April to June time frame is Q2. I have a good feeling about this time frame and couldn't imagine them being any later than that as they are already late out of the gate. Kudos to AMD for being on time and taking advantage of this unchallenged market.Japanese site 4Gamer.net reports that the entry-level GK107 card could be the first model of Nvidia's new 28 nm GPU series and arrive with a 128-bit memory interface as well as GDDR5 memory. The GK106 will follow as a mainstream version and apparently use the same GPU core, but support a 256-bit interface as well as PCI Express 3.0, instead of PCIe 2.0 in the GK107.
A performance version GK104 is due in Q3 and will use a 384-bit memory interface and integrate 1.5 GB of memory. According to 4Gamer.net, the card will deliver a single-precision floating point performance of 2 TFlops. A high-end GK110 apparently scheduled for Q4 uses two GK104 cores and deliver about 4 TFlops while the flagship model GK112 isn't scheduled to be released before 2013 and arrive with a 512-bit GDDR5 interface.
I also expect Nvidia to come out stronger than everyone is expecting much above 7970 performance. I'm sure Nvidia is thinking ahead and will be prepared for any AMD refresh that will have to come out to just compete. Time will tell to set the record straight and we can all speculate anyway we'd like."We are on track with our Kepler roadmap. We have 28nm silicon in house now," said Igor Stanek, Senior Product PR Manager at Nvidia during an interview with the Fudzilla website.
"Our transition to 28nm is going better than 40nm, and yields are better than our original plan," concluded the company's rep without going into any details regarding Kepler's roadmap.
However, over the course of the last few months, multiple Nvidia representatives have said that the first Kepler-based graphics cards aren't expected to arrive until Q2 of 2012, so this is probably the timeline that Stanek is referring to.
Before Kepler arrives, the GPU maker is expected to release a series of die shrinks of Fermi built using TSMC's 28nm fabrication process.
The first chips based on the Kepler architecture were taped out by Nvidia at the beginning of September.
Kepler is the code name used by Nvidia to refer to its next-generation graphics processing unit architecture, which, just like AMD's Radeon HD 7000 GPUs, will be manufactured using TSMC's 28nm fabrication process.
The new graphics core is expected to be more flexible in terms of programmability than the current Fermi architecture.
In the second half of 2010, Nvidia promised that Kepler, and its successor Maxwell, will include virtual memory space (allowing both the CPU and the GPU to use a unified virtual memory) and pre-emption support, as well as a series of other technologies meant to improve the GPU's ability to process data without the help of the system's processor.
According to previous Nvidia estimates, these changes, combined with the new manufacturing process, should deliver 3 to 4 times the performance per Watt of the Fermi architecture in double-precision 64-bit floating point operations.
^^ completely agree. I was thinking of either doing sli for my 580s or selling my 580 for a 780... but really i can play bf3 on high 2xmsaa @60fps... i dont really need ultra or 4x msaa especially considering the hassle and the cost. I can max pretty much everything else out.Originally Posted by Exostenza
Coming from an amd perspective I was going to sell my 6970 and grab a 7970, but then I realized there isn't a single game I need it for. Until the new generation of consoles cone out I wont be needing the power of the new Gen so I might as well save my money and buy it when it is appropriate for my pc gaming needs. Nothing I have doesn't run maxed out at 1080p at the moment. That includes bf3.
I used to always want the latest although that I've seen where it gets me in a world of console ports I see my money is best saved or spent on something else.
Just my 2 cents.
Sent from my HTC EVO 3D X515a using Tapatalk