Intel has been building up this year to its eventual release of its first widely available consumer 10nm Core processor, codenamed "Ice Lake". The new SoC has an improved CPU core, a lot more die area dedicated to graphics, and is designed to be found in premium notebooks from major partners by the end of 2019, just in time for Christmas. With the new CPU core, Sunny Cove, Intel is promoting a clock-for-clock 18% performance improvement over the original Skylake design, and its Gen11 graphics is the first 1 teraFLOP single SoC graphics design. Intel spent some time with us to talk about what’s new in Ice Lake, as well as the product's direction.

The Core of Core: 10th Gen Core

Intel’s first batch of 10nm Ice Lake processors are being given the official brand name of ‘Intel 10th Generation Core’, and will feature up to four cores with hyperthreading and up to 64 execution units of Gen11 graphics. The aim of this first round of parts will be the thin-and-light mobile market in the form of the Ice Lake-U and Ice Lake-Y processors. Intel uses these designation for anything from 5W to 28W TDP, which covers all the mobile ultra-premium devices.

The cores inside Ice Lake-U are based on the ‘Sunny Cove’ microarchitecture, and are a further extension of the overall Core microarchitecture design. The new core affords several security benefits towards Spectre and Meltdown, and Intel is promoting a very healthy 18% IPC increase from its Skylake microarchitecture, which was initially launched as a 6th Gen Core part in 2015 (more on this later).

Asides from the core design, and the increased graphics performance, Intel is also putting a lot of effort into the rest of the design of the SoC. This includes AVX-512 extensions to help with deep learning and inference (applying pre-trained neural networks to new situations), integrated Thunderbolt 3 support for up to four full-bandwidth ports, CNVi support for Wi-Fi 6, and a range of platform designs under the umbrella of Intel’s new Project Athena initiative, which Intel hopes to spur on the next generation of premium devices and experiences in this market.

The Processors

Despite Intel continually talking about upcoming devices, and very general top down specifications, we have not seen a full, official CPU list from the company about what frequencies and what performance metrics the new Ice Lake processors will have. At an event a couple of months back, Intel showed this slide:

This slide states that we should expect to see i3, i5, and i7 versions of Ice Lake, with TDPs ranging from 9W to 28W, however the key value in there would be 15W. The processors will be up to four cores (so expect to see some dual cores), with a turbo frequency up to 4.1 GHz. Graphics will be available up to 64 execution units and up to 1.1 GHz, with certain platforms enabling four Thunderbolt 3 ports. Memory gets a healthy boost compared to previous platforms, with support being up to LPDDR4X-3733 (32 GB) or DDR4-3200 (64 GB). Each CPU has 16 PCIe 3.0 lanes for external use, although there are actually 32 in the design but 16 of these are tied up with Thunderbolt support.

Without a specific CPU list, it becomes a little worrying that the company hasn’t actually decided where the binning of these processors is going to fall. It also speaks to the fact that we are still several months away from having these processors in the market, so Intel is trying to find that balance of performance and yield. What we did discover at Computex earlier this year is that some vendors which are planning to have Ice Lake systems available, did disclose some CPU data:

There are of course some unconfirmed specification lists floating around the internet as well.

Ice Lake Design Wins, and Project Athena

At Computex, Intel showed off a number of systems it says will be the leading designs for Ice Lake in Q4. These included a very impressive Dell XPS 13 system, a HP design with a wooden finish, and an Acer Swift model aiming to be the lightest Ice Lake laptop to come to market.


The Dell XPS 13

All of these devices come under Intel’s new Project Athena initiative.

Project Athena borrows inspiration from Intel’s previous initiatives, such as Centrino and the Ultrabook. The goal here is to promote an ecosystem of Intel’s partners to design the next wave of devices and form factors that spurs on a good deal of innovation. This means that Project Athena has some very strict design targets that Intel’s partners have to follow and achieve in order to get the Athena designation/certification.

This means a lot of the following:

  • Modern Connected Standby
  • Biometric Login
  • Wake from Sleep in <1 sec
  • Core i5 or better
  • >8GB DRAM in dual channel
  • >256GB NVMe SSD, or Optane
  • OpenVINO and WinML support
  • 16+ hours of video playback
  • 9+ hours of wireless web browsing
  • Charge 4+hrs in 30 mins
  • Thunderbolt 3, Wi-Fi 6, Gigabit LTE (optional)
  • 2-in-1 or Clamshell,
  • 12-15.6 inch, minimum resolution 1080p, touch display, narrow bezel on 3 sides
  • Backlit keyboard, precision touchpad, pen support

Truth be told, supporting all of these means that the laptop should be a good buy with a decent user experience. These are a great set of goals to have for a mobile device, and it looks set that devices with the Athena designation should be very good.

However something to keep in mind is that in order to enable some of these technologies, it requires the OEMs to invest into Intel’s component ecosystem. Battery life, for example, helps if OEMs use the sub-1W panels that Intel has designated suitable for these devices. To implement Thunderbolt 3 and Wi-Fi 6 in a system is easy if a vendor uses an Ice Lake CPU, which also means that OEMs have to buy Intel’s AX200 chips (or a Killer AX1650, which is an AX200 underneath) to get Wi-Fi 6 to work. For Thunderbolt 3, re-timers are needed to support Type-C, and Intel makes those. The only other way to implement these features requires add-in cards which are higher power, and using those makes hitting the battery life targets, or the form factor requirements, difficult. Ultimately, to get the best of the Project Athena targets, the only way to do so is to buy more components from Intel or Intel approved component suppliers. Some may argue that programs like Project Athena end up cutting competition in this regard.

It should be noted that Ice Lake isn’t a requirement for Athena. But at this point it really, really, helps.

Intel will give the final Athena certification with a verification platform. This certification is built around what Intel says are ‘Key Experience Indicators’, such as the device being ready-to-go at a moment’s notice, providing enough worry-free battery life for common office tasks, and maintaining consistent responsiveness regardless of the state of the system.

Expect to see Athena devices in the market in Q4.

This Article

In this article, we’ll be going over Intel’s disclosures on Ice Lake, its new core Sunny Cove, as well as the new supported features and technologies within. We also comment on each of the new implemented items, with respect to user experience and realistic market/industry responses.

Combining 10nm CPU + 14nm Chipset
Comments Locked

107 Comments

View All Comments

  • The_Assimilator - Wednesday, July 31, 2019 - link

    Getting Thunderbolt on-die is huge for adoption. While I doubt many laptop manufacturers will enable more than a single TB port, desktop is an entirely different kettle of fish.
  • umano - Wednesday, July 31, 2019 - link

    I am afraid but I cannot consider 4 cores cpu as premium
  • Khenglish - Wednesday, July 31, 2019 - link

    This honestly is looking like the worst architecture refresh since Prescott. IPC increases are getting almost completely washed out by loss in frequency. I wonder if this would have happened if Ice Lake came out on 14nm. Is the clock loss from uArch changes, process change, or a mix of both?

    Performance of an individual transistor has been decreasing since 45nm, but overall circuit performance kept improving due to interconnect capacitance decreasing at a faster rate at every node change. It looks like at Intel 10nm, and TSMC 7nm that this is no longer true, with transistor performance dropping off a cliff faster than interconnect capacitance reduction. 5nm and 3nm should be possible, but will anyone want to use them?
  • Sivar - Wednesday, July 31, 2019 - link

    "...with a turbo frequency up to 4.1 GHz"
    This is the highest number I have come across for the new 10th generation processors, and according to SemiAccurate (which is accurate more often than not), this is likely not an error.

    If this value is close to desktop CPU limitations, the low clock speed all but erases the 18% IPC advantage -- an estimate likely based on a first-gen Skylake.
    Granted, the wattage values are low, so higher-wattage units should run at least a bit faster.
  • Farfolomew - Wednesday, July 31, 2019 - link

    I’m a bit confused by the naming scheme. Ian, you say: “The only way to distinguish between the two is that Ice Lake has a G in the SKU and Comet Lake has a U”

    But that’s not what’s posted in several places throughout the article. The ICL processors are named Core iX-nnnnGn where CML are Core iX-nnnnnU. Comet lake is using 5 digits and Ice Lake only 4 (1000 vs 10000 series).

    Is this a typo or will ICL be 1000-series Core chips?
  • name99 - Wednesday, July 31, 2019 - link

    Regarding AI on the desktop. The place where desktop AI will shine is NLP. NLP has lagged behind vision for a while, but has acquired new potency with The Transformer. It will take time for this to be productized, but we should ultimately see vastly superior translation (text and speech), spelling and grammar correction, decent sentiment analysis while typing, even better search.

    Of course this requires productization. Google’s agenda is to do this in the cloud. MS’ agenda I have no idea (they still have sub-optimal desktop search). So probably Apple will be first to turn this into mainstream products.

    Relevant to this article is that I don’t know the extent to which instructions and micro-architectures optimized for CNNs are still great for The Transformer (and the even newer and rather superior Transformer-XL published just a few months ago). This may all be a long time happening on the desktop if INTC optimized too much purely for vision, and it takes another of their 7 years to turnaround and update direction...
  • croc - Thursday, August 1, 2019 - link

    It seems that Ice Lake / Sunny Cove will have hardware fixes for Spectre and Meltdown. I would like to see some more information on this, such as how much speed gain, whether the patch is predictive (so as to block ALL such OOE / BP exploits) etc.
  • MDD1963 - Thursday, August 1, 2019 - link

    A month or so ago, we heard a few rumors that the CPUs were ahead ~18% in IPC (I see that number again in this article), but are down ~20+% in clock speed.... ; it would be nice to see at least one or two performance metrics/comparisons on a shipped product. :)
  • isthisavailable - Thursday, August 1, 2019 - link

    Unlike Ryzen mobile, intel’s “upto” 64 EUs part will probably only ship in like 2 laptops. Therefore amd has more designs in my book. I don’t understand people who buy expensive 4K laptops with intel integrated gfx which can’t even render windows 10 ui smoothly.
    Looking forward to Zen2 + navi based 7nm APU.
  • Bulat Ziganshin - Thursday, August 1, 2019 - link

    > it can be very effective: a dual core system with AVX-512 outscored a 16-core system running AVX2 (AVX-256).

    it's obviously wrong - since ice lake has only one avx-512 block but two avx2 blocks, it's not much faster in avx-512 mode compared to avx2 mode

    the only mention of HEDT cpus at the page linked is "At a score of 4519, it beats a full 18-core Core i9-7980XE processor running in non-AVX mode". Since AVX-512 can process 16 32-bit numbers in a single operation, no wonder that a single avx-512 core matches 16 scalar cores

Log in

Don't have an account? Sign up now