On the back of a series of recent announcements regarding Intel’s future product line and portfolio, Intel has disclosed to us that it will be holding a forward-looking Architecture Summit/Event in a few weeks. The event will be an exclusively small affair, with only a few press invited, but an opportunity for Intel to discuss its future vision for the next few months with engineers and technical fellows set to give some detailed presentations.

One of the most frequent requests we have put to Intel over the recent months is for a return to an Intel that offers more information. In previous years, Intel would dive deep into its product portfolio and its architecture designs in order to showcase its engineering talent and prowess. This often happened at the awesome annual Intel Developer Forum, a yearly event held in the heart of San Francisco, but since it was disbanded a couple of years ago, the level of detail in each subsequent launch has been agonizingly minimal. For an engineering company that used to proudly present its technical genius on a stage, in detail, to suddenly become so very insular about its R&D raised a lot of questions. It would appear our persistence is paying off, and Intel is going to do something about it.

Details on the content of the Intel Architecture Summit/Event are slim at this point, as invites are slowly being handed out. At this point we are not immediately aware whether Intel intends to have an embargo. In the past at these sort of events, some of the information became almost immediately available, while some of the meatier details had longer embargo times to allow for the press to get to grips with the information and ask questions and write articles. When Intel discussed the Skylake design in detail before it hit the shelves, there was a short lead time. This event is likely to be along the same lines.

At this point we do not know exactly what Intel will be discussing – the only thing we’ve been told is that it will be ‘update’ with Intel’s architects and technical fellows focusing on architecture. This could extend into CPU, GPU, AI, and everything in-between, and if we’re lucky, manufacturing. Given that Cascade Lake is a known part at this point, it would be difficult to see Intel discussing more on the CPU side unless they have an ace in the design we don’t already know about. A far more interesting topic would be on the GPU side, assuming that Raja Koduri and his team have something to say. We already know that the Nervana Neural Network Processor is due out in 2019, so there could be some detail to discuss there as well. An outside possibility is Intel talking 10nm. One can hope.

I’ll be attending for AnandTech. I hope this ends up being a good event, so that there are more like it in the future.

POST A COMMENT

37 Comments

View All Comments

  • vladpetric - Tuesday, November 6, 2018 - link

    You're using the :-P sign, but I'm sure that they already have patents and plans to do something along these lines.

    It won't be "FPGA all in" because it's super low frequency (you don't even get a single GHz), but rather FPGA blocks around fully custom ASIC components.
    Reply
  • eva02langley - Tuesday, November 6, 2018 - link

    On this day... at this time... they announcing this...

    :facepalm:
    Reply
  • peevee - Tuesday, November 6, 2018 - link

    "One of the most frequent requests we have put to Intel over the recent months is for a return to an Intel that offers more information. In previous years, Intel would dive deep into its product portfolio and its architecture designs in order to showcase its engineering talent and prowess. This often happened at the awesome annual Intel Developer Forum, a yearly event held in the heart of San Francisco, but since it was disbanded a couple of years ago, the level of detail in each subsequent launch has been agonizingly minimal."

    Because they have nothing to show. Adding even more specialized instructions (see the AVX-512 hell) only makes CPU even more bloated/less efficient for 99.99% of tasks which are not going to use the instructions.

    They need to switch to a completely different computer architecture specifically designed for the technological realities of today (something like my SIMCA) and finally retire Von Neumann's arch designed for tube computers of 1940s.
    Reply
  • imaheadcase - Tuesday, November 6, 2018 - link

    If it works, why change it. Most technology today is based on old technology because it works. More often than not you hear how older technology out last modern stuff in certain fields. Reply
  • peevee - Thursday, November 8, 2018 - link

    The thing is it does not. When Intel, AMD, ARM etc cite very high MIPS etc, that is NOT what you get in real applications, nowadays by the factor of 10-100. And even on these fake metrics, they are essentially stuck for years.
    And of course nothing they did works in mobile, which is way bigger market than PCs. Like PCs vs mainframes in the 80s and 90s, if you've seen it, you'd have deja vu just like I do. Simply because ARM64 is slightly less awful (but still the same inefficient basic architecture, only low memory requirements and PoP saves their a$$es for now - and 20 different-arch coprocessors on a single chip which do all the ACTUAL work).
    Reply
  • eastcoast_pete - Tuesday, November 6, 2018 - link

    Let's hope this is not about the architecture of the new building on Intel's campus (:

    Seriously, though, Intel needs to get a move on if they want to stay ahead: in addition to the obvious threat (AMD Zen architecture), there is also the increasing likelihood that Apple may play trendsetter once again and start using its own, non-Intel chips. I found the statement at the iPad pro/A12x launch about the A12x performing better than over 90% of all current laptop processors quite ominous. Up to now, most criticisms of Intel have focused on their failure to move their main lines to 10 nm (one small series doesn't count, apparently, yields are atrociously low). However, the lack of progress in their micro-arch over the last years is even more worrying. Maybe they surprise us?
    Reply
  • HStewart - Tuesday, November 6, 2018 - link

    My guess is they will discuss up and coming change in architecture of systems to meet the changes base on completion. I would agree Cascade Lake but I would also something to deal with process changes along with security fix for Spectre/Meltdown. Both of this Intel has been harm with bad press and I believe it would be desirable by Intel team to give confidence that they are on track in make changes to eliminate any concerns.

    But of course we are just users and have no idea of what Intel coming out - it could be something completely new.
    Reply
  • visualzero - Tuesday, November 6, 2018 - link

    Listed below are the numerous architectural and process innovations Intel has released during the past years:

    2015: Skylake, 14 nm
    2016: Skylake, 14 nm
    2017: Skylake, 14 nm
    2018: Skylake, 14 nm

    In the GPU side it's looking even more sad. So I wonder what we have in store for 2019? Few simple ISA extensions to Skylake arch would be my guess, and yes, with 14 nm.
    Reply
  • HStewart - Tuesday, November 6, 2018 - link

    It funny how people confuse architecture vs node - they are not the same. Actually the latest 14nm has slight improvement in Node. Lets just leave it at - by stating Skylake for all versions of architectures show ignorance of the design. Which almost as bad as my nm is smaller than yours. Reply
  • name99 - Tuesday, November 6, 2018 - link

    It's funny how some people have ZERO clue of what micro-architecture actually means, but still consider themselves experts...

    OK, tell us the SIGNIFICANT changes to micro-architecture between Skylake 2015 and * Lake 2018. Hint: a few new instructions, better implementations of microcode, higher frequencies, all do NOT count as significant changes to micro-architecture.
    Reply

Log in

Don't have an account? Sign up now