One has to think at some point these heterogeneous chips will end up in the clouds.  I keep thinking, can even graphics processing be done remotely and the results spooled out (over HDMI, or something) back to a wireless client.   Heterogeneous design with everything tied together in a cloud, deciding where to put the app, or app service, sounds radically efficient.   And I was calling for divergent rather than convergent paths for technology, oh, in 1993.   We don't all have the same Swiss Army knife, and many of us host a silver service set in our home.

A few years ago a company called Ohio Scientific came up with a 'one size fits all' solution that incorporated three families of microprocessors on one board. The idea was that no matter what program you pulled in, you'd be able to run it on this versatile system board.

A bit of googling helped me find this description:

Model 510 CPU board (C3) (C) 1979 ------------------- 3 CPUs: 6502A, 6800, Z-80, ACIA, PIA, 3 1702A PROMS for 6502 (256x8), 1 1702A PROM for 6800 Address decoding for up to 1MB memory 6502 Proms at $FDxx, $FExx, $FFxx 6800 Prom at $FFxx Processor selection manual or connected to PIA PA6, PA7 (01 = Z80, 10=6800, 11=6502) PIA PA0-PA3 -> A16 -A19. PA4 ->ROM/RAM sel, PA5 ->Processor Switch Also configured as 2 CPU system board with 6502A & Z-80-4, 68B50, 6821, 6810 & 2716 DMon EPROM labeled OSI CP-1

Description from http://marks-lab.com/osi/files/osi-hardware.txt

I never had the opportunity to play with one; at the time I was fooling around with the Exidy Sorceror as well as an old PDP-8 that I got conned into buying. But that's another story.

I'm wondering when (if ever) a time will come when quality hardware isn't proprietary. Why do I need my refrigerator to run a closed platform? Will there ever be a fully open graphing calculator? The chip design doesn't seem like the hard part nowadays... Will Dell ever sell PCs based on processors designed by the crowd?

True, but I think there is an industry-wide shift towards tighter integration/on-die component unification.  Intel, as I recall, has said Haswell will be largely BGA.  The days of being able to build and modify servers may be waning, although on a component scale you'll always be able to "upgrade" by adding new nodes.

However, server-wise the main shift will likely be more of a diversification of kinds of processors (e.g. lightweight cores for virtualization); there will still be a lot of pushback towards shifting solely to SoCs, as your comment alludes to.

The chief reason for mentioning the whole SoC trend is not to suggest that it will drive out traditional server chips directly; while it will likely catch on for certain server form factors (e.g. low-power servers), socket chips will likely continue to sell strong.  However, the SoC work is important as the lessons-learned from a heterogeneous processor architecture perspective will likely be applied to socket chips in traditional servers, which still will be radically different from the homogeneous core-type chips that today are primarily used.

In that regard even the "traditional" socket chips will mirror, to some extent, the shift in processing that is occuring on the mobility side, moving from homogeneous computing units to heterogeneous "specialist" units.

Well, this is what I read: 

IBM has been working closely with ARM since 2011 to develop a co-designed mobile SoC dubbed Cortex-M0, which will put nearly all the components of the smartphone -- RAM, wireless modems, CPU, GPU, power management circuitry, and possibly even the camera sensor, onto a single tightly wired CPU. While no official announcements have been made, it is a pretty safe bet that IBM will look to apply the lessons learned to its server chips.

The compromise is that you have to accept what is given, no or very little alteration will be allowed.

It does not sound to me like this is a "one sized fits all" proposition. In contrast, this is going to change the sever market. Instead of just being concerned about hardware specs, these triple architecture designs will allow servers to do exactly what they need to - no more, no less. That's more efficient than current designs, and will translate into cost effectiveness.

Plus, the server market is in need of some sort of upheaval. With cloud services dominating the headlines, something has to change in the bare metal.

Everytime they try to do a "One size fits all," something is sacrificed.