is a pain but at the same time people
that do program need to smarten up on how to for very specific things, not
putting them down of course, its just in my view NVIDIA does surpass ATI in
alot of ways, but again i dont know how u guys program with regards to
CUDA, but i think its time for NVIDIA to get it but kicked in terms of
actual programming and not be forced to use CUDA...  cause ive seen things
using NVIDIA that is far sepurior to CUDA, but its all closed source so u
guys will never see it....  this does include using the cores a bit
better...  just something to think about...
Matt Rafter/Ruthenbeck
Email: toffuuu at gmail.com
http://www.google.com/profiles/toffuuu
http://www.hickorytech.net/~toffuuu/
http://www.facebook.com/toffuuu
http://www.last.fm/user/mac2010
http://www.youtube.com/TheMac6010 <http://www.youtube.com/TheMac4010>
http://www.boincstats.com/signature/user_29296.gif
There may be fairies at the bottom of the garden. There is no evidence for
it, but you can't prove that there aren't any, so shouldn't we be agnostic
with respect to fairies? Richard Dawkins


On Fri, Feb 1, 2013 at 12:02 AM, Andrew Hime <andrewhime at verizon.net> wrote:

> Bert,
>
> With all due respect to all involved, the brick wall has been around for
> probably a decade or more. I'm pleasantly surprised when something happens
> every two years or so. The whole project has pretty much been on autopilot
> for a LONG time at this point.
>
>
>
> On 01/31/13, bert<bertodell at suddenlink.net> wrote:
>
> So apparently anyone who buys a 600 or 700 series Nvidia card(when the
> 700 comes out or any later cards) is screwed and it would be no use to
> run the distributed.net client even when Cuda has moved far away from
> 3.1 which is old? Distributed.net NEEDS to put this information on their
> front page that they no longer can put out a client that can support the
> newer cards. What a damn waste and to think after 13 years the brick
> wall is beginning to appear....
>
>
> Bert
> On 1/31/2013 1:18 PM, Décio Luiz Gazzoni Filho wrote:
> > On Jan 31, 2013, at 3:52 PM, Joseph Kaye <jkaye at isd.net> wrote:
> >
> >> On 1/30/2013 2:18 PM, bert wrote:
> >>> The Cuda client is still at 3.1 and the with the latest Nvidia
> >>> driver(310.90) using version 5,could this be the reason my son's GTX
> 680
> >>> is slower than his old GTX 580(which is in use on my other son's
> >>> computer)? I was kind of shocked and was expecting a much quicker pace
> >>> in going through 64 stats units(the GTX 580 is averaging about 3
> minutes
> >>> or so vs almost 8 minutes with the GTX 680!) Any help or suggestions
> >>> would be appreciated.
> >>>
> >>> Bert
> >>>
> >>>
> >>> _______________________________________________
> >>> rc5 mailing list
> >>> rc5 at lists.distributed.net
> >>> http://lists.distributed.net/mailman/listinfo/rc5
> >>>
> >> It doesn't look like the 6xx series is working so well for dnetc.
> >>
> >> http://bugs.distributed.net/show_bug.cgi?id=4507
> >>
> >> Apparently they changed the design of the GPU, and while they do have
> >> more cores now, they removed instructions (or something) that DNETC
> >> needs for faster computations. IIRC, it's kinda like when Intel removed
> >> the ROT function from the P4 CPU's. They had a higher clock speed, but
> >> because of the ROTate function was not there, the keyrate was much
> slower.
> > Just to clear up a common misconception: Intel never *removed* an
> instruction from a new processor that was present in an earlier processor,
> including rol. That would break up backward compatibility which is a main
> selling point of the x86 architecture (and by extension the Wintel
> platform).
> >
> > What did happen is that there is a piece of hardware used for efficient
> (usually single-cycle) implementation of variable-sized shifts and
> rotations (the shl, shr, sar, rol, ror, rcl and rcr instructions) -- that
> hardware is called a barrel shifter. it has historically been implemented
> on every Intel processor since the 80386 or so, but don't quote me on that.
> Certainly the classic 1993-era Pentium did have it. The barrel shifter is
> what wasn't present on the Pentium 4, and the reason why the rol
> instruction executed slower (I believe it took 4 cycles).
> >
> > So the instruction has always existed, even on the Pentium 4 -- it had
> to because of backward compatibility reasons -- but the hardware for
> efficiently implementing it didn't exist only on the P4 chips, and Intel
> has added it back on the newer Core chips, which is why they perform better.
> >
> > Décio
> > _______________________________________________
> > rc5 mailing list
> > rc5 at lists.distributed.net
> > http://lists.distributed.net/mailman/listinfo/rc5
>
> _______________________________________________
> rc5 mailing list
> rc5 at lists.distributed.net
> http://lists.distributed.net/mailman/listinfo/rc5
>
> _______________________________________________
> rc5 mailing list
> rc5 at lists.distributed.net
> http://lists.distributed.net/mailman/listinfo/rc5
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.distributed.net/pipermail/rc5/attachments/20130201/74de93d3/attachment-0001.html 


More information about the rc5 mailing list