Along with an update on their x86 plans, AMD has also presented an update on their ARM plans at financial analyst day today. The news there is a mixed blessing, depending on one’s point of view.

AMD’s “Seattle” SoC – the ARM Cortex-A57 powered Opteron A1100 – will finally be shipping in H2 of this year, after first sampling towards the end of last year. This unfortunately is almost a year behind AMD’s original schedule, though AMD seems moderately optimistic about catching up once they have their first ARM silicon out the door.

But the real focus of AMD’s comments on ARM for FAD involve K12, the AMD-developed ARM CPU core being designed alongside Zen. With AMD having opted to prioritize Zen development, K12 has been pushed back from 2016 to 2017, essentially taking the near-simultaneous launch of the two parts off the table. AMD for their part is attributing this change in schedule only to the decision to focus on Zen, however with Opteron A1100 delayed, it’s entirely possible this is also a knock-on effect that has pushed back the entire AMD ARM roadmap.

In any case, even with the delay AMD is still eagerly moving ahead with their ARM plans. A1100, even though it’s late, will be the pathfinder for AMD’s ARM efforts, serving as a platform to further develop the AMD ARM ecosystem, getting developers acquainted with the technology and getting software ready for it. K12 in turn will come in after that ecosystem has already seen some development, allowing AMD to get their new hardware out to the market and already have software support for it. I hesitate to say that this makes A1100 entirely a pathfinder product – until it’s available, it’s not clear how many customers might purchase it for production work – but clearly AMD’s big play is K12, not A1100.

And though K12 is delayed, AMD tells us that this hasn’t changed how it’s being developed, which is to say that it’s being done in concert with Zen. So virtually everything AMD gets right with Zen will be integrated into K12 as well, just on the basis of the ARM ISA instead of x86. AMD still believes that the time is right for ARM in the server space – along with a very obvious place in the semi-custom SoC space – and that K12 will be an interesting alternative to Zen in that regard.

Comments Locked

15 Comments

View All Comments

  • KAlmquist - Wednesday, May 6, 2015 - link

    Is there any indication of the intended performance of K12 relative to Zen? Since they are developing it in concert with Zen, it would make sense that the performance of the two cores would be similar, but I haven't seen anything from AMD saying that.
  • gamerk2 - Thursday, May 7, 2015 - link

    You can't compare ARM to X86 like that; ARM CPUs simply don't have the building blocks X86 CPUs have fine tuned for decades now to improve performance. That's why the best ARM chips match Intel Atom, at best.

    As ARM CPUs scale up, they're going to have major performance/power problems, simply because they aren't as fine tuned as X86 is. That's why I view AMDs move into ARM as being a major mistake. They missed the growth phase, and they're competing now against two different companies (Intel and Qualcomm) instead of just one.
  • KAlmquist - Thursday, May 7, 2015 - link

    I don't know what you mean by building blocks.

    If you are talking about corporate know how and intellectual property, there is certainly a difference between the dominant x86 company (Intel) and the main designer of ARM cores (ARM Holdings). But Zen and K12 are being designed by the same company. If the performance goals for Zen and K12 are the same, I would expect them to perform similarly.

    What I don't know is whether the performance goals are the same, or whether AMD has decided to make one of the designs higher performance than the other.
  • SleepyFE - Thursday, May 7, 2015 - link

    My 2 cents: AMD is to late to the ARM race. Intel is in Surface tablets, that are finally good and Microsoft dropped Windows RT for the most part (it is still used, just not mentioned). They need to stick to their guns and just work on x68-64 and get the power down to phone form factor like Intel has. They should also license the phone CPU IP to give it more traction (something Intel will never do).
  • HisDivineOrder - Tuesday, May 12, 2015 - link

    They want to see if Zen makes it so they don't have to focus on ARM. If Zen fails or isn't a huge success, then they can fall back to their ARM-based chips. If Zen is as amazing as they hope and has success to match, I think AMD may reconsider ARM plans, especially given nVidia's slow backtracking away from ARM.

    ARM just isn't the Paradise of Promise that it once seemed to be.

Log in

Don't have an account? Sign up now