next gen kepler to support dx 11.1, also take a year to rollout all cards

[shadow001]

Originally Posted by ninelven

I'm not the one who needs pictures. Either answer the questions or admit you have no actual evidence for your claims.


Exactly, how much die space do the ROPs take on Fermi? What is the percentage of the total area of Fermi? How much die space do the ROPs take on Tahiti, and what percentage of the total area?

That would be information that would only be known for the reasons i mentioned earlier, assuming Nvidia itself allows the information to be released, so stop with the stupid argument if you please.

Exactly, how should the ROPs and texture units be "enhanced?"

Like i said earlier and you didn't bother to understand at all, they need to do more work for every clock cycle in practical real world terms, meaning adding more memory bandwith would help, but adding even more of same ROPS is pointless, as it was proven with the 32 ROPS on tahiti wich is 50% less than on Fermi, and Fermi gets it's ass kicked hard.....This is not hard to understand either...

No, just like nvidia. Texture units are tied to SIMD engines in GCN; it is clear you don't have a clue what you are talking about.

Connected together and integrated into the shader block are 2 different things....The first allows to futher enhance the texturing output without needing to mess with the shader block itself, and the second option does not wich is the option Nvidia took....

[shadow001]

Originally Posted by Rollo

I can't remember the last time Charlie was right about something, but if he is about this apparently GK104 is a 560Ti replacement.

If it performs like a GTX580 or slightly better, has 2GB of VRAM, and an MSRP of $299 NVIDIA would sell TONS of them and totally devalue 7970s and 7950s.

Would be a pretty amazing turn of events if true, and great news for everyone except ATi.

But I can't remember the last timne Charlie was right, so I'll take it with a 40# bag of softener salt.

Please continue with the damage control...It's fun to read.


I'm still waiting for the chip that crushes the HD7970 in performance, and haven't heard or seen a damn thing btw...Not even rumors.

[ninelven]

Originally Posted by shadow001

but adding even more of same ROPS is pointless, as it was proven with the 32 ROPS on tahiti wich is 50% less than on Fermi, and Fermi gets it's ass kicked hard.....

I already covered how this was wrong in my first post, but you apparently refuse to understand. I can only conclude that you are now being intentionally dishonest and simply trolling.

But just in case it REALLY didn't sink in the first time, here it is again

Originally Posted by ninelven

Although Fermi has 48 ROPs, it can only put out 2 pixels per SM per clock, which equals 32 (16 SM x 2 = 32PPC). The stock clock of the GTX 580 is 772 vs 925 for the 7970, which makes the 7970 20% faster. The 7970 also has a 37% bandwidth advantage over the GTX 580. Looking at the numbers from your first graph 13.33 / 9.75 = 1.37 or a 37% advantage for the 7970 indicating that bandwidth is the limiting factor and exactly what one would expect.

Look kid, if you have such a great such a great understanding of these matters, you should be employed in the industry or patenting your ideas and selling the IP. By all means, apply to Nvidia for a job or email their engineers with your improvements to their designs. I'm sure they would love to hear from you personally. But don't waste your time posting vague nonsensical statements on a fansite without any actual evidence to back up your claims; that just makes you look like an ignorant troll. Anyway, I'm done here.

[Ninja Prime]

Originally Posted by Rollo

I can't remember the last time Charlie was right about something, but if he is about this apparently GK104 is a 560Ti replacement.

If it performs like a GTX580 or slightly better, has 2GB of VRAM, and an MSRP of $299 NVIDIA would sell TONS of them and totally devalue 7970s and 7950s.

Would be a pretty amazing turn of events if true, and great news for everyone except ATi.

But I can't remember the last timne Charlie was right, so I'll take it with a 40# bag of softener salt.

Hows that crow taste rollo? Wheres this magic 50% faster than last gen card? Isn't it a failure in your eyes if it isn't 50% faster than last gen?

[Muppet]

And another thread derailed .

[Rollo]

Originally Posted by shadow001

Please continue with the damage control...It's fun to read.


I'm still waiting for the chip that crushes the HD7970 in performance, and haven't heard or seen a damn thing btw...Not even rumors.

What "damage"? AMD getting a few months of sales of 28nm parts? Why would I care about this?

[Rollo]

Originally Posted by Ninja Prime

Hows that crow taste rollo? Wheres this magic 50% faster than last gen card? Isn't it a failure in your eyes if it isn't 50% faster than last gen?

Like I said, I can't remember the last time Charlie was right about something. I'll believe he's right when I see the reviews confirming it.

I was only noting a card with 2GB, the NVIDIA feature set, and GTX580+ performance would sell a ton at $299 MSRP.

[Roadhog]

Looks like the Kepler won't be near a 7970 after all.

http://semiaccurate.com/forums/showp...&postcount=321

[Rollo]

Originally Posted by Roadhog

Looks like the Kepler won't be near a 7970 after all.

http://semiaccurate.com/forums/showp...&postcount=321

Charlie Demerjian, the God of FanATics.

Charlie Demerjian, the

Charlie Demerjian, the source of 95% of the world's anti NVIDIA FUD.

Charlie has quite the legacy going.

I encourage everyone who considers Charlie a valid source of information to stock up on 7970s.

[shadow001]

Originally Posted by Rollo

Charlie Demerjian, the God of FanATics.

Charlie Demerjian, the

Charlie Demerjian, the source of 95% of the world's anti NVIDIA FUD.

Charlie has quite the legacy going.

I encourage everyone who considers Charlie a valid source of information to stock up on 7970s.

All the main outlets sold the majority of HD7970's already....There're coming in but selling fast so stocks aren't exactly high....Btw, how's the flame resistant suit holding up?


I'm asking since we're just at the start and you may have to keep strong for many months to come....

[shadow001]

This is from Vr-zone about 3 months ago, and pray it isn't accurate at all






We see where the new chips slot in the performance scale of things relative to the old generation, and what comes out first isn't even the GK104 but lower end parts first, and the GK110 is basically a dual GPU GK104 based card, with the real high end only being released in early 2013....Pray that this also isn't accurate at all and that VR-zone is talking bull**** too, just like charlie is as well.


http://vr-zone.com/articles/report-n...map/14067.html

[shadow001]

Originally Posted by ninelven

I called you a kid because I guessed you were one based off your behavior. You can take that however you want....

As long as you keep in mind that you should have actual supporting evidence before making a statement and representing it as fact

Really, then how's this:


The theoretical maximum that the GF110 is capable of is 37.06 Gigapixels/sec, but only delivers 9.6 gigapixels acording to that chart in practical terms.


The theoretical maximum of AMD's tahiti is just over 29 Gigapixels/sec, yet delivers those 13.3 Gigapixels/sec when mesured in practical terms...So it has less in theoretical maximum over the GF110 by a fair amount no less but delivers more in practical terms, wich is where it counts.


So who's more efficient and does this count as supporting evidence enough?....