Richland & Kabini rumours

[parvadomus]

I can see this:
Bulldozer = Netburst
Jaguar = Pentium M (then Core and Core 2)

[NostaSeronx]

Originally Posted by parvadomus

I can see this:
Bulldozer = Netburst
Jaguar = Pentium M (then Core and Core 2)

Not going to happen, Dozer fam might outlast Cat fam.

[pablo87]

Originally Posted by mrmt

Lack of transparency in AMD isn't restricted to the WSA, but to every single subject you can think of. You just have to look on how few items are disclosed on their annual report. Revenue breakdown, COGS breakdown, margin forecast, margin per segment, roadmaps, all this isn't fully disclosed on AMD SEC fillings or even answered in the Q&A.

Look on how different companies deal with roadmap for example. We already know what Intel will launch in 2013, and we already know what Qualcomm will have in 2013. We had a good idea on how these products would work and the launch time frame. And they have been consistently delivering in the last few years. Now have a look at AMD. We don't know what AMD will launch in 2013 and how it will perform. Only Kabini is being disclosed, Richland, which comprises a significant part of AMD business, comparable to Brazos if you look at revenues, is a huge "?". And 2014? We already know where Intel will go, and Qualcomm, and even Nvidia for that matter. But can you say the same about AMD? No.

Same with forecasts. Intel gives revenue and margin forecasts for the entire year, AMD, pff, not even for the next quarter.

Just look on what Kumar tried to do at the last WSA Q&A. Have we been dealing with an honest and transparent company, they should step forward and mentioned that there would be no waiver and that all chips would go for GLF, but instead Kumar kept mum about the subject until directly inquired by an analyst.

I could spend the entire day recalling AMD quarterly calls and how they omitted important information from the investors, information that could change the perception from investors, but I think the point is already clear enough.

With the WSA AMD is just proceeding with their business as usual attitude, but this time what is really hurting is that the WSA is a potential liability worth many times the value of the company now. For example, how much is the new take-or-pay charge if AMD decide to not purchase chips from AMD? Are there safeguards to protect AMD from GLF delays or low yields? Are the purchase commitments a temporary relief or they are a new definitive level (I think they are not definitive, more on that later)? You can't really do a long term investing decision on AMD without answering these questions, and so far AMD still refuses to provide them.

I'm yet to see AMD cross the red line in lying straight face to investors, but the lack of transparency on these sensitive issues is almost on par with that.



You know, one of the jokes in the O&G sector is that the most profitable business of the world is a poorly managed oil company. I disagree. The most profitable business of the world is AMD foundry. No matter how much you screw up, your customer will still pay you a lot of money.

Completely agree. Honestly nobody should invest in AMD and nobody should recommend AMD because of this. It's worse than a penny stock in many ways because being the only other sizable x86 CPU provider, it must be a decent investment, right? Wrong.

Also, what they don't realize is whatever negatively affects long term investors has the same effect on corporate buyers...uninvestable and unbuyable go hand in hand.

PS - Kumar now officially CFO.

[USER8000]

Entered thread looking for info about some of the 2013 AMD CPUs - however it appears the cake is a lie as the thread seems to be about stocks and shares not CPUs.

[Haserath]

Originally Posted by USER8000

Entered thread looking for info about some of the 2013 AMD CPUs - however it appears the cake is a lie as the thread seems to be about stocks and shares not CPUs.

Kabini:
Upgraded Bobcat core(instruction sets, 128-bit, IPC, & clocks)
Up to 4 cores
GCN based graphics-Possibly 2 CU?
Up to 25W TDP

Temash:
Upgraded BC core
1-2cores
GCN based GPU

Richland is a big ?

And the big cores are MIA.

Does that about wrap things up for the info we have now?

[piesquared]

Not quite, HD8000.

[Haserath]

That's GPU.

[Zor Prime]

I don't know about any of you but I would love to know what Jim Keller is up to.

[piesquared]

Originally Posted by Haserath

That's GPU.

It's more of a cluster of compute units.

[NostaSeronx]

Originally Posted by Haserath

Kabini:
Upgraded Bobcat core(instruction sets, 128-bit, IPC, & clocks)
Up to 4 cores
GCN based graphics-Possibly 2 CU?
Up to 25W TDP

Temash:
Upgraded BC core
1-2cores
GCN based GPU

Kabini:
Up to 4 Jaguar Cores(Up to AVX1.1+HSAIL, 20% aggregate improvement same TDP)
GCN 2.0 2 CU (<128)
Up to 18 Watt TDP
1.6 GHz - 2.2 GHz

Temash:
Up to 4 Jaguar Cores(Up to AVX1.1+HSAIL)
GCN 2.0 2 CU (<128)
Up to 9 Watt TDP
1.0 GHz - 1.4 GHz

Richland:
Up to 4 Piledriver "2013" Cores(Up to AVX1.1+HSAIL)
GCN 2.0 6 CU(<384)
Up to 100 Watt TDP
2.4 GHz - 4.4 GHz

All 28-nm GlobalFoundries.

[Haserath]

Temash up to 4 cores? Seems like a waste just like Tegra 3. Too many cores, not enough speed per core, unless they have a good turbo.

I guess it makes some sense if they use the same dies for both.

[happysmiles]

but will it run Crysis?

[MightyMalus]

Originally Posted by happysmiles

but will it run Crysis?

Well, yeah, since the E2-1800 already seems to do so, run Crysis 2 that is.

[CTho9305]

Originally Posted by NostaSeronx

Kabini:
Up to 4 Jaguar Cores(Up to AVX1.1+HSAIL, 20% aggregate improvement same TDP)
GCN 2.0 2 CU (<128)
Up to 18 Watt TDP
1.6 GHz - 2.2 GHz

Temash:
Up to 4 Jaguar Cores(Up to AVX1.1+HSAIL)
GCN 2.0 2 CU (<128)
Up to 9 Watt TDP
1.0 GHz - 1.4 GHz

Richland:
Up to 4 Piledriver "2013" Cores(Up to AVX1.1+HSAIL)
GCN 2.0 6 CU(<384)
Up to 100 Watt TDP
2.4 GHz - 4.4 GHz

All 28-nm GlobalFoundries.

...source?

[parvadomus]

I think they will use TSMC, as they already have their GPUs on that process.

[Homeles]

Originally Posted by CTho9305

...source?

He's NostaSeronx. He's his own source.

[NTMBK]

Hey Nemesis, go listen to Anandtech's Podcast 13, from about 46 minutes onwards. There's something in there you should probably listen to.

[Nemesis 1]

Can't listen to pobcast I have to reset . If its about the delay . Me and Robert talked about a half an hour today about it . He reading this topic from vegas hotel room and called me today . Ya its sucks that we won't see devices until 2014. But valley view will be shipping in 2013. Robert also told me to wait till I see the Z5280s W . Its a bit differant than the tablet atom has now According to him the GPU performance is amazing for device that size according to Robert . I see the Z2580 as being faster than Tegra 4 in compute
As for the graphics we have to see whats up . Its a good thing that its a new year or I would be moving away from intel . But ya this is stike 1 for 2013. Intel gen 7 is one reason Robert gave me for the delay . The other reason has something to do with 4G. and the fact that the z2580 performs strong

[USER8000]

Originally Posted by Haserath

Kabini:
Upgraded Bobcat core(instruction sets, 128-bit, IPC, & clocks)
Up to 4 cores
GCN based graphics-Possibly 2 CU?
Up to 25W TDP

Temash:
Upgraded BC core
1-2cores
GCN based GPU

Richland is a big ?

And the big cores are MIA.

Does that about wrap things up for the info we have now?

Originally Posted by NostaSeronx

Kabini:
Up to 4 Jaguar Cores(Up to AVX1.1+HSAIL, 20% aggregate improvement same TDP)
GCN 2.0 2 CU (<128)
Up to 18 Watt TDP
1.6 GHz - 2.2 GHz

Temash:
Up to 4 Jaguar Cores(Up to AVX1.1+HSAIL)
GCN 2.0 2 CU (<128)
Up to 9 Watt TDP
1.0 GHz - 1.4 GHz

Richland:
Up to 4 Piledriver "2013" Cores(Up to AVX1.1+HSAIL)
GCN 2.0 6 CU(<384)
Up to 100 Watt TDP
2.4 GHz - 4.4 GHz

All 28-nm GlobalFoundries.

Thanks.

[Ajay]

Originally Posted by NostaSeronx

Richland:
Up to 4 Piledriver "2013" Cores(Up to AVX1.1+HSAIL)
GCN 2.0 6 CU(<384)
Up to 100 Watt TDP
2.4 GHz - 4.4 GHz

All 28-nm GlobalFoundries.

Up to 4.4GHz? I thought GloFo's 28nm process netted lower clocks (but much lower TDPs)

I thought that this was part of the reason SR was moved to 2014. It doesn't matter if you get a ~30% IPC boost if you lose the benefit due to lower clocks (that and $$s for back end OPs).

[piesquared]

Richland shipping (40% performance increase)
Kaveri second half 2013 (revolutionary HSA features)
Kabini and Temash first half 2013 (capable of leading edge applications and games)
HD8000m shipping (GLOBALFOUNDRIES 28nm low power?)

http://pcquest.ciol.com/content/news...ews+%28PCQUEST

[MisterMac]

40% perf of what?

perf per watt?

ST?

MT?


That's pretty much just a PR piece - no facts.
No anything.
So.. yea.

Also there's noway in hell Richland is PD while Kaveri is SR.
Not that short lag.

[inf64]

Originally Posted by piesquared

Richland shipping (40% performance increase)
Kaveri second half 2013 (revolutionary HSA features)
Kabini and Temash first half 2013 (capable of leading edge applications and games)
HD8000m shipping (GLOBALFOUNDRIES 28nm low power?)

http://pcquest.ciol.com/content/news...ews+%28PCQUEST

Wow man, nice find!
Kabini and Temash were expected to bring some massive perf/watt gains over previous low power Brazos offerings,but Richland and 40% increase? Just amazing if true. Now, anybody remembers the x264 developer who had an early access to Richland ES ~2 months ago? He claimed his sample was specced at 35W TDP and ran at 3.2Ghz . Now AMD has 32nm Trinity part that runs at 2.3Ghz(3.2Ghz Turbo) and has 35W . Simple math applied to base clocks: 3.2/2.3=1.39 or 40% . Suspiciously close to what AMD states for end products based on Richland . No wonder they pushed out Kabini to 2014,who needs a higher IPC product that cannot clock high enough to achieve this kind of performance jump? Smart move .

[Nemesis 1]

Great find almost reads like the BD stuff right up till the ugly truth raised its head .

[mrmt]

Originally Posted by inf64

Wow man, nice find!
Kabini and Temash were expected to bring some massive perf/watt gains over previous low power Brazos offerings,but Richland and 40% increase?.

A move from VLIW to GNC wouldn't yields a 40% increase in GPU compute power in the same TDP? I find this hypothesis far more plausible than some magic dust that would allow 40% increase in clock speed at the same power level.