12-07-11, 02:48 AM
|
#61 | |
|
Registered User
Join Date: Apr 2007
Location: UK
Posts: 2,510
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Keplar will be more powerful than the GTX 590. It's a no brainer...
|
|
|
|
12-07-11, 03:33 AM
|
#62 | |
|
Registered User
Join Date: Mar 2003
Location: Utah
Posts: 2,263
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
|
|
|
|
|
12-07-11, 09:23 AM
|
#63 | |
|
Registered User
Join Date: Jul 2004
Posts: 574
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
|
|
|
|
|
12-07-11, 03:39 PM
|
#64 | |
|
Registered User
Join Date: Nov 2011
Posts: 32
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
I mean, other than the 580, what good did the 5xx series do for speed? Yes less heat, but.. 460 = 560 470 = 560 ti 480 = 570 580 was the only true step up. 590 offers way too much performance to be taken down so quickly, I get the 28nm process but for years now, nothing ever materializes the way it's rumored to, there's always a heat issue, or a power issue, etc. ALWAYS.
__________________
AMD Phenom ll x4 965 Black Edition @ 4.0GHZ - Kingston 8GB DDR3 1600Mhz - ASUS M5A97 EVO - eVGA nVidia GTX 570 1.25GB - 700W Cooler Master PSU - nVidia CM Case |
|
|
|
|
12-07-11, 04:55 PM
|
#65 | |
|
Registered User
Join Date: Mar 2003
Location: Utah
Posts: 2,263
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
|
|
|
|
|
12-07-11, 05:48 PM
|
#66 |
|
|
Resident Alien
Join Date: Jan 2005
Posts: 6,776
|
Quote:
|
|
|
|
|
12-08-11, 09:26 AM
|
#67 | |
|
Registered User
Join Date: Jul 2004
Posts: 574
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
I'm not going to say if its going to be faster or slower than the 590, I just don't see how you can come to your reasoning. |
|
|
|
|
12-08-11, 11:15 AM
|
#68 | |
|
Registered User
Join Date: May 2005
Posts: 17,986
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
As far as everything else I'd say you're 100% correct. Today's hardware is so powerful it is insane. And we're not going to see any games that just have that "wow" factor to them untill the next generation of consoles is released as those will be supporting top end PC features such as tessellation and possibly even some form of physics acceleration. Those new consoles will have hardware that is leaps and bounds above the present gen consoles and so the new games targeting those consoles will have insane graphics and we'll finally see titles more worthy of our PC hardware. But we've a bit of a wait for that unfortunately. Probably at least 2 more years imo, maybe longer. I am looking forward to it, however.  |
|
|
|
|
12-08-11, 11:46 AM
|
#69 | |
|
Resident Alien
Join Date: Jan 2005
Posts: 6,776
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
|
|
|
|
|
12-08-11, 12:47 PM
|
#70 | |
|
Registered User
Join Date: May 2005
Posts: 17,986
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
Anywho been thoroughly pleased with the three recent AMD cards I've owned. Unless they completely screw the pooch I'll be picking up a 7 series card once they're available, and I'm looking forward to it. |
|
|
|
|
12-08-11, 05:59 PM
|
#71 | |
|
Registered User
Join Date: Mar 2003
Location: Utah
Posts: 2,263
|
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
 Reasoning being, 28nm doesn't have the performance scaling to double performance. Leakage is getting worse, this is why Intel switched to 3-d gates at 22nm, performance characteristics are getting worse and worse for each shrink, for traditionial processes. For example, from 4870->5870 doubled and in some cases more than doubled resources, more than doubled transistor count, from 953 million to 2.15 billion, and increased clocks. Yet performance scaling was only generally in the 60-70% range. If even if we expect kelper to be over 6 billion transistors, as massive or more massive than fermi was(which I don't) and thus double resources, its not going to get 100% scaling. Also, at best, they can only get ~50% more bandwidth unless they go back to 512 bit bus, which makes it even bigger, maybe GTX 280 size. Even that 50% is going cost them a big chunk fo die size for a better memory controller. Reportedly the memory controller from 4870 -5870 had to double in size to handle the faster clocks, also reportedly this is the reason for fermi memory controller not being able to scale up very well beyond 4ghz, because its not beefy enough. I don't see any way they can make kepler beat a 590 unless its in some benchmark that previously had some odd bottleneck that they've fixed, ala Heaven bench. The hard info we have is that DP is "over 1 Tflop" on kelper, which while its not specific, it kind of gives us a ballpark. Thats only a 25-30% increase. If it was closer to 1.5, or so which would be close to double performance, they probably would have bragged up "over 1.5 Tflop" right? Seems to me that they aren't going for such a huge chip this time, and are trying more for efficency per die area. Edit: On the "two different architectures" thing, reports are kelper is mostly a die shrink of fermi without too much new. /shrug |
|
|
|
|
12-08-11, 09:17 PM
|
#72 | |
|
Join Date: Nov 2003
Location: Cincinnati, OH
Posts: 1,841
 |
Re: nVidia's 28nm Kepler expected to hit stores in late 2011?
Quote:
|
|
|
|
 |
| Thread Tools | |
|
|
