The only questionable aspect of the die shot in terms of "could this be Steamroller?" Is doubling up on the FPUs. It's certainly not an unbelievable layout.
http://hothardware.com/News/AMDs-Next-Gen-Steamroller-CPU-Could-Deliver-Where-Bulldozer-Fell-Short/
SR doesnt double the FPUs.
Not really. I would prefer you wait and see rather than completely agree with me.
No, I said not to be a religious fanatic. What I say is 90% certain to happen.So we have no reason to listen to you?
It does, look again particularly at the arrows that point to the FPU.SR doesnt double the FPUs.
It does, look again particularly at the arrows that point to the FPU.SR doesnt double the FPUs.
Floating Point Execution Unit 1 = Single Thread
Floating Point Execution Unit 2 = Single Thread
It does, look again particularly at the arrows that point to the FPU.
SR is "APU only", right? No discrete CPU SKUs IIRC.
No. AMD announced SR Berlin CPU as well
I wait additional CPUs announced for next year.
It's probably a CPU in the same way that the Athlon 760K is a CPU- they disabled the GPU.
It's probably a CPU in the same way that the Athlon 760K is a CPU- they disabled the GPU.
Joining AMD speakers Lisa Su, senior vice president and general manager, global business units; Mark Papermaster, senior vice president and chief technology officer; and Phil Rogers, corporate fellow, are thought leaders from some of todays foremost technology companies including:
APU13 will feature breakout sessions focused on industry trends in computing. In February, AMD announced two new additions to the conference agenda including a much-requested gaming focus: the 2013 AMD Game Developer Summit. This addition will showcase the latest GPU and APU technologies and their inclusion in the most widespread or next-generation gaming platforms across mobile, tablet, PC, online/cloud and console.
- Mike Muller, chief technology officer at ARM;
- Johann Anderson, chief architect at Electronic Arts DICE;
- Tony King-Smith, vice president of Marketing at Imagination;
- Chienping Lu, senior director of Mediatek USA;
- Nandini Ramani, vice president of development at Oracle Solutions;
- David Helgason, founder and CEO of Unity Technologies;
Maybe or maybe not. At this moment we only know that are CPUs, not APUs.
My biggest concern is that the long rumored lower clocks will turn out to be true. One would hope that AMD would have a couple of SKUs in the 3.0-3.5 GHz range even if it were mainly for show.
Thouses rumours are built upon irrational logic.
What would be the purpose of a 100W 3.5ghz chip that
would have 20% higher perf/mhz but 0% delta in perf/watt.
AMD has clearly stated that high frequencies will be maintained
and that perf/watt would be improved.
You have to consider the overall change to bulk from SOI might have a negative impact as well, if only initially. If things have changed AMD isn't going to go back and revise their slides. Nobody ever does.
I'm not sure why but I'm getting more of a Bulldozer feeling than a Piledriver one about Steamroller. There could be too many big changes there that takes longer to fix that the initial plan was. Obviously I hope I'm wrong.
http://www.techpowerup.com/167884/amd-adopts-28-nm-bulk-manufacturing-in-2013.htmlMonday, June 18th 2012
According to AMD senior VP and CTO Mark Papermaster, the company will adopt the 28 nanometer bulk CMOS silicon fabrication process for its chips in 2013
They officialy aknowledged 100W 2M4C SR , granted the 3.5ghz limitation is true then a 100W 4C SR would perform the same as a 100W piledriver 4C , seriously , why bother making a CPU that
would be not more power efficient , with all the hassle of a new node..?..
One thing that set my alarm bells ringing was Andrew Feldman saying Berlin was "cool". I don't want to hear that it's "cool", I want to hear that it's "awesome". Cool can simply mean different, and obviously with the large IGP it's definitely got a "cool" factor about it in regards servers but I still really would much rather have read "awesome" instead.
SRoller..."What we are doing with the Warsaw Opteron is ripping out cost and power and increasing performance, and it is compatible with the existing G34 socket,"
The Warsaw chip will offer about 20 per cent higher performance per watt than the Opteron 6300, says Feldman
A hint :"Berlin is cool, and it uses a new Steamroller core from us and delivers tremendous compute and power efficiency," says Feldman. "When you have a huge amount of compute in a single-socket part, this is ideal for workloads where performance per watt per dollar and compute density per dollar are paramount."
Finaly , an interesting trend with big consequences :AMD is saying very little about the Steamroller core at this point, except that it offers double the performance of the Jaguar core and will max out with twice the memory capacity, too.
"Will ARM win in servers? And will AMD win with ARM? I think ARM wins in the long run. In the history of compute, small, lower cost, and higher volume always wins. And community always wins. ARM has lower power, but I don't think, in the end, that it wins because it is lower power. It wins because it is lower cost. It takes the process of making a CPU down from three and a half years and $350m and $400m down to 18 months and $30m."
September-October to OEMs, November-Decemeber to DIYs.When does Kaveri ship? Then we will know.
SOI doesn't effect clock rates nor how much logic you can put down. SOI only affects the end outcomes: Yields and Lifespan.You have to consider the overall change to bulk from SOI might have a negative impact as well, if only initially.
They officialy aknowledged 100W 2M4C SR , granted the 3.5ghz
limitation is true then a 100W 4C SR would perform the same as a
100W piledriver 4C , seriously , why bother making a CPU that
would be not more power efficient , with all the hassle of a new node..?...