Thursday, May 1st 2014
New GTX TITAN-Z Launch Details Emerge
NVIDIA's GeForce GTX TITAN-Z missed the bus on its earlier 29th April, 2014 launch date, which was confirmed to the press by several retailers, forcing some AIC partners to content with paper-launches of cards bearing their brand. It turns out that the delay is going to be by just a little over a week. The GeForce GTX TITAN-Z is now expected to be available on the 8th of May, 2014. That will be when you'll be able to buy the US $3,000 graphics card off the shelf.
A dual-GPU graphics card based on a pair of 28 nm GK110 GPUs, the GTX TITAN-Z features a total of 5,760 CUDA cores (2,880 per GPU), 480 TMUs (240 per GPU), 96 ROPs (48 per GPU), and a total of 12 GB of GDDR5 memory, spread across two 384-bit wide memory interfaces. Although each of the two GPUs is configured identical to a GTX TITAN Black, it features lower clock speeds. The core is clocked at 705 MHz (889 MHz on the GTX TITAN Black), with GPU Boost frequencies of up to 876 MHz (up to 980 MHz on the GTX TITAN Black); while the memory remains at 7.00 GHz. The card draws power from a pair of 8-pin PCIe power connectors, and its maximum power draw is rated at 375W. It will be interesting to see how it stacks up against the Radeon R9 295X2 by AMD, which costs half as much, at $1,500.
Source:
ComputerBase.de
A dual-GPU graphics card based on a pair of 28 nm GK110 GPUs, the GTX TITAN-Z features a total of 5,760 CUDA cores (2,880 per GPU), 480 TMUs (240 per GPU), 96 ROPs (48 per GPU), and a total of 12 GB of GDDR5 memory, spread across two 384-bit wide memory interfaces. Although each of the two GPUs is configured identical to a GTX TITAN Black, it features lower clock speeds. The core is clocked at 705 MHz (889 MHz on the GTX TITAN Black), with GPU Boost frequencies of up to 876 MHz (up to 980 MHz on the GTX TITAN Black); while the memory remains at 7.00 GHz. The card draws power from a pair of 8-pin PCIe power connectors, and its maximum power draw is rated at 375W. It will be interesting to see how it stacks up against the Radeon R9 295X2 by AMD, which costs half as much, at $1,500.
105 Comments on New GTX TITAN-Z Launch Details Emerge
but for the last part i am totally following you
i guess lower clock is what you get for a air cooling solution and a tdp of 375w, maybe with a 3x8pin ... but again the price point of the 295x2 is the main force and if you take a OC 295x2 like the Sapphire even in Gflops the Z is behind... i would love to see a 790(Ti) but for the moment the 295x2 is my favorite, even if the hybrid cooler is a little hindrance due to the place needed for the radiator, just for user who want two of them, me with only one i would be happy :D
500w versus 375w well ... for power efficiency the Z hold the lead but at what price ...
If the whole idea is a PR stunt for the halo, then Nvidia should just go nuts at pay no heed to the PCI-SIG. Supply enough power (3x8pin), add in some binned chips to guarantee 1150-1200MHz boost and be done with it. Maybe take a leaf out of AMD's book and bundle the card with a couple of 740QC's and a 240mm rad just for sh*ts and giggles.
Personally, I find dual cards a waste of time and resources. Benchmarks results (and subsequent conclusions) are heavily dependant upon a working driver profile for SLI/CrossfireX in the chosen games, and when it doesn't work, disabling one GPU is a limited option fix for an expensive cash outlay. If you're looking at productivity/content creation applications that don't leverage SLI/CFX, then that's all good- but it still represents a miniscule number of potential users that require a precise feature set.
I'm guessing, overclocking two 6GB 780's will net a better experience, moreso when you factor in the $1860 saving over the Titan Z.
i can't but agree on the dual gpu card are a wast... even if i like to see them, ofc i would be happy with one 295x2 in my SG09B but a R9 290/290X would be more than enough already.
I understand the arguments.
CON #1: It creates a precedent. A really expensive card, like we never had before. It creates a new (new-new) price bracket for very (very-very) high end cards. We don't want that.
REPLY to CON #1: For every Koenigsegg, there are millions of affordable cars of all sizes and for all purposes. You're not required to buy the Koenigsegg. You can buy the half price Nissan GTR and still go as fast as the speed limit.
CON #2. It's stupid. It makes no sense. I can get INSERT-NAME-HERE card for half the price, or I can get two of the INSERT-ANOTHER-NAME-HERE for even less.
REPLY to CON #2: So what? If we won't push the limits, how will we ever get ahead? You're not required to buy into the crazy-bonkers ragged edge products.
CON #3: It's not as great for mining as the INSERT-NAME-HERE! AMD FTW!
REPLY to CON #3: The world is not just about mining. NVIDIA created an ecosystem in the professional market and they can now get a nice return on that investment. For the professional market, it's a bargain card. If AMD wants in, they must work at it. It's irrelevant that an AMD card is good at certain compute tasks if the companies that write the software for the professional market do not care. And there are good reasons for them not to care, one of the most important ones is that AMD always offloads almost everything to INSERT-COMPANY-NAME-HERE.
The most recent example to this is Mantle. AMD created a lot of buzz, but in reality it offloaded the actual work to the game developers. The same with 3D display technology. AMD offloaded work to some company and then it buzzed it up with the words "free" and "open source". And there are many other examples...
CON #4: Nobody will buy the card. If you buy the card, you're stupid! NVIDIA is stupid! Titan-Z is stupid!
REPLY to CON #4: I hear this argument a lot. People that can afford expensive things are for some reason all stupid. Well... maybe some of them are, but most of them are smarter then most people. And a lot of people will buy this card. They will.
Crazy and stupid are not the same thing.
CON #5: Why would NVIDIA create such a product? The same was asked when Titan came along.
REPLY to CON#5: Because people will buy it. This kind of purchase can be justified in many ways. If you have the money, 'because I can' is enough. NVIDIA thanks you.
CON #6: Whatever.
REPLY to CON #6: Whatever.
The comparison between the car is nonsense too. I would call the R9 295X2 a Bugatti Veyron, and this one would be a cheaper Nissan in real value.
That said, I will buy the card only if it is fairly priced at around 1000 bucks. If you are greedy and want more, no deal. :laugh:
www.geforce.com/whats-new/articles/announcing-the-geforce-gtx-titan-z
If this card makes more sense than 2X Titan Black to professionals then spend the extra money but as long as Nvidia aims this card at gamers for $3,000 then you will continue to see comments like the above posts all over the net from gamers.
This card and it's price tag make ZERO SENSE!
What people should really understand and know is the the "12GB" of Vram is really 6GB
they're doing what they did with the 690 allocating 4GB per GPU
So in the Z's casse 6GB to each GPU which means you really only get 6GB of usable VRAM.
I'm a stout Nvidia/Intel user but this saddens me to see such stupidity.
They are doing what they HAVE done with every dual GPU they have made, AMD does the same thing.
Found a screen shot of the PCB. One crowded PCB, scares me like the GTX590 PCB.
Yah Dual GPU cards have WAY too much heat on a single PCB
LOL
For that price one would have hoped they'd equip it with a decent PCB, I'm sorry but ATI has always been superior, look at the "overkillness" they slapped onto the 295x2.
I expect that with dropping one phase per gpu, the rest are rated a bit higher to compensate, but who knows.
Nevertheless the design looks underpowered. Both Titan too much Zeroes and 295X2 Celsius are failures design wise... they are utterly useless for the given price, R/D cost and other stuff... it is just a check in the book like we had them...