AmigaOne X1000: best potential mini-space shuttle controller?

[Karlos]

Yeah right lets take a processor thats slower than 4 year old pcs, an operating system with no memory protection, and a worse web browser than I have on my cell phone and use it for mission critical control applications.

Although the subject matter of the thread is clearly entertainment, you seemingly haven't heard that almost all mission critical systems, particularly on spacefaring hardware is way, way lower spec than anything you'd get in a consumer device, right?

What matters for these applications is robustness rather than speed. For example, the Mars rovers use PPC based processors that run at only ~33MHz that were made when desktop machines were in the high hundreds. However, unlike your current 2-4GHz processor, these devices will withstand radiation levels that would literally kill you within minutes:

http://en.wikipedia.org/wiki/IBM_RAD6000

So, as it happens, the PPC architecture is already familiar territory for this sort of application.

[Karlos]

It says 20Mhz and not 33Mhz depending on what link you look at.

The RAD6000 was rated at up to 33MHz, that's not to say it's used at that speed in all applications.

http://en.wikipedia.org/wiki/Comparison_of_embedded_computer_systems_on_board_the_Mars_rovers

Anyway I'm guessing robustness is only a part of it.

Power usage is also a factor, but radiation hardening is a big deal for circuitry that is going to be used outside the atmosphere / magnetosphere of Earth. It only takes one high energy cosmic particle to pass through your processor substrate to flip the state of one or more bits in a register / memory cell etc.

[Karlos]

The 1.8GHZ dual core PA6T should be equal to a C2Duo at 3Ghz. WHy? PPC executes more data per cycle than x86.

I wouldn't be so sure about that. Modern x86 hardware is pretty damned good at the old instructions-per-cycle count. The Core2 is no slouch.

[Karlos]

What do they use for radiation shielding for circuitry? Lead?

Nope, that would be too heavy. The key to radiation hardening is to use larger process sizes. Although it makes your transistors bigger and therefore increasing the chance of a particle hit, it decreases the effective amount of charge that particle can dump into the silicon comprising your transistor, thus reducing the chance of a bit flip. Basically, the smaller your components, the more vulnerable they are to the damaging effects of ionization. The second thing you need to do is harden the chip circuitry itself, eg putting ECC on everything.
 

But anyways heat may be another concern. In a vacuum there is no air to cool a CPU, and the higher a CPU's clock rate versus a lower clock rate, the more cooling is needed for the higher clock.

Well, without air, the CPU still cools. There's thermal contact with the circuit board and furthermore, radiative heat loss. However, low power 33MHz parts don't get that warm. For devices like the Mars Rover, they actually have to put electrical heaters in the control unit to ensure it doesn't freeze, since your average Martian night is bitterly cold.