• Welcome to Overclockers Forums! Join us to reply in threads, receive reduced ads, and to customize your site experience!

GTX470 and GTX480 Clocks ?

Overclockers is supported by our readers. When you click a link to make a purchase, we may earn a commission. Learn More.

JJG

Member
Joined
Nov 10, 2003
Location
Missouri
did nvidia just drop more jucy details (clocks) on the GF100 cards ? or am i reading this wrong ?

Source

We first got word that production A3 GF100s were back in Santa Clara near the end of January. When enough of them rolled off the line to characterize the silicon, we hear there were no parties in Santa Clara. For those not interested in the 'why' side of things, the short answer is that the top bin as it stands now is about 600MHz for the half hot clock, and 1200MHz for the hot clock, and the initial top part will have 448 shaders. On top of that, the fab wafer yields are still in single digit percentages. Number one on Nvidia's hit list is yields. If you recall, we said that the yield on the first hot lot of Fermis that came back from TSMC was 7 good chips out of a total of 416 candidates, or a yield of less than 2 percent
 
Charlie bashing Nvidia? I'm simply shocked.

We're just going to have to wait and see what the products look like when they're actually released.
 
+1... I hope this isnt true.. but lots of details and knowing nothing like I do about them, it makes sense. I dont buy the yields though. How would anyone make a dime on anything with yields that low? What are successful yield percentages?
 
The yield might be 2% for a 448 shader card, but they should be able to use some of the other wafers for lesser cards.
 
Source is semiaccurate, this thread is now void.

Seriously people, all that guy does is whine on and lie about nvidia stuff. It's not even worth making threads about.
 
Source is semiaccurate, this thread is now void.

Seriously people, all that guy does is whine on and lie about nvidia stuff. It's not even worth making threads about.

Yep, he was so totally wrong about the overheating laptop GPUs.
 
Yep, he was so totally wrong about the overheating laptop GPUs.

Yeah, predicting over heating laptop gpus has about as good a chance as being correct and saying, you know I think it will snow this winter in new york.:bang head

Semi accurate sucks. Just because they get stuff right 5% of the time doesn't mean you should excuse the other 95% of bull crap the put on there. :bang head
 
He's been right an uncomfortable number of times recently for you nvidia fanboys.

I don't like his writing style on constant bashing, but so far it has been fairly accurate.
 
He's been right an uncomfortable number of times recently for you nvidia fanboys.

For someone with an apparent grudge against Nvidia, you sure do spend a lot of time on this side of the forum. Charlie fanboy, heh.
 
That gave me a good chuckle. I'm no stripe of fanboy. You won't see me bashing or boosting any product just because of who made it.

Wow excellent evidence you provided to the contrary of your past posts. You're not obvious about it, but there's no doubt you're loyal to the brand. :blah:
 
Wow excellent evidence you provided to the contrary of your past posts. You're not obvious about it, but there's no doubt you're loyal to the brand. :blah:

Go ahead, show me a single example of fanboyism. Till then, stop the emoticon nonsense and namecalling.

edit: BTW, my HTPC runs on AMD/ATI :blah:
 
Your little article.

"The generation gap between Fermi and RV870 has the potential to be as large as the RV770 to RV870."

Baseless, completely speculative nonsense with no logic to back it up. The whole thing is extremely selective.
 
Your little article.

"The generation gap between Fermi and RV870 has the potential to be as large as the RV770 to RV870."

Baseless, completely speculative nonsense with no logic to back it up. The whole thing is extremely selective.

As I've said myself.. It's "potentially" and "if they make target clocks with the full 512 SPs."

I stand by the guesswork. A GTX 480 - assuming they can make clocks, and assuming all 512 shaders are working - will perform close to a 5970. Whether Nvidia can actually produce the cards is another matter.
 
I see this thread is degenerating fast. :screwy:

Even though it's Charlie, he's done pretty good lately calling the faults with Fermi. I think he's full of himself and loves to sensationalize things to pat himself on the back, but I also believe he has some inside tracks on what's happening with the 480's too. I guess we will just have to wait and see what they finally release.

I don't know about you all, but this reminds me a lot of ATI/AMD with the R600 gpu, which it being so late and lack of advance benchmarks. I sincerely hope that nVida can come out with a winner too, just to keep the market tight and prices down if nothing else. But I'm leaning towards Charlie being more right than wrong at this point in time, from the stuff I have read so far. And this is coming from someone who definitely isn't an AMD fanboy (or nVidia fanboy) either. Most of my systems are running nVidia cards in them.

Let's keep this thread civil, or I will knock some heads, ya hear?:eek:
 
Honestly Charlie just might be taking a shot in the dark hoping margin of his error not going to be very large , but really with all the information we have it is a good guess .
 
Someone better not have called me a nvidia fanboy, last time I spent my money on a graphics card, it was on a ati thank you.

I'm out of this thread, have fun bickering.
 
Back