NVIDIA GF100 & Friends speculation

Are you REALLY basing performance projections off of a silly PR slide? Please, tell me you're joking.
If the 470 was faster than the 5870 (or even equal, for that matter) and the 480 significantly faster, Nvidia would have designed that slide accordingly for sure. It's a PR/marketing slide afterall, it's supposed to say "look how good our products are and how bad theirs are!". You don't place the 470 so far below the 5870 in such a slide unless you absolutely have to because everything else would be revealed as a flat out lie once the NDA lifts.
 
If the 470 was faster than the 5870 (or even equal, for that matter) and the 480 significantly faster, Nvidia would have designed that slide accordingly for sure. It's a PR/marketing slide afterall, it's supposed to say "look how good our products are and how bad theirs are!". You don't place the 470 so far below the 5870 in such a slide unless you absolutely have to because everything else would be revealed as a flat out lie once the NDA lifts.


Depends on what they are talking about is "$" :)
 
Are you REALLY basing performance projections off of a silly PR slide? Please, tell me you're joking.

It sort of puts a limit to 470's performance - Do you REALLY think PR would put it next to 5850 (slightly above, but below a bar that wouldn't have to be there), if it was actually more or less on par with the 5870?

Interesting numbers from the nv ftp btw (time to look for reliable references regarding the first 4 colums) - but I would recommend nvidia to 'mark' the ftp accounts by moving the watermark around a bit, instead off adding removable numbers ;)
 
So you're advocating that adding value and more features is unncessary because you can pay more for other components that do it?? :smile:

Good one - but an X-Fi can do some more things, so it'd add value on its own yet again. :)

BTT: Most people i know are still using regularly connected 2.1 - 5.1 speakers, not routed with several HDMI-extenders through their receivers in their living rooms and back to the room where the PC sits.

It's a great-to-have feature though for living room/HT PCs, but in my personal opinion it is not very useful for high-end gaming cards. It is no more decisive for my buying decision as for example the video decoders capabilities (again: for high-end gaming cards that sit in high-end gaming rigs).

thats understandable

i think it is only fair to add the 5970 to the benchmark after all you guys did it with the release of the 5870 before by adding the nvidia gtx 295

http://www.pcgameshardware.de/screenshots/original/2009/09/HD5870-CoD-WaW-1280.png
http://www.pcgameshardware.de/screenshots/original/2009/09/HD5870-FC2-1280.png

not trying to be rude just would like to see it.
As I said: We're considering it right now. But a, no two - we added 4870 X2 too - bad decisions from half a year back don't necessarily mean, we have to keep with that until all time ends. After all, we've quit benchmarking Quake 3 also without being called names. ;)
 
Last edited by a moderator:
As I said, x86 is quite popular right now. But x86 isn't nearly as "locked-in" in the HPC space as it is in the consumer space. Yes, performance-porting is challenging, but usually that's managed by porting a relatively small number of libraries, such as BLAS and LAPACK, where most of the compute time is spent. Such libraries are typically the only parts of HPC applications that are architecture-optimized anyway.

x86 IS LOCKED IN! All the libraries, the tools, the drivers, flows, etc. Are basically x86 based now. This doesn't even get into the quality of things like the compilers vs other architectures.

The #1 reason why x86 is popular in the HPC space right now is because AMD and Intel are leveraging the huge (by HPC standards) volume of consumer-space products to basically out-R&D their competitors.

yes, and your point is?

Because Linux is vastly superior for this space. Some of the biggest benefits off the top of my head are the ssh interface (which is essential for working remotely), the more-or-less standardized compiler and library setup (which is really important for porting between different machines), and the extremely powerful commandline (which is essential for saving time in executing large numbers of jobs).

And here I was thinking free and supported with drivers.
 
Good one - but an X-Fi can do some more things, so it'd add value on its own yet again. :)


As I said: We're considering it right now. But a, no two - we added 4870 X2 too - bad decisions from half a year back don't necessarily mean, we have to keep with that until all time ends. After all, we've quit benchmarking Quake 3 also without being called names. ;)


they insulted you for that? that sucks >.<
 
No, x86 now only makes up like 95% by revenue and something like 99% by volume. So I guess that is less than the 100%/100% of the PC space, but to say its much less important is kinda funny.
What I mean is that there is vastly less "lock-in" of x86 processors. The main reason that they're so popular is because they're often genuinely better for the cost, a cost that is subsidized by the desktop/laptop markets for AMD and Intel, a cost reduction not available to other companies. However, if there is a real, cost-effective alternative to x86 processors, I don't think it will take long for HPC's to take advantage of it. If, for instance, nVidia could work with some other CPU company to bundle a CPU with their GPU, leveraging the GPU R&D from the consumer space, it is conceivable they could put out a cost-competitive, high-performance integrated design that could well be quite useful there. It would be a bit of an uphill battle, but still within reason.

But for desktop systems, there just isn't any reasonable way for any significant move away from x86, because Windows is so pervasive.

As for drivers, the majority of Linux drivers these days are built into the kernel. I'd be rather surprised if those aren't cross-platform by large.
 
As I said: We're considering it right now. But a, no two - we added 4870 X2 too - bad decisions from half a year back don't necessarily mean, we have to keep with that until all time ends. After all, we've quit benchmarking Quake 3 also without being called names. ;)

So wait, if I understand this correctly - you will only ever benchmark dual-gpu cards against other dual-gpu cards from now on?

I mean if you aren't going to bench them against single gpu cards then surely that only leaves dual gpu cards?
 
You guaiz seen this?
73529807.jpg

gtx4802.jpg
 
So wait, if I understand this correctly - you will only ever benchmark dual-gpu cards against other dual-gpu cards from now on?

I mean if you aren't going to bench them against single gpu cards then surely that only leaves dual gpu cards?

The taster article observes:
pcgameshardware said:
Auf Dual-GPU-Karten verzichten wir, da diese aufgrund der Eingabeverzögerung und den Mikrorucklern ein nicht vergleichbares Spielgefühl bieten.

A more useful comparison for these crossfire-on-a-stick cards is probably to include other Crossfire and SLI solutions.

So Carsten, as we seem to be in request mode in this topic.... :p
 
Probably just a type since the guy had to copy it by hand. It matches up with the other resolution.

The numbers don't seem unreasonable. 10-50% faster averaging 25% is pretty much where I expected the GTX480 to be.
 
Probably just a type since the guy had to copy it by hand. It matches up with the other resolution.

The numbers don't seem unreasonable. 10-50% faster averaging 25% is pretty much where I expected the GTX480 to be.


that one smells of nvidia marketing i'm not trusting that since there's no way any reviewer's gotten 2 480s and a 470 by now
 
that one smells of nvidia marketing i'm not trusting that since there's no way any reviewer's gotten 2 480s and a 470 by now

Sure, they are clearly labeled as nvidia slides, source here: http://futuremark.yougamers.com/forum/showthread.php?t=125009 So most probably legit, but of course with all the usual bias regarding games, settings and drivers we can expect from marketing slides (from either company). Not something I would draw an average from.
 
Back
Top