• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

[SA] GK110 aka GTX 680 release date: Late Q3 '12

blackened23

Diamond Member
http://semiaccurate.com/2012/02/07/gk110-tapes-out-at-last/

With the size of GK104 now pretty settled, what about the big one? Sources are now saying this chip might be called GK110, but we are still hearing some insiders say GK112. Lets stick with GK110 for the article though, numbers ending in 0 tend to soothe moles more than numbers ending in 2.
Recently, a Taiwanese dancing mole, hair died green and still a bit hung over from New Year parties, gave us the answer. He said that GK110 is basically reticle limited, about 23.5mm on a side. The math says that it is about 550mm^2, with the last two generations coming in at 529/550mm^2 (GF100/GF110 respectively) and 576mm^2 for GT200.
The reason for the vagueness it that the chip just taped out a few weeks ago. Current green-topped roadmaps not from green topped moles have the release date slated for August/September. While this is quite possible, several of SemiAccurate’s sources with prior experience bringing high performance silicon to market scoffed at the time tables. Either way, late Q3 2012 is a decent mental placeholder.
One thing the mole said when he looked up with somewhat bleary eyes is that the chip definitely has a 384-bit memory bus. Other documents have the part burning close to 300W, and you can read two things in to this number. First is that this part is very likely to be an HPC oriented chip with the CU count, and attendant power-hungry interconnect, being notably higher than GK104. Second is that the rumours of GK100 being cancelled early in the game are likely true, they said problems revolved around interconnects and power issues.
Will GK110 solve these, and therefore Denver’s similar problems? Will it pull ‘only’ 300W, or will we get another Fermi-esqe performance per watt waterfall? Will GK110 be skewed toward HPC like the early leaks suggested? Will it once again come at the cost of gaming performance? Will there even be a consumer variant, or will it be professional/compute only? Some of these questions can be answered when silicon comes back. Others are a little more subjective. No matter what happens, this will be fun to watch.S|A

Another Charlie article....standard disclaimers apply
 
Seems logical and in line with what the rumors suggested until now. So they bet their first money on the GK104 which should fall between Tahiti and Pitcairn. How much it will be able to compete with the 7970 remains to be seen but I expect a fair battle with the 7950 at a very competitive price. Anything better would be exceptionally well for the midrange chip.
 
Disappointing news. August/September seems way too late. Not really sure it matters anymore though. Heck my overclocked GTX 480 pretty much chews through any game I can throw at it and I just turn down a couple settings and BF3 runs great too. If pc gaming doesn't keep progressing these launches lose more and more importance.
 
Damn. Well here's hoping the GK104 brings us some good performance for the dollar for us wanting an upgrade but not willing to pull the trigger on the current expensive 79xx series.
 
Damn. Well here's hoping the GK104 brings us some good performance for the dollar for us wanting an upgrade but not willing to pull the trigger on the current expensive 79xx series.

Here's more rumors on the price and specs. Weren't previous x60s released closer to $200? And $1K for a 690, wow.
 
Damn. Well here's hoping the GK104 brings us some good performance for the dollar for us wanting an upgrade but not willing to pull the trigger on the current expensive 79xx series.

It likely will, $300-$350 for GTX580 performance +/-5%. I think they are playing it smart this time in putting out their mid-range rather than holding out to get out their high-end chip to compete with the 7970. Q3 is pretty poor though if true for their real high end.



Here's more rumors on the price and specs. Weren't previous x60s released closer to $200? And $1K for a 690, wow.

Those are just the same ridiculous lenzfire rumours being re-posted by another site though.
 
Thats a copy and paste from lenzfire. That isn't a new rumor. That is called, plagarism without citing original source. And the original source is probably BS.

On the bottom of the charts they do cite Lenzfire. I hadn't seen the chart before.
 
He has no informations. So nothing changed.

If BigK had his tape-out a few weeks back it will be here around april - july. Look at GF110. Review samples were 1 1/2 months old. And GF110's tape out was not in march 2010...
 
He has no informations. So nothing changed.

If BigK had his tape-out a few weeks back it will be here around april - july. Look at GF110. Review samples were 1 1/2 months old. And GF110's tape out was not in march 2010...

This is much more akin to the launch of GF100 than GF110...

Again, it wouldn't surprise me to see a launch at Q3 or even Q4. That's the price NVIDIA is willing to pay for a huge die and somewhat higher performance.
 
Here's more rumors on the price and specs. Weren't previous x60s released closer to $200? And $1K for a 690, wow.

Hopefully the Attorney General or whoever handles this stuff nails AMD and Nvidia for price fixing again. These prices fall right into line with each other without affecting the others and still leaves the last gen in a good position.

Thankfully I have the final say as to what I will and will not pay. As it currently sits I will not buy another gpu at these prices.
 
He has no informations. So nothing changed.

If BigK had his tape-out a few weeks back it will be here around april - july. Look at GF110. Review samples were 1 1/2 months old. And GF110's tape out was not in march 2010...

Yeah... no. A new arch on a new process with a 550mm2 die is just asking for horrid yields. I've got to agree with Axel here, even Q3 seems optimistic.
 
This is much more akin to the launch of GF100 than GF110...

Again, it wouldn't surprise me to see a launch at Q3 or even Q4. That's the price NVIDIA is willing to pay for a huge die and somewhat higher performance.

Depends on the specs.

If NVIDIA is doubling specs while AMD is only increasing ~40% differences might be larger.
 
He has no informations. So nothing changed.

If BigK had his tape-out a few weeks back it will be here around april - july. Look at GF110. Review samples were 1 1/2 months old. And GF110's tape out was not in march 2010...

Uhh, what. It takes 6-8 months after average *after* tapeout for a product to be released. Following a tapeout you get engineering samples that go through testing, tweaking and validation. Furthermore, all of Charlie Fermi leaks to my knowledge ended up being correct. Feel free to google and check
 
He has no informations. So nothing changed.

If BigK had his tape-out a few weeks back it will be here around april - july. Look at GF110. Review samples were 1 1/2 months old. And GF110's tape out was not in march 2010...

A huge chip will NOT make it to release silly on its first spin. No way. More than one spin Will be required. So Sept/Oct is much more likely than April/July.
 
Yeah... no. A new arch on a new process with a 550mm2 die is just asking for horrid yields. I've got to agree with Axel here, even Q3 seems optimistic.

You know that nVidia has Kepler-GPUs since months? That they know how to optimise their process tools? That's the reason why every Fermi Chip after GF100 came with A1 (tape out) to the market.
 
LOL:biggrin:
Actually it looks like the first money went on GK100....R.I.P 😉
Well, at least that would explain why Kepler is so late. You can't burn a chip design and then magically recoup the engineering hours that went into producing it.

NV probably thought they had the inter-connect problem well in hand after the GF110 but it seems like their traditional weakness in process implementation bit them in the behind @ 28nm.

That, or their 28nm design tools just couldn't accurately emulate crosstalk between interconnects - again.
 
You know that nVidia has Kepler-GPUs since months? That they know how to optimise their process tools? That's the reason why every Fermi Chip after GF100 came with A1 (tape out) to the market.

Maybe GK106 samples, but GK110 as of now is nothing more than an architecture design. If there were samples in the wild we'd know and they would've shown it at recent industry events.

AMD has a much better grasp than NVIDIA when it comes to launching new GPUs on new process nodes. Now, we don't know if the die size is in fact that big. If it is, don't be surprised if it launches at the end of the year and consumes an astronomical amount of power. Again, NVIDIA is willing to launch products months after if it means they get to retain their single-GPU performance crown at the cost of everything else.
 
Radeon HD 8000 series...

So you think AMD is going to refresh their Cayman Islands GPU's this year, on the same 28nm node, then come out with their new architecture - Sea Islands - next year, again, on the same 28nm node?

4870 series debut - 6/25/08
5870 series debut - 9/23/09
6970 series debut - 12/15/10

Hmmmm.....15 months between each new top end GPU. Something tells me AMD is not going to bring out a new lineup of cards anytime soon.
 
Back
Top