> the Cell (if you ignored the SPE's) should run the same PPC code.

Yes, it definitely does. The Cell PPE runs stock PPC code as well as AltiVec code. But Cell is the only PPC that runs Cell SPE code. That's the point Zylesea was trying to make.

> we may have some variants in our future anyway if the developers ever
> decide to tackle SMP.

Assuming an SMP capable MorphOS, single-threaded software would run fine on multi-core hardware (using only one of the cores) as well as multi-threaded software would run fine on single-core hardware (running the threads virtually concurrently via preemptive multitasking). There're no code variants required for that.

> Cell and Power8 technology? Damn Andreas, that sounds far too optimistic.
> (although the though gave me a cold chill). Then I think back on your track
> record of predictions so far...

Not so much about my predictions so far, but I just wouldn't know how to interpret that IBM executive's words in any other way.

> let's find someone with deep pockets build something with this

That would have to wait some while still because I predict that POWER8 won't come before 2012 ;-)

> take back PC from those nimrods at Intel.

I doubt POWER8 will be suitable for PC. There would have to be something to POWER8 like G5/PPC970 was to POWER4.

Quote:
LOL.

can we finally bring the talks back

http://www.psdowngrade.com/

Quote:

YouTube warning on video linked by above site:
This video has been removed as a violation of YouTube's policy against spam, scams, and commercially deceptive content.

".. scams, and commercially deceptive content", well that doesn't sound positive.

[ Edited by Jim on 2010/11/15 20:40 ]

Update:

> I predict that POWER8 won't come before 2012

...or 2013. See page 6 of:

http://power.org/wp-content/uploads/2011/03/IBM_March_29_Webinar_-_Dr._Luigi.pdf


Edit: PDF link updated

[ Edited by Andreas_Wolf 18.09.2012 - 23:17 ]

Update:

> Cell and Power8 technology? Damn Andreas, that sounds
> far too optimistic.

"IBM intends to produce the Power8 processor, planned for 2013 (in 28 or 22nm), using 3D stack technology, with a directly linked memory and also, probably, a layer of small specialised computing cores adapted for specific intended uses. It is here that the successors of the Synergistic Processing Units of the Cell processors might turn up; the 3D stacks offer lots of room for modularity."
http://www.h-online.com/newsticker/news/item/Processor-Whispers-About-Chancellors-and-3D-Chips-1206912.html

Wow! The info about Power8's inclusion of what could be considered the successors to the SPEs is interesting.
But the 3D stack technology really tops that off. I hadn't expected that for some time.
The announcement about directly linked memory is a little vague, so I'd be interested in seeing how that plays out.

It sounds like Power8 will be a significantly different platform to code for.
And the 2013 date sounds about right for a PlayStation 4 introduction, although I'd be surprised to see use a derivative of this.

Produced at 22 or 28nm? Should allow for better clocking.

> the 2013 date sounds about right for a PlayStation 4
> introduction, although I'd be surprised to see use a
> derivative of this.

Yes, I'm still doubting that there's a connection between IBM's plans for POWER8 and their voiced intention to provide the CPUs for the successors of the current PPC based gaming consoles. On the other hand, a trimmed version of the POWER8 (including SPEs, also for backwards compatibility to PS3 games) may seem as just the right CPU for the PS4.

>On the other hand, a trimmed version of the POWER8 (including SPEs, also for backwards compatibility to PS3 games) may seem as just the right CPU for the PS4.


After that call, I'd never doubt it.