Intel on Thursday notified its partners and customers that it would be discontinuing its Itanium 9700-series (codenamed Kittson) processors, the last Itanium chips on the market. Under their product discontinuance plan, Intel will cease shipments of Itanium CPUs in mid-2021, or a bit over two years from now. The impact to hardware vendors should be minimal – at this point HP Enterprise is the only company still buying the chips – but it nonetheless marks the end of an era for Intel and their interesting experiment into a non-x86 VLIW-style architecture.

The current-generation octa and quad-core Itanium 9700-series processors were introduced by Intel in 2017, in the process becoming the final processors based on the IA-64 ISA. Kittson for its part was a clockspeed-enhanced version of the Itanium 9500-series ‘Poulson’ microarchitecture launched in 2012, and featured a 12 instructions per cycle issue width, 4-way Hyper-Threading, and multiple RAS capabilities not found on Xeon processors back then. It goes without saying that the writing has been on the wall for Itanium for a while now, and Intel has been preparing for an orderly wind-down for quite some time.

At this point, the only systems that actually use Itanium 9700-series CPUs are the HPE Integrity Superdome machines, which are running the HP-UX 11i v3 operating system and launched in mid-2017. So Intel's sole Itanium customer will have to submit their final Itanium orders – as well as orders for Intel’s C112/C114 scalable memory buffers – by January 30, 2020. Intel will then ship its last Itanium CPUs by July 29, 2021. HPE for its part will support their systems through at least December 31, 2025, but depending on how much stock HPE wants to keep on hand, they'll presumably stop selling them a few years sooner than that.

With the EOL plan for the Itanium 9700-series CPUs in place, it certainly means that this is the end of the road for the whole Itanium project, both for HPE and Intel. The former has been offering Xeon-based NonStop and Integrity servers for years now, whereas the latter effectively ceased development of new CPUs featuring the IA-64 ISA earlier this decade. The machines running these CPUs will of course continue their operations through at least late 2025 (or until HPE drops HP-UX 11i v3) simply because mission-critical systems are bought for the long-haul, but Intel will cease shipments of Itaniums in 2.5 years from now.

Related Reading:

Source: Intel

Comments Locked

63 Comments

View All Comments

  • mode_13h - Friday, February 1, 2019 - link

    I'm not sure there was a single cause for IA64's failure. My favorite scapegoat was Intel's IP lawyers. They patented every aspect of that ISA, to the point that no potential exists for there ever to be a clone. This made too many potential adopters wary of locking them into a single CPU supplier.

    But I agree with your point - Intel originally tried to hold back 64-bit from x86, using it as a lever to force broader adoption of IA64. The combination of IA64's high prices, low (x86) performance, and the availability fast AMD chips with 64-bit addressing was a headwind IA64 couldn't hope to counter.
  • Spunjji - Friday, February 1, 2019 - link

    Agreed with the above. Intel boxed themselves in right from the start, arguably sacrificing the potential of the product to their own profit margins and market segmentation requirements.

    All due credit to AMD for exploiting those weaknesses when they were able, but Intel really did leave that opportunity on the table for them.
  • HStewart - Friday, February 1, 2019 - link

    What I heard is IA64 was extremely advance - it supposedly had reloadable microcode which Intel got from Dec Alpha. It is possible this technology was migrated into x86 processors.

    I remember the early days 64 bit x86 and supposedly Intel had a 64 bit version before AMD. But they probably did want 64 bit to be adapter to IA64 and the primary issue in my IA64 is not adapted because there is too much software on x86 platforms and even a decade later this problem can be still observed. This can be seen with the failure of Windows for ARM (Qualcomm). Things are different now than a decade ago (a little more) because during the 32bit days 4G of memory was a huge amount of memory and even today there are some systems with only 4G or less memory. For example BestBuy has 243 laptops with 4G and 13 with 2G
  • mode_13h - Sunday, February 3, 2019 - link

    Didn't Itanium have a hardware x86 translater? Even so, recall it being quite slow.
  • SarahKerrigan - Sunday, February 3, 2019 - link

    Only pre-Montecito. The software emulators later were much improved (1.6GHz I2 being able to more or less match 1.6GHz Pentium4 on SPEC-type code.)
  • HStewart - Friday, February 1, 2019 - link

    I don't believe AMD had credit for down fall of IA64. Yes a decade later 64 bit is important in x86 market but what really killed IA64 was the fact no one was willing to switch software to platform from Xeon processor line which over the decade as improved both in memory and performance make IA64
  • HStewart - Friday, February 1, 2019 - link

    Keep in mind, I not saying that 64 bit on x86 did not contributive to IA64 downfall - in ways it did but Intel Xeon is primary reason. I would expect in last decade or so, Intel Xeon line would have gone 64 bit anyway. AMD just speeded it up.
  • sing_electric - Friday, February 1, 2019 - link

    I go back and forth about this. On one hand, Itanium was developed using assumptions about the future of computing that turned out not to be true, and so it might have died off, since I don't think Intel's plan from the late 90s (that eventually, 64-bit Itanium would move downmarket and kill off x86) would have really happened. So without AMD under that version of history, Itanium never makes it below expensive workstations, and eventually, Intel has to relent and come up with a way of addressing more than 4GB of memory on x86, but it might happen some time later.

    On the other hand, corporate mergers had killed off most of Intel's competition from other architectures: HP and Intel jointly developed Itanium, so HP made sure PA-RISC wasn't going to be a direct competitor, and, by luck, HP also found itself in charge of Alpha (through their purchase of Compaq who'd purchased DEC), and killed it off in favor of Itanium. PowerPC might have been an option, but I'm not sure what the terms were of IBM and Apple's agreement, particularly with the PowerPC 970 (G5) series.

    So in that version of non-AMD history, Intel (actually, HP) effectively controlled the market, and Intel could have pushed Itanium exclusively, killing Xeon off and eventually forcing Itanium on prosumers then consumers (and giving Microsoft and others time to figure out how to handle the x86-Itanium transition - possibly by forcing x86 to 'legacy' status and waiting until Itanium was fast enough to emulate x86-32 in software at a reasonable speed). I guess it's possible customers, particularly those who were using UNIX anyways, COULD have migrated en masse to PowerPC on Apple's OS X server, which would have radically changed the course of Apple's history, but I doubt it.
  • HStewart - Friday, February 1, 2019 - link

    I don't believe even without AMD picture Itanium would kill off x86 could even if 64 bit was in the picture. The problem is convincing customers or more precisely convert software to IA64. I been at my job for 9 years and previous job was related for 14 and it is still 32bit x86 ( MFC and now with .net integrated ) Server environments would be different.

    Just for information, this announcement does not mean Itanium is dead - just Itanium 9300 - not the 9700 and not sure about 9500?
  • GreenReaper - Friday, February 1, 2019 - link

    Uh, yeah, it does. They have a picture of the 9300 on there (probably because that's what they have as a sample - successors only really mattered to those who had them already), but the news is about the 9700. Intel said the 9700 would be the last Intel Itanium processor back in May 2017:
    https://itpeernetwork.intel.com/evolution-mission-...
    "Although the 9700 series will be the last Intel Itanium processor, our OEM partners will continue to deliver system- and software-level innovation and support for Intel Itanium processor family users, as they weigh the benefits of business continuity with their longer term mission critical strategy."

    Basically they're getting out, if HP wants to continue making servers with it that's their business but they'd better snap them up quick because the bell has tolled for last orders from Intel.

Log in

Don't have an account? Sign up now