Kepler in the Workstation: Nvidia Rolls Out New Quadros

[Draven35]

A Kepler-based Quadro line

Kepler in the Workstation: Nvidia Rolls Out New Quadros : Read more

 

[TheBigTroll]

Great news. just that double precision compute still lags

 

[Draven35]

Yes, I agree... if your application uses it.

 

[witcherx]

guys check amds tressFX

 

[wiyosaya]

[citation][nom]TheBigTroll[/nom]Great news. just that double precision compute still lags[/citation]
That is where Titan comes in.

 

[Guest]

i'm not inpressed, I think i'll hold on to my Quardro FX 4800 for another year than update to a Quadro 5000 when suckers sell them off to buy this new crap.

 

[thegreatms]

I'd love to see a in depth review of the performance of these cards when running real workstation software. In my case that would be SolidWorks with medium to large assemblies.

It would be nice to understand how much real world difference there is between: high end gaming cards, last gen workstation cards, and current gen workstation cards.

 

[Draven35]

kjh, you do realize that the FX 4800 has less CUDA cores than anything except the bottom-end K600, right? and that the memory on these is much faster, and that OpenGL and compute tasks are going to be much faster?

greatms, doing detailed reviews using Solidworks has... licensing issues.

 

[hiperkubs]

Draven35, you are a bit wrong on importance of Cuda cores, every generation can't be compared by it's count. For example by going from Fermi to Kepler the core count has tripled, but overall transistor count not so much, it has risen at about 15%, and the same with core overall frequency.
Quadro Fx4800 in single precision computation is truly comparable to the k2000, minus the open Gl 4.1 kapability, the older fx 4800 has open Gl 3.3. That's about it.

 

[mapesdhs]

[citation][nom]hiperkubs[/nom]... For example by going from Fermi to Kepler the core count has tripled, ...[/citation]

For some tasks the memory bandwidth available per core is much more important than the number
of cores. This is why the newer GTX 600 series cards are not as fast as one might expect compared
to the 500 series - a lot more cores, but not the mem bw to feed them. And that's why using several
cheaper cards with fewer cores but more bw per core often results in much better performance than
a single card with loads of cores. Try using four GTX 460s and see how it compares to a 670 or 680
for AE.

Transistor count doesn't mean anything though. A newer design might have more elements purely
because of a more sophisticated power delivery system and power management system, which
doesn't translate to better performance, but reduces cost re power consumption. Transistor count
is as useful as the old pointless MIPS metric for CPUs.

Ian.

 

[mapesdhs]

[citation][nom]thegreatms[/nom]... high end gaming cards, last gen workstation cards, and current gen workstation cards.[/citation]

Note these cards can vary greatly in their performance depending on the available main CPU power.
The potential of a good Quadro can be wasted if the CPU is poor. Thus, for a proper comparison,
tests should be done using both a typical generic 'professional' config (standard XEON or two, with
no oc'ing) and an enthusiast-style normal mbd (eg. 5GHz 2700K, or even an older oc'd dual-core).
The differences can be amazing, especially for CPU-sensitive apps like ProE.

Ian.

 

[mapesdhs]

I forgot to include references for my comments. See:

http://www.sgidepot.co.uk/misc/viewperf.txt

AE data still under construction (working on 3930K and dual-X5570 tests atm).

Ian.