Linux Looks To Retire Itanium/IA64 Support

[edxposed]

IA32 support should also be removed, this obsolete garbage should go into a museum

[zexelon]

This is the end of an era... not a super great era... but still. The Itanium was probably one of the most ambitious and innovated architectures of recent times. Unfortunately its also a cautionary tail of what happens when you let the architecture engineers run over the software engineers. You can make the most exceptional CPU, with all the most amazing features... that cant actually be programmed by known methods. Essentially the same thing happened to the Cell processor...

No matter how awesome the CPU is, in design... if you cant actually program it with out investing billions in research... its basically a paper weight.

[CommunityMember]

I think the Itanium debacle also put people off some interesting ideas in IA64, such as hints that make instruction scheduling easier and more efficient.

Itanium might have succeeded if the compiler technology of the time could have taken advantage of the VLIW that the architecture supported. Instead, all too many of the slots ended up being no-ops. That, and Intel would have needed to believe strong enough in the future of the architecture to use their best fabs (smallest lithography) for the CPUs, which would have eaten into what was the cash cow at the time, the x86 CPUs.

[ezst036]

I really wish Itanium started off its life as an open source architecture the way RISC-V is. Its fortunes would've surely been different, as probably would ours.

[Ironmask]

At first I found this confusing - if Itanium was made as recently as 2021, that implies there must have been customers to justify its production in 2020, yet the article suggest there haven't been any. I know there's no modern Windows OS to support it. The BSDs have IA64 support but they seem to struggle just to be fully caught up with x86-64, so I don't see why anyone would run their enterprise on IA64 with BSD. So, I looked it up - apparently the OS is HP-UX, which is some other Unix derivative. I knew HP was really the only reason Itanium was still alive but I didn't think they made their own OS for it. I can't say I'm surprised though - I'm sure Intel didn't want anything to do with it and clearly, nobody from any other market cares, so it was really up to HP to do all the work.


It would also explain why Intel thought they could compete against ARM in the mobile market using x86. So the funny thing is, I'd say Intel has had more reasons not to put all their eggs in the x86 basket than to do so.

My guess is they kept making them under some contractual reasons or partnership deals. In fact, while I don't have any sources, that sounds very familiar to me.
I'm sure there some corporate and government computers still running Itanium somewhere who probably do need upgrade/replacement parts. But one would think Intel would just tell them to stuff it, especially because I'm sure the number of remaining customers is in the double digits. But that's the enterprise world, everything gets supported for 50 years and everyone stops using it after 20.

i'm sure both of its users will be devastated

Both? Biesheuvel said there's only one left!

[D-Nis]

The curse of IA64 might still haunt Intel. I predict they'll keep all their CPU eggs in the x86 basket for too long.

Intel is far more diverse than you would first think.

Currently they are bringing up Xe GPUs of all kinds, they have bought Altera for their FPGAs and they're in some kind of partnership with SiFive.

In the past they've probably done it all too, iAPX 432, Itanium, ARM and so forth.

It is kinda fun to poke around in their history.

[EphemeralEft]

Damn, 65k lines?! Isn’t it the compiler’s job to port architecture-agnostic code to architecture-specific instructions? Or is all that code just drivers?

[bug77]

This news seems bigger than it is. The big step will be removing IA64 support from compilers.

[kurkosdr]

(double, sorry)

[kurkosdr]

This is the end of an era... not a super great era... but still. The Itanium was probably one of the most ambitious and innovated architectures of recent times. Unfortunately its also a cautionary tail of what happens when you let the architecture engineers run over the software engineers. You can make the most exceptional CPU, with all the most amazing features... that cant actually be programmed by known methods. Essentially the same thing happened to the Cell processor...

No matter how awesome the CPU is, in design... if you cant actually program it with out investing billions in research... its basically a paper weight.

Nah, Itanium was never that great because the compilers it required to perform proved impossible to write. But let's be real, what mattered was that Intel tried to position Itanium as a successor to x86-32, essentially hoping that the 4GB barrier would force people to migrate to Itanium (which would get rid of that pesky competitor in the x86 space known as AMD), a plan that made sense at the time since Itanium was better at running x86-32 code than the other RISC platforms. Some RISC vendors like SGI even assumed Itanium would be a success by default because it would go to every PC and enjoy the economies of scale that x86 did and does. Then x86-64 happened and Itanium ceased having a reason to exist. Intel lost interest in Itanium right there, but they had to keep making chips because some locked-in corporations were willing to pay for them. But even that niche became too niche by 2017, which brings us to Kittson... Kittson wasn't even the die-shrink of Poulson it was supposed to be, instead it's the same Poulson chip from 2012 with a 5% clock-speed bump. OMG, they found some chips in the wafers that could be clocked 5% higher without going up in smoke, that totally warrants a new codename! Pay up, dear locked-in customers!

You can probably guess by now that I am glad Itanium is history: Itanium was never good in the first place, and if it had succeeded, Intel would have become a monopoly.

There are 3 technologies you don't have the right to feel nostalgic about:
- OS/2 (aka a more retarded version of Windows that can't install itself and is a ploy by IBM to wrestle control from cheaper PC compatibles)
- Windows Phone (a mobile OS that efficiently combines the locked sideloading of IOS with the uncertain updates of Android, worst of both worlds)
- Itanium (see above)

Let's be glad this garbage is history.