next gen kepler to support dx 11.1, also take a year to rollout all cards

[ViN86]

Originally Posted by MUYA

I am sure Nvidia learnt from NV30, Fermi as well...

From the sounds of the article, that doesn't seem to be the case.

[Robs07M6S]

Originally Posted by Muppet

Personally, I'm waiting until Kepler is released or solid info from a reliable source. That's when I'll make up my mind which camp I go with next round.

Smart man, if you already have a capable GPU then it will pay off to wait out a few months and see what Kepler is all about before making a decision. More competition between ATI and Nvidia means better prices for the buyer. If kepler is just barely faster than ATI's new cards and ATI in turn lowers the prices a good bit then ATI is where I will be if the difference in cost is large enough.

[Xion X2]

Originally Posted by slaWter

If it won't be what I'm expecting, then I won't upgrade this time. Honestly, I don't have a reason to upgrade anyway. Pretty much everything runs great in Surround and for 1h of gaming every 2-3 weeks or so, there is no point anyway. I don't remember the last time I started my PC. Probably just for some backup tasks. I haven't even updated to the latest iRacing version and that says a lot

Who are you, and what have you done with Slawter?

[Viral]

Some leaked (censored) slides from OBR,



All it tells us is that the clock speed is below 1000MHz, the Cuda Core count is 4 digits (above 999) and that there is no hot clock, as rumoured. So those Lensfire specs are no even more obviously wrong. The other, stating 4096 cuda cores may be correct, but I'm expecting less cores myself.

Also, it (i'm assuming GTX 680) is faster than 7970, on internal benchmarks. As expected. How much? No idea.

EDIT: NVM... it's probably fake

[Roadhog]

Fake...

The fan is from a GTX 550

[Muppet]

Originally Posted by Roadhog

Fake...

The fan is from a GTX 550

I'd say everything up to this point is a fake. Until Nvidia or a reputable site release something, I take it all with a grain of salt.

[shadow001]

Well this is distressing:


http://vr-zone.com/articles/analyst-...012/14806.html


Makes a global overall assesment of Nvidia for 2012, and they're not expecting anything until the second half of the year...

[MUYA]

Originally Posted by shadow001

Well this is distressing:


http://vr-zone.com/articles/analyst-...012/14806.html


Makes a global overall assesment of Nvidia for 2012, and they're not expecting anything until the second half of the year...

And the people making that assessment have 1st hand info from NV themselves? I don't think so

More like they are going by the same rumor mills as all tech websites

[shadow001]

Originally Posted by MUYA

And the people making that assessment have 1st hand info from NV themselves? I don't think so

More like they are going by the same rumor mills as all tech websites

They evaluate the value of a companies stock, and the inner workings of the contracts they received for their current products like tegra, and the companies timetable for future product releases, and you better believe they have to have access to confidential information from Nvidia to see if they keep them on their preffered list as a company that's worth investing into.


They don't read rumors and hearsay like we do, they work on facts and hard evidence for their evaluation.

[Muppet]

[Muppet]

When i read that, all I can think about is Nvidia isn't making Catalyst drivers for ATI

[MUYA]

http://www.3dcenter.org/news/die-akt...rformance-chip

Originally Posted by 3dcenter via Google translator

Product name (top solution): GeForce GTX 680 (is not entirely safe)
28nm production at TSMC, the area approximately 340mm ² (unofficial estimate)
4 Graphics Processing Cluster (GPC)
4 Streaming Multiprocessors (SM) aka shader clusters per GPC, ergo a total of 16 shader clusters for the GK104-chip
96 stream processors (SP) aka shader shader units per cluster, ergo a total of 1536 shader units for the GK104-chip
8 texture units (TMU) aka shader texture units per cluster, ergo a total of 128 texture units for the GK104-chip
32 raster operation units (ROPs)
256-bit DDR memory interface (up to GDDR5)
Chip clock (top model): 950 MHz
Elimination of Hotclocks, no extra clock speed of the shader units more
Single Precision teraflops computing power of 2.9, double precision with 1:6 = 486 DP GFlops processing power, 121 Texturierleistung Gtex / sec
Memory clock (top model): 2500 MHz, memory bandwidth so that at 160 GB / sec
2048 MB of GDDR5 memory configuration