[DarthShader]

This is not a BD, this is Trinity. It has a different mem controller and different goals, maintaining maximum throughput being not one of them. Going to 256bit will happen someday anyways, the sooner the better.

PS. Source of your claim?

[fellix]

This is comparison of the IGP "uncore" sections of Llano and Trinity -- SIMDs are cut out too. Trinity's section takes 40% more area, compared to Llano's.

[no-X]

Any explanation? Cayman has bigger ROPs (EQAA, faster ops with single/dual-channel FP32, faster Int16, coalesced writes). Maybe VCE and 3rd display pipeline for Eyefinity have some impact, too. But I can't believe that improved ROPs, VCE processor and 3rd display output can be responsible for such a massive difference.

[fellix]

Second setup pipe?

*runs for cover*

[3dilettante]

The pictures do not look like they have an equivalent level of detail, but if the Trinity shot is accurate and no obfuscated, the GPU section looks like it has fewer ordered grids that correspond to SRAM or customized logic than Llano. The kind of featureless pudding inbetween all the storage is visually similar to the RV770 die shot.

Perhaps AMD has allowed the logic on the periphery to bloat, due to more standard cells and automated layout. The logic sections may be physically bigger out of proportion of any transistor count increase, possibly to reduce leakage or variation.

[DarthShader]

http://www.anandtech.com/show/5333/i...cs-at-ces-2012

The second was supposed to be a DX11 racing demo, however the demo itself appeared to be a video of gameplay looping rather than a live demo (video player controls briefly popped up during the demo, tisk tisk).

Anybody would like to bet on Ivy launching without DX11 drivers?

[Alexko]

At this point it wouldn't be surprising, but I can't see many people running DX11 games on Ivy Bridge anyway.

[Paran]

Originally Posted by DarthShader

Anybody would like to bet on Ivy launching without DX11 drivers?

Not me. Final driver were scheduled for January or end December.

[Kaotik]

Originally Posted by Paran

Not me. Final driver were scheduled for January or end December.

Yet now at CES they can't run F1 2011 in DX11, and use video of the game playing on VLC instead.

[DSC]

http://www.youtube.com/watch?v=Otcge1cn8Os

[FUDie]

Originally Posted by DSC

http://www.youtube.com/watch?v=Otcge1cn8Os

Did the system have wood screws as well?

-FUDie

[DSC]

http://www.anandtech.com/show/5359/i...-on-ivy-bridge

I don't even know what possessed Intel to do what they did at CES 2012, but everyone had a good laugh at Intel's expense.

[french toast]

Didnt AMD critisise Intel for using a ring bus to L3 on sandybridge, saying they wouldn't go that route for fear of 'thrashing' the cache and starving the cpu?
I also heard ove at semi accurate that they didnt expect trinity/piledrive to have L3? i dont have an opinion my self, just thought i would throw that one into the mix....

Saying that memory bandwidth has been a bane for all fusion processors, i actually thought the intel system was quite neat, and maybe it caught AMD by suprise, it certainly narrowed the gap to closer than it would have been.

The dozer cores seems to be hampered by lower than intended frequency and cache latency..if they could get the process sorted, and fix those issues it would be competitive enough IMHO.

[french toast]

WTF? i posted that in the other ivybridge v trinity thread and it gets posted in here?

[itsmydamnation]

http://hothardware.com/News/AMD-Fusi...olt-In-Action/

not bad for a 17watt APU.

[ToTTenTranz]

If 17W is the TDP for the whole APU, then this is really impressive, that's half the 35W TDP of the previous notebook Llano APUs.

It would also explain why Wichita was scratched, as that power level had previously been occupied by Zacate.
And if AMD eventually makes a low-clocked single-module Trinity going down to ~10W TDP, it could also explain why Krishna was scratched too.

[sebbbi]

Originally Posted by ToTTenTranz

If 17W is the TDP for the whole APU, then this is really impressive, that's half the 35W TDP of the previous notebook Llano APUs.

It would also explain why Wichita was scratched, as that power level had previously been occupied by Zacate.

Looks like Z-01 replaces the whole 9W C-range (Z-01 is identical to C-50 in every way, but TDP got down from 9W to 5.9W). It's already on production (some shipping Win7 tablets are using it). And Trinity at 17W basically invalidates the whole 18W E-range. It's very interesting to see how the 17W Trinity compares to the 17W i7 3667U Ivy Bridge. 3667U CPU turbos up to 3.0 GHz, so Intel is going to keep the single thread performance crown easily, but Trinity could beat it in four thread performance, and it has likely a slightly faster GPU as well (but Ivy's new GPU isn't that bad either, so Intel is going to offer at least some competition in that area as well).

[ToTTenTranz]

Originally Posted by sebbbi

Looks like Z-01 replaces the whole 9W C-range (Z-01 is identical to C-50 in every way, but TDP got down from 9W to 5.9W). It's already on production (some shipping Win7 tablets are using it). And Trinity at 17W basically invalidates the whole 18W E-range. It's very interesting to see how the 17W Trinity compares to the 17W i7 3667U Ivy Bridge. 3667U CPU turbos up to 3.0 GHz, so Intel is going to keep the single thread performance crown easily, but Trinity could beat it in four thread performance, and it has likely a slightly faster GPU as well (but Ivy's new GPU isn't that bad either, so Intel is going to offer at least some competition in that area as well).

Nonetheless, Intel's ULV cpus have been placed at completely different price points to what AMD has offered so far..
I have my doubts that Trinity will compete with the i7 "U Series" Ivy Bridge at the same price.

It'll probably be Trinity vs. i3 Ivy bridge "CULV" for best price/performance 11.6-13" subnotebooks and i7-U for premium solutions.

That said, Trinity will probably offer substantially better graphics performance than its direct competitor, and CPU performance will be just "good enough".

[AnarchX]

Originally Posted by itsmydamnation

http://hothardware.com/News/AMD-Fusi...olt-In-Action/

not bad for a 17watt APU.

~1:30 in Youtube video: "50% more compute capability at almost half the power".

Do they take the VCE with some hundred GFLOPs into account?

[mczak]

Originally Posted by ToTTenTranz

If 17W is the TDP for the whole APU, then this is really impressive, that's half the 35W TDP of the previous notebook Llano APUs.

Indeed. And Llano couldn't really achieve very impressive clocks at 35W (1.6Ghz non-turbo, 2.5Ghz Turbo), you'd think for two-module Trinity to make sense they'd need similar clocks (well if base clock is a bit lower that would be ok as long as it can turbo up in enough situations).

[Paran]

Originally Posted by Kaotik

Yet now at CES they can't run F1 2011 in DX11, and use video of the game playing on VLC instead.

They can't? People who tried it disagree with you.

http://www.youtube.com/watch?feature...&v=agR-5DF9HZg
http://www.youtube.com/watch?v=PCBy4...eature=related

[hkultala]

Originally Posted by sebbbi

Looks like Z-01 replaces the whole 9W C-range (Z-01 is identical to C-50 in every way, but TDP got down from 9W to 5.9W). It's already on production (some shipping Win7 tablets are using it). And Trinity at 17W basically invalidates the whole 18W E-range

Trinity is about 240-250mm^2 on 32nm. (Llano is 228mm^2 and trinity is slightly bigger)

Ontario is 77 mm^2 on older, cheaper 40nm process.

so over 3 times size difference, even bigger silicon price difference.

So even though Trinity can get to the "power range" of Brazos, AMD can sell Brazos with much cheaper price while still getting profits from the chip.

So Trinity cannot replace bobcat-based chips, there is lots of "low-end market" at 18W.
What trinity can do is compete against those ULV core i3 chips.

[Kaotik]

Originally Posted by Paran

They can't? People who tried it disagree with you.

http://www.youtube.com/watch?feature...&v=agR-5DF9HZg
http://www.youtube.com/watch?v=PCBy4...eature=related

Yes, it was corrected later and press got to see it too - however on their official stage they used VLC video while claimed it to be game playing on the machine

[sebbbi]

Originally Posted by hkultala

So even though Trinity can get to the "power range" of Brazos, AMD can sell Brazos with much cheaper price while still getting profits from the chip.

So Trinity cannot replace bobcat-based chips, there is lots of "low-end market" at 18W.
What trinity can do is compete against those ULV core i3 chips.

Of course, but in the long run Brazos seems to be fading away. There has been basically no progress in one year now (0.05 GHz overclock with E450, and another 0.05 GHz coming up later this year). Z-01 at 5.9W (1/3 of Brazos TDP) is not that far behind in performance (and is really cheap to produce), and Trinity offers much better performance at same TDP. If either the Z-01 is scaled up or Trinity is scaled down (single module version would be considerably cheaper to produce and wouldn't likely need agressive cherry picking to reach 17W), there would not be much room left for Brazos anymore. Too bad Deccan, Wichita and Krishna all got canned (28 nm would have made the E-series much more competitive in the long run).

[Kaotik]

Originally Posted by sebbbi

Too bad Deccan, Wichita and Krishna all got canned (28 nm would have made the E-series much more competitive in the long run).

I haven't seen any signs of Wichita & Krisha being canned, there were a lot of false news about how they need to "redesign them for TSMC" which was obviously false, it was known like 6 months before those news that at least part of Wichita and/or Krishnas will come from TSMC.