But why not just jump and let momentum carry x86 like before? The problem with Itanium was largely that the ISA itself sucked to work with and SW/tools were not ready for prime time when 3p SW/HW vendors like Nvidia were expected to have ported to it.
It doesn't seem like ARM and maybe RISC-V will have the same issues, at leatin terms of magnitude so I don't really see why it matters.
I think long term they risk ending up like Canon/Nikon in the DSLR market when Sony came along with the new fangled mirrorless technology - sometimes you gotta disrupt yourself and skate to where the pick is going.
Largely agree. I'd be astonished of they don't have high performance RISC-V designs under development.
Problem is that the endpoint is much less attractive (for them) than where they are now and the transition will be very, very messy. At a time when the business is under strain for other reasons it's a risky move.
Should have done it a few years ago - when they had process lead - but hindsight is a wonderful thing!
Itanium was absolutely a plan to take out the competitors in the unix- and minicomputer market, where margins were much, much higher than in the generic x86 market. That worked. SGI, Digital, HP, Compaq/Tandem, they all fell.
It was not necessarily the plan to abandon the architecture, but once it was won, it also wasn't terribly important to keep going. Much like most corporate takeovers to this day.
Intel would have been happy to keep the market segmented for a few more years, but what happened instead was that the market vacuum was filled by Linux and x86 instead. That would likely have happened sooner or later anyway, but there you go.
It was a poor architecture though and if not by AMD64 it would have been killed by something else more in line with traditionnal high perf superscalar. Maybe even just Arm.
Even Microsoft directly shipped a PowerPC system running a modified NT kernel in the Xbox 360.
If Itanium continued to implode with no other alternatives, PowerPC would have been the most likely to pick up the slack. The main reason why it more or less failed was from a lack of volume to pay for leading edge R&D for the process side. Without AMD64, Intel's Itanium obsession combined with the mid aughts dennard scaling wall catching everyone with their pants down would have given a nice bit of breathing room for PowerPC to exceed x86-32.
They killed it at about the time they started working on AMD64 internally with AMD. Dave Cutler himself gave feedback on the pre silicon design; it was basically co designed with Microsoft. They kept PowerPC in public products until they had another way out. And to this day PowerPC support still exists internally in the NT kernel.
They also literally were shipping an NT derived kernel for Xbox 360 into the 2010s.
Between 1997 and the release of XBox in 2001 there was enough years of code changes (two major NT based releases), also XBox NT kernel was basically that, a stripped down kernel without any relation to Windows 2000 userspace.
And notice I said 360; they reimported the PowerPC support from mainline NT in 2005. And to this day they still have PowerPC support internally in mainline NT.
And that small bit doesn't address the core of what I'm saying, that PowerPC support would have seen even more support if the two options were that and Itanium.
Today not 'everyone' is using x86 - by a long margin - so it's a bit of a stretch to say that in a hypothetical alternative history an architecture that failed in the market would be utterly dominant.
If you exclude everything that does not go into your direction and make the hypothesis that a poor architecture would have risen and then would not have been replaced, you conclude that "everybody" would use it?
No people would just use 32 bit x86 and continue with that for many more years and move to SPARC/PowerPC for the few cases where you really need 64 bit.
People not just gone use really bad processors because they have no other options.
This was right in the time period of Windows Everywhere. Windows on MIPS, Alpha and so on. And for server workloads just using going to Unix is totally fine.
People would rather run server workloads on Unix rather then using windows with shitty expensive processors.
People that are unwilling to move to Unix very likely just stick around on 32bit instead.
That version of Windows died with NT 4.0, several years before Itanium was a product.
We were running Windows 2000 in production, alongside Aix, HP-UX and Solaris workloads across all our customers back in 1999 - 2003, before we got hit in the first .com startup crysis.
