Doesn't Jaguar have similar IPC to Piledriver despite using 6mm2 for 2 cores compared to 21mm2 for one Piledriver module? That would be pretty telling in itself.
That was before AMD internally reorganized their priorities and externally published this:
Where do you see steamroller (a big-core produced on bleeding-edge technology) sitting in the above infographic? On the left or on the right?
That tells you where it sits as a priority within AMD, which should also give some indication of why AMD isn't making it a huge priority to get preliminary results or much in the way of leaks/previews/marketing about it into the public domain.
Doesn't Jaguar have similar IPC to Piledriver despite using 6mm2 for 2 cores compared to 21mm2 for one Piledriver module? That would be pretty telling in itself.
iirc we didn't have much info on jaguar or the gpu families either. We might get hard numbers some time soon though. If steamroller is another 15%(including clocks) there is no need for AMD to go about advertising it as such. Also that pic seems like the design goals of the big cores have been changed after bd release.
And they aren't even using soi now, it isn't bleeding-edge.
Globalfoundries, the world’s second largest contract maker of semiconductors, will start to produce test wafers using its hybrid 14nm eXtreme mobility (XM) process technology as soon as in the first or second quarter of 2014. Early adopters of the technology will be able to produce their test circuits to find out the pros and cons of the process. Unfortunately, the main customer of GlobalFoundries, will not be able to benefit from the 14nm XM FinFET technology.
The 14nm-XM offering is based on a modular technology architecture that uses a 14nm FinFET devices combined with 20nm-LPM process back-end-of-line (BEOL) interconnect flow. Leveraging the maturity of the 20nm-LPM technology will enable a rapid time-to-market as well as a smooth transition for customers looking to tap the benefits of FinFET system-on-chips as soon as possible. According to Globalfoundries, 14-nm FinFETs have a 48-nm fin pitch, which is identical to what Globalfoundries expects about Intel's FinFET fabrication process.
Mike Noonen, executive vice president of worldwide marketing and sales, told EETimes web-site that 14XM mutiproject wafer (MPW) runs could take place in the first or second quarters of 2013 and would be used by early adopters of the process to run test circuits.
Globalfoundries seems to have a clear roadmap for both SOI as well as fully-depleted SOI at 28nm and 20nm. But those technologies use traditional planar transistors, not innovative FinFET transistors, which means that AMD will not be able to match Intel’s performance and power saving capabilities (Intel claims that tri-gate transistors enable 37% higher speed, or 50% lower power consumption compared to planar transistors) in the foreseeable future; at least, till Globalfoundries and its partners develop ultra high-performance 14nm process technology.
Specifically, to get a 30% increase in performance over 28nm bulk LPS PolySiON, HPP increases die cost by 30%, while FD-SOI only increases die cost by 10%. (Both HPP and FD-SOI are HKMG/GateFirst).
There were tape outs for 28nm-SLP from GlobalFoundries in the August to October time frame in 2011.28nm in production at GloFo since 2011 Gotta love the marketing BS.
There was tape outs for 28nm-SLP from GlobalFoundries in the August to October time frame in 2011.
More trouble with GF?
Although it's been a painful road, Hector Ruiz saved AMD by buying ATI. Otherwise AMD would have been left to battle Intel in processors and have nothing else worth mentioning in their arsenal.
Ruiz was basically a terrible manager and let his ego cloud his decision making, but credit where credit is due it took a lot of guts and foresight to realize that the CPU/GPU marriage would eventually become THE device.
Really, an apu is "THE device"? Is so why is amd at about 20% market share, still losing money, while Intel still makes a huge profit each quarter?
28nm in production at GloFo since 2011 Gotta love the marketing BS.
Well to be fair 28nm SOI is assumedly better than 22nm bulk, though how does it compare to Intel's FinFET(at the same node) is something worth looking into. So in essence GF >>> Intel, at least as far as marketing slides are concernedAtleast they moved on from the 2010 with 28nm
Exactly. Besides that if AMD had not bought ATI and instead could have done proper R&D for CPUs and process tech who knows were they would be now. I very much doubt they could be any worse of than now.
$5.5 billion for ATI would be a pittance today and would barely buy a cutting edge fab.
So I guess AMD would have done better than GF has with their $15 billion+ capex over the past 3-4 years, including $2 billion on one R&D facility? You guys must have a really high opinion of AMD and their ~$1 billion annual R&D budget for the entire company!
$5.5 billion for ATI would be a pittance today and would barely buy a cutting edge fab.
Common platform committed to using bulk for 28nm so AMD had no choice. Going forward, FD-SOI is certainly a possibility.
Idontcare said:I really have to wonder what isn't being said though because if it really was as simple as pushing a button and porting your existing bulk-Si design to an FD-SOI flow, saving yourself 20% production cost in the process, then everybody on the planet that is fabless would be clamoring to have their chips ported over ASAP.
Doesn't Jaguar have similar IPC to Piledriver despite using 6mm2 for 2 cores compared to 21mm2 for one Piledriver module? That would be pretty telling in itself.
Well, it may be a pittance, but isn't 5.5 billion about twice the entire market cap of AMD today?
So I guess AMD would have done better than GF has with their $15 billion+ capex over the past 3-4 years, including $2 billion on one R&D facility? You guys must have a really high opinion of AMD and their ~$1 billion annual R&D budget for the entire company!
$5.5 billion for ATI would be a pittance today and would barely buy a cutting edge fab.