os that rather uses the gpu?

JD jd1008 at gmail.com
Sat Jul 17 03:17:28 UTC 2010

  On 07/16/2010 04:55 PM, Christofer C. Bell wrote:
> On Fri, Jul 16, 2010 at 6:49 PM, Robert Myers <rbmyersusa at gmail.com 
> <mailto:rbmyersusa at gmail.com>> wrote:
>     Whether you like it or not, and whether, even more important, you
>     understand it or not, the architecture of a computer has a big
>     impact on the kinds of models you can implement with any degree of
>     efficiency on the computer.  Hanging lots of flops on inadequate
>     bandwidth is popular because you can get a high ranking on the Top
>     500 list with a minimal expenditure, but it also means that you
>     can't do an important calculation like a global FFT at anything
>     like reasonable efficiency.  Flops are almost free.  Bandwidth is
>     expensive.  Unfortunately, what is almost free (flops) can be
>     nearly useless for, say, an FFT unless you have the bandwidth to
>     move data around globally fast enough.
> You need to make friends with a guy named Edward Lorenz.  Bandwidth 
> has nothing to do with it.  Do you even know what this term means?
>     I don't think name-calling and labeling ever helps.
> Then stop doing it.
> -- 
> Chris
Hi Chris,

"In August 2007, PCI-SIG announced that PCI Express 3.0 will carry a bit 
rate of 8 gigatransfers <http://en.wikipedia.org/wiki/Gigatransfer> per 
(128 bits per transfer) !!
That is about 137,438,953,472 bytes per second.
Viva SLI and multi-treaflop/s gpu's !!

Alright! All you DSP fans, and telemetry data fans, get to work :) :)

And you wifi cracker fans, you now have even a better tool than
what the japanese team had:


If they could crack TKIP in under a minute using a laptop, perhaps
now they can tackle and crack AES, which they were not able to do back 
then (2009).

Technology is indeed a two-edged sword :)
It temporarily gives us a false sense of security, only to be
robbed of that sense by self same technology.



More information about the users mailing list