a) Basically, no one ever used hardware-based IA-32 execution, so better to use the silicon for something else,' said Illuminata analyst Gordon Haff. 'Of course, basically no one uses software-based emulation either
HP-UX uses (used?) IA-32 emulation quite a bit - the debugger whildebeest (sp?) was a IA-32 application. I wasn't aware of this fact until I looked at it. Emulation was more or less flawless.
b) Itanium failed. It failed for many reasons. First, because it relied on compilers to generate optimal code (sequences of correctly paralellized instruction groups) to get decent performance - the world is not quite ready for this. Second, because it didn't seem to do much better than existing (Intel) processors, and thus had no reason to exit. It was a novel idea, and it was a lot of fun to play with, but ultimately more or less useless.
c) Itanium was not targetted for the desktop PC market, although they did have desktop Itanium machines available. It was definitely not targetted for laptops (doubt it could fit in one last time I looked). It was targeted at servers and had some success in that area, though (b) above still holds.
Slashdot Mirror
*Sigh* Note to self: type, read, post. In that order. The debugger was a PA-RISC application, emulated in software... I rest my case.
a) Basically, no one ever used hardware-based IA-32 execution, so better to use the silicon for something else,' said Illuminata analyst Gordon Haff. 'Of course, basically no one uses software-based emulation either HP-UX uses (used?) IA-32 emulation quite a bit - the debugger whildebeest (sp?) was a IA-32 application. I wasn't aware of this fact until I looked at it. Emulation was more or less flawless.
b) Itanium failed. It failed for many reasons. First, because it relied on compilers to generate optimal code (sequences of correctly paralellized instruction groups) to get decent performance - the world is not quite ready for this. Second, because it didn't seem to do much better than existing (Intel) processors, and thus had no reason to exit. It was a novel idea, and it was a lot of fun to play with, but ultimately more or less useless.
c) Itanium was not targetted for the desktop PC market, although they did have desktop Itanium machines available. It was definitely not targetted for laptops (doubt it could fit in one last time I looked). It was targeted at servers and had some success in that area, though (b) above still holds.