[ToTTenTranz]

Originally Posted by Psycho

Yeah, london is the family consisting of Thames, Chelsea, Heathrow, Wimbledon.. and supposedly the gpus on khrisna and trinity.

Erm.. I can't see "London" in that graph, nor I remember seeing it in any other graphs related to SI recently.

[Lightman]

192bit memory bus? That ahould put xdr2 rumors to rest.

[Snyder]

Originally Posted by ToTTenTranz

Erm.. I can't see "London" in that graph, nor I remember seeing it in any other graphs related to SI recently.

Weeeeell...
Wimbledon, Heathrow, Chelsea, Thames - just enter those terms in the online map of your choice.

[AlexV]

Originally Posted by mboeller

....or everything, including Trinity and Krishna/Wichita are using already GCN.

Not quite probable that one. Also, GCN strikes me as something that will forfeit their density advantage and as such I'd expect it to trickle down far more slowly into the Lolcat/Atom world, but I may be wrong.

[Kaotik]

Originally Posted by Lightman

192bit memory bus? That ahould put xdr2 rumors to rest.

It's not official slide

[ToTTenTranz]

Originally Posted by Snyder

Weeeeell...
Wimbledon, Heathrow, Chelsea, Thames - just enter those terms in the online map of your choice.

Oh okay.

Even then, looking at the lowest performing Thames, it's supposed to carry 2x Seymour's performance. That's 2x the performance of a 160shader, 8TMUs, 4ROPs GPU.

Unless there's another, lower-performance London GPU, that should be the GPU going into the ~9W Krishna.

We may be looking at something like >240 VLIW4 shaders for the successors of C-50 and E-350. That's mighty powerful for a ~11" low cost subnotebook.

[rpg.314]

Originally Posted by AlexV

Not quite probable that one. Also, GCN strikes me as something that will forfeit their density advantage and as such I'd expect it to trickle down far more slowly into the Lolcat/Atom world, but I may be wrong.

GCN will of course be less dense (flops/mm wise), but as long as perf/mm is more (which should be the case), then I don't see why GCN's introduction has to be delayed beyond the usual integration/validation issues.

[fehu]

http://www.dailytech.com/article.aspx?newsid=22831

some info on future amd apu

[fellix]

Source

[3dilettante]

I'm not enamored with the arbitrarily rotated 3d graphs. It only serves to obfuscate differences. If it weren't for the numerical tables, half the time we'd probably guess some of the larger values are smaller based on how needlessly skewed the perspective is.
Were these graphed like this as a joke?

[ToTTenTranz]

It seems IvyBridge's new iGPU will indeed have lower clocks.

All things considered, Intel's new iGPU can only be considered "functional" and not "performant", imo.

[Paran]

Originally Posted by ToTTenTranz

It seems IvyBridge's new iGPU will indeed have lower clocks.

Why do you think so?

[ToTTenTranz]

Originally Posted by Paran

Why do you think so?

Because it scores similarly to the HD3000 in synthetic benchmarks, while supposedly having more EUs.

[Paran]

Originally Posted by ToTTenTranz

Because it scores similarly to the HD3000 in synthetic benchmarks, while supposedly having more EUs.

This is an early ES sample with low clock frequencies both CPU and GPU. I don't think we can make a statement for Retail CPUs based on this early ES. 39% better in Vantage is pretty good considering 2600k GPU clocked 50% higher.

[sebbbi]

Could be also because of early drivers. Everyone seems to optimize first for 3Dmark.

[Paran]

Originally Posted by sebbbi

Could be also because of early drivers. Everyone seems to optimize first for 3Dmark.

ES driver. Launch ready drivers are planned for early next year.

[Psycho]

Originally Posted by fellix

hmmm.. Something is not quite right.. A8-3800 should be the same gpu as 3850, and 2105 is the same HD3000 graphics as 2600k... http://www.guru3d.com/article/amd-a8-3850-apu-review/12


Maybe they are running llano with 1066mhz ddr3 or single channel

[fehu]

yeld problems for Llano confirmed

[hoho]

Originally Posted by fehu

yeld problems for Llano confirmed

http://www.anandtech.com/show/4894/a...obal-foundries

[Arun]

I must admit I thought AMD was getting ripped off by switching to 'good wafer' pricing since it seemed the process should be mature by now, and it looked like nothing more than management panicking at low early yields which were unlikely to be representative of production yields (see: TSMC 40nm, which had an awful start but excellent yields ever since they fixed the via issue, anyone switching to 'good wafer' there too late would have wasted a lot of money).

So I'm both pleasantly and unpleasantly surprised by the fact 32nm yields are still subpar - AMD's management made a very good call, but GF underdelivering is still very bad news for both GF and AMD. It will be interesting to see how TSMC handles the 28nm and High-K transitions - if they do much better, that's going to hurt GF's prospects with 3rd parties a fair bit.

[TKK]

According to Charlie D. it is mostly a Llano-specific problem though, he says both Bulldozer and upcoming Trinity have much better yields.

http://semiaccurate.com/2011/09/28/a...ll-in-one-day/

[DavidC]

Originally Posted by Paran

This is an early ES sample with low clock frequencies both CPU and GPU. I don't think we can make a statement for Retail CPUs based on this early ES. 39% better in Vantage is pretty good considering 2600k GPU clocked 50% higher.

According to this site, Ivy Bridge's GPU is at 400-900MHz(latter speed is Turbo). Compared to 850-1350MHz on Sandy Bridge.

http://translate.google.ca/translate...26prmd%3Dimvns

[fehu]

some early problem with 22-3d?

[TKK]

Originally Posted by fehu

some early problem with 22-3d?

Even if there was, these numbers are still pretty bad news for AMD, if true.

Up to 40% faster than SB-GPU at ~half the clockspeed? Trinity better be good, 'cause final silicon IB will probably eat Llano for breakfast (driver stability and image quality might be a different matter, though).


As for Trinity, it looks like the CPU part won't be much faster than Llano; reviews show the 3.6 GHz (+Turbo) FX-4100 losing against A8-3850 in gaming performance, that means BD's IPC/core in games is a whopping ~25-30% lower than Llano's. So even with the 10% higher IPC promised for Piledriver cores, Trinity will need at least 20% higher clockspeeds just to beat Llano on the CPU side.

So if IB's GPU is as much of a step forward as it appears to be (in terms of performance/clock at least), Trinity's Devastator GPU has to be a considerable step forward compared to Llano as well, otherwise Intel might actually beat AMD in both areas...

Time to sell my remaining AMD stock, I guess.

[DavidC]

Originally Posted by TKK

Up to 40% faster than SB-GPU at ~half the clockspeed? Trinity better be good, 'cause final silicon IB will probably eat Llano for breakfast (driver stability and image quality might be a different matter, though).

I don't think it'll be THAT bad. But if its true, it seems Intel's target with IVB in graphics is where Llano is at. Turbo works pretty well on Sandy Bridge, which is why the gain will be more like 40-50% over what its doing now rather than 2x.