Just to maintain that IBM tradition where a new CPU meant a new OS and therefore twice as much pain to the customer. Heck, they might even release the new version with clustering this time....

Since mainframes have a long history of unloading tasks to auxillary components, this doesn't suprise me in the least. CPUs with multiple FPUs are old hat, and the Cell fits that bill just fine, doesn't it? Unix machines have been ofloading tasks to multiple hardware for 20 years. Of course IBM is going to be producing some really fun kits.

It may be a bit premature to comment on optical chip interconnects, though. You could be talking about three years instead of two to get some of the problems ironed out.

yeah, but dud they inprove the Alitvec Unit ;)

the x86 boxes are finally almost catching up, its about time they improved the Alivec and put this upgraded tech into the SOC units,for the likes of Efika 2/3 use sometime soon, a generic and cheap ,yet powerful, multi PPC CPU SOC with internal FPG'a for video codecs on the fly at the very least.

the worlds about the very small as well as the very big, why do they ignore the Altivec unit just because its served them so well without an update for many a year...

make it and they will come, mass market PPC SOC based wireless routers and in car AVC decoding at the very least could use an update for todays markets and beyond, wake up please or we will have x86 +FPGA in that space too....

In the real world things like optical interconnects are hard to pull off only marketing (said with a sneer and a spit) would make statements about it without a working model so I take the silence for what it is caution.Meanwhile what is Intel doing I doubt they are sitting around waiting for IBM to kill them on the high end.

Yes IBM have a recent history of releasing new CPU's and a new version of the OS (AIX) simultaneously but you only actually need the new version of AIX if you want to leverage the CPU for some of it's more advanced features.

Running older versions of AIX on newer chips would always enhance or rather augment the performance/price point you just wouldn;t get the advanced fetures, this is where you would need the OS Upgrade, but then you are making a business decision, unless of course you just want to play.

Seems to me if he says they looked at optical for Power6, decided against it, but are looking at it again for Power7... that means exactly that. Maybe this time Power7 will have optical, but only if this time it's worth doing, so to me that seems like it's just an off chance.

I want off the shelf 100GbE optical in the home.. cheap interconnect chips in my PCs that let me modularly stack computing resources... IBM, bring us your mainframe and server chipset technology to the home enthusiast.. I'm tired of being trapped in the intel MS hole.. IBM is the king of Virtualization technology.. I want it in my home.. :)

I want to buy level 2 processor cache modules that can optically interconnect with the processors.. I want processor modules that are electrically isolated from my host motherboard and interconnected via dense strands of optical interconnects. let's modularize the PC so components can stack like cell's to grow as big as my money can buy.

32nm 100GbE multi-core interface chips need multi-vendor standardization and mass production. Let's skip the 10GbE standard and go straight to the future. If a good number of partner vendors came together with IBM on the 32nm technology, a very advanced SoC 32nm controller chip with features such as tcp/ip offload engine, iSCSI processing, advanced QoS/firewall/SPI/etc could be devised that would make 100GbE an instantly adopted standard.