Once you start pushing the performance envelope with the ARM core, your performance-per-watt advantage will become less pronouced.

The ARM processor looks so good in your benchmark because it is really not asking much of the silicon at all. Increase the ARM processor's clock rate to 3ghz, and you will need to add:

1) More cache to prevent memory core starvation
2) More voltage to make the silicon transistors switch faster.

This will cause the ARM processor to create a LOT more heat.

The key will be to find an acceptable performance level that doesn't work the silicon hard so you don't consume a lot of power. x86 or ARM, it doesn't really matter.

Many of the solar coatings used on windows are electtrically conductive.

This was probably why the glass was absorbing a lot of the FM radio energy.

The hardest parts of doing this will be the TCP/IP stack and drivers to connect to the internet.

The messages are not long/require lots of screen realestate or memory.

It certainly scores *cool* points for making exceptionally OLD hardware do very new things, but it doesn't score points for difficulty or complexity.

But if someone finds it useful, then it wasn't a waste of time.

Use trusted friends and family as your unwilling victims (ahem ... testers)

At least at first, because simply getting it loaded onto many different computers will start showing the defects you have missed.

This isn't a post to bash Vista or AoC, just pointing out the similarities between the two.

Both had horrendously terrible releases, and while the products may have ended up reasonably solid after much fixing and tweeking, nothing is going to fix the bad release publicity.

Maybe this is a message to publishers that releasing a half-finished product, then fixing it later, is really a terrible terrible idea that should be avoided at all costs. Microsoft certainly is trying VERY HARD to avoid the mistakes of vista with windows 7, even though they are quite similar OSes.

As a programmer, I am quite facinated.

Without the semi-random input from a human, would computer chess programs eventually simply play a half a dozen different games (based off the more psudo-random beginning moved)

I don't know anything about chess programs though, so I could be wrong with how my gut says they should behave.

It could also be simply that people become better at spelling as they age.

I know I am far better at spelling now then 12 years ago when I left high school.

Of course there is still a market for NUMA machines. (or at least the programming behind it) All new CPU designs use intergrated memory controllers and have individual cache per core. That means:

Each core has a small area of memory (its cache) that it can access very quickly at low cost, while the rest of memory is very expensive in comparison. You would be correct in pointing out the that isn't pure-NUMA, because the cache can reference different memory areas.

Also, because all recent CPUs (except the older Core 2 processors) have the memory controllers build into the CPUs, memory gets attached to a CPU, rather then a system now. In a multi-processor X86 box, to access memory attached to a difference CPU, you have talk to it via the CPU its connected to. This is very expensive, and a very pure NUMA environment that is commonplace with a huge future market.

There is nothing stopping a linux virus/malware program running as the user.

Most of the things you want a botnet for DON'T require root access on the infected machines

Not to mention that many privilige escallation bugs get found on linux, any unpatched bug could let a malware program elevate its own permission to root and install systemwide.

I also have a quad core, with 4 gig of ram and a velociraptor boot/app drive.

Openoffice still took about 8 seconds to start without quickstarter.

Thats WAY too long when I used to be able to open Office 97 in about 3 seconds on a 486.