Slashdot Mirror
Itanium Will Only Be Partly Supported by Longhorn
ver.sicher.ungsvergleich writes "Although stopping short of pulling the plug entirely on Itanium, MS has said that Longhorn will only be able to work for a limited number of higher-end jobs. On the positive side, Microsoft does see a future for the chip, but that 'big iron' slot is not exactly what Chipzilla envisioned as Itanium's future."
I think you fail to realise an important thing: change typically happens by evolution, not revolution, and that's even more true when there's a multi-billion dollar industry involved. Do you honestly believe that everyone's just going to throw every system they have away?
It's not gonna happen. The industry likes migration/upgrade paths, and in 90% of all cases, a design that extends is gonna win over one that outright replaces.
Intel seems to have been unwilling to face that fact, but what they failed to realise is that their monopoly is not big enough to simply force change on people - rather, their move just gave AMD etc. an opportunity to slowly but steadily chip away at that monopoly.
From a market perspective, that's a good thing, of course - but if I was an Intel shareholder, I'd demand that heads roll for this gross mismanagement in the top executive floor.
quidquid latine dictum sit altum videtur.
In the world of good compilers originally envisioned by HP/Intel: No.
In practice: Yes.
Why? Because compilers aren't nearly as good as HP/Intel hoped but state of the art Out-of-Order processors are great. There is only so much theorethically possible ILP to extract in regular code, and good OoO chips extract most of it in an automatic fashion from existing code. So the hardware guys did a better job here than the software guys, and the Itanium bet on software.
To clarify on OoO processors doing most of the possible work in extracting ILP: Even if the instruction window was increased to infinity (that is, all ILP is always found) it would still not yield dramatically much better performance (I have seen estimates of about 25% best-case). So even with a perfect compiler there is just not much to gain, and we do not have perfect compilers. This very high level of performance in extracting ILP is what is forcing the new shift to TLP with architectures like the Sun Niagara.
I don't think we should be pleased that the Itanium failed. As I have often discussed in the past I think Intel really deserves a lot of credit, they are the undisputed top dog in the market, and despite that they are also one of the companies that consistently attempt new different approaches in high-profile products. Neither the Itanium nor the Netburst (which really is interesting and innovative technology) worked out well, but it is trying things that makes technology move forward.
That's not to say that AMD is a bad company, they managed to make the best x86 implementation yet, which is great (though I still consider the K7 to have been the golden age since their pricing structure truly was incredible then).