Slash Boxes

SoylentNews is people

posted by Fnord666 on Friday December 14 2018, @01:55AM   Printer-friendly
from the latest-and-greatest dept.

Intel has announced new developments at its Architecture Day 2018:

Sunny Cove, built on 10nm, will come to market in 2019 and offer increased single-threaded performance, new instructions, and 'improved scalability'. Intel went into more detail about the Sunny Cove microarchitecture, which is in the next part of this article. To avoid doubt, Sunny Cove will have AVX-512. We believe that these cores, when paired with Gen11 graphics, will be called Ice Lake.

Willow Cove looks like it will be a 2020 core design, most likely also on 10nm. Intel lists the highlights here as a cache redesign (which might mean L1/L2 adjustments), new transistor optimizations (manufacturing based), and additional security features, likely referring to further enhancements from new classes of side-channel attacks. Golden Cove rounds out the trio, and is firmly in that 2021 segment in the graph. Process node here is a question mark, but we're likely to see it on 10nm and or 7nm. Golden Cove is where Intel adds another slice of the serious pie onto its plate, with an increase in single threaded performance, a focus on AI performance, and potential networking and AI additions to the core design. Security features also look like they get a boost.

Intel says that GT2 Gen11 integrated graphics with 64 execution units will reach 1 teraflops of performance. It compared the graphics solution to previous-generation GT2 graphics with 24 execution units, but did not mention Iris Plus Graphics GT3e, which already reached around 800-900 gigaflops with 48 execution units. The GPU will support Adaptive Sync, which is the standardized version of AMD's FreeSync, enabling variable refresh rates over DisplayPort and reducing screen tearing.

Intel's upcoming discrete graphics cards, planned for release around 2020, will be branded Xe. Xe will cover configurations from integrated and entry-level cards all the way up to datacenter-oriented products.

Like AMD, Intel will also organize cores into "chiplets". But it also announced FOVEROS, a 3D packaging technology that will allow it to mix chips from different process nodes, stack DRAM on top of components, etc. A related development is Intel's demonstration of "hybrid x86" CPUs. Like ARM's big.LITTLE and DynamIQ heterogeneous computing architectures, Intel can combine its large "Core" with smaller Atom cores. In fact, it created a 12mm×12mm×1mm SoC (compare to a dime coin which has a radius of 17.91mm and thickness of 1.35mm) with a single "Sunny Cove" core, four Atom cores, Gen11 graphics, and just 2 mW of standby power draw.

Original Submission

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 4, Interesting) by takyon on Friday December 14 2018, @03:24AM

    by takyon (881) <{takyon} {at} {}> on Friday December 14 2018, @03:24AM (#774257) Journal

    Same here. One correction though... AMD is not more expensive than Intel. Not by $/core, not by $/performance. And that will become very apparent when they start releasing "7nm" desktop chips next year. But this list of Intel stuff still warrants a look anyway.

    To give credit where it's due, Intel dominates in low-Watt x86. Their sub-8W Celerons, Pentiums, and Atoms are pretty ubiquitous in Chromebooks and whatever the Windows equivalent is while there are basically no AMD chips in those (there are some ARM chips). I like those machines since they are light, fanless, and have great battery life. They also do pretty well with the 15 Watt laptop chips, i.e. the ones found in "ultrabooks". And then even when we factor in AMD's expected IPC and clock improvements in 2019, Intel might still be ahead in single-threaded performance across the board.

    So when I see the "hybrid x86" demo chip, that's pretty interesting. Neither Intel or AMD has given much thought to putting cores of different sizes and performance/efficiency on the same die. That's the big.LITTLE/DynamIQ approach that is found in hundreds of millions of smartphone chips. It will be interesting to see if these kinds of designs benefit laptop and tablet users. Also, my understanding is that Intel could mix cores from different process nodes. So they could put one big "10nm" core alongside several "14nm+++++" cores.

    This 3D packaging approach they are experimenting with is interesting but is far from what may be available in a decade or two, where 3D placement of layers of cores and memory could allow computers to be thousands of times faster [].

    If you're interested in AMD, then you should be looking at this leak* [] and keeping your eyes peeled on CES 2019. AMD is likely to increase "7nm" Ryzen core counts up to 16, from 8. That's right, Ryzen with 16 cores, not just Threadripper. Combine that with about a 20-25% performance increase from IPC improvements and clock speeds, and you can see why Intel is getting antsy and showing off its goods.

    Apparently this new info about "12nm" mobile APUs [] just came out. I'm not going to touch it since I want to see them double core counts to 8, from 4, which they might do on the "7nm" node in 2020. And I still want AV1 support [] in any new hardware.

    *The YouTuber who released the leak has walked back some details, such as AMD's use of "14nm" I/O dies to connect 8-core chiplets shown in the diagrams. That was a guess on his part, and his sources say that it will just use Infinity Fabric.
    [SIG] 10/28/2017: Soylent Upgrade v14 []
    Starting Score:    1  point
    Moderation   +2  
       Interesting=1, Informative=1, Total=2
    Extra 'Interesting' Modifier   0  
    Karma-Bonus Modifier   +1  

    Total Score:   4