Remember x86-64? The stick AMD was supposed to beat Intel to death with?
Then Intel got themselves the same stick, and the would-be beaters found something else to talk about. Yes, AMD is doing better now, but not because of x86-64. Indeed, AMD’s increased fortunes have come well after Intel switched.
Microsoft came out with a Windows XP for x86-64, but the world hasn’t exactly stampeded to get it.
So what did we end up? A roar, then a mouse.
Of course, some will say, really, all should say, “Wait a minute, x86-64 isn’t dead in the water. When Vista arrives, so will x86-64.” And this is quite true.
But were the hypemasters saying that two years, one year ago? How many of you bought CPUs back then at a premium primarily because of x86-64? What did you get out of it?
This is not an exercise in AMD-bashing, but to illustrate a much bigger truth: hardware and software run on two different clocks.
It’s a lot easier for one group to scratch some new silicon paths and crank out a zillion copies of it than it is for a zillion programmers to tell those paths what to do.
This is true for x86-64, it is true for dual cores, it is true for whatever shader X.0 is being touted. It’s even true for items like solid state drives.
Since big increases in raw speed are no longer an option, any advances are increasingly dependent on having a software infrastructure that uses it. Until that happens, all anybody buying something with the new feature is doing is paying for the privilege of sitting on eggs waiting for them to hatch.
This doesn’t mean you should never hatch eggs. If you buy a computer meant to last five years, and you know an egg is going to hatch in two, it might be wise to sit on the nest for a while.
What it does mean is that you shouldn’t pay a lot for the privilege of sitting on those eggs. If you can justify the purchase and price you pay for an item with some eggs without considering the eggs (or at least not too much), then the eggs are a fringe benefit.
But don’t pay hundreds of dollars more for something with some feature that will sit idle for most of its useful life.