Comments Locked

78 Comments

Back to Article

  • drexnx - Wednesday, June 10, 2020 - link

    who is naming these chips at intel?

    fire them immediately.
  • Sivar - Wednesday, June 10, 2020 - link

    Fire someone for the names, "Lakefield", "Tremont", or "Sonny Cove"?
  • drexnx - Wednesday, June 10, 2020 - link

    no, i3-L13G4, i5-L16G7
    they just throw random numbers and letters that don't represent anything in their names - what makes it the 13 vs the 16? why is one a G4 and the other a G7?

    they really need a geological feature other than "Lake" too, but that's another issue...
  • voicequal - Wednesday, June 10, 2020 - link

    G7 = IGP w/64 EUs
    G4 = IGP w/48 EUs
    G1 = IGP w/32 EUs

    This has been consistent across Gen 11 IGPs, beginning with Ice Lake. Sort of mirrors the i3, i5, i7 branding, but on the GPU side of things.
  • phoenix_rizzen - Wednesday, June 10, 2020 - link

    The G4 and G7 is fairly standard on the Ice Lake CPU SKUs, and relate to the number of EUs in the iGPU.

    The i3/i5 is dumb on these CPUs. They should have resurrected the m3/m5 monikers as these are mobile device chips.

    The L13 and L16 is annoying.

    m3-1013G4 would make more sense. It's an m3, 10th gen CPU, model number 13 (just a relative number to place it in the SKU stacK), with a G4 iGPU.

    m5-1016G7 would make more sense. It's an m5, 10th gen CPU, model number 16, with a G7 iGPU.

    Buyers can just compare m3 to m5, or G4 to G7 to figure out which one is better. Or, if they eventually release more m3 SKUs or m5 SKUs, compare the model numbers.

    But, Intel's MO is to make things as confusing as possible when it comes to model numbers and features available.
  • Spunjji - Tuesday, June 16, 2020 - link

    "But, Intel's MO is to make things as confusing as possible when it comes to model numbers and features available."

    Bingo. They're been doing it with Xeons for around a decade now. Create one incomprehensible naming scheme, then replace it with a completely incomparable and even less comprehensible scheme a few years later.
  • PaulHoule - Wednesday, June 10, 2020 - link

    How about "Creek" as in "S⁴ Creek?"

    Intel has to get on the ball or it will be eaten by ARM and AMD.
  • yeeeeman - Wednesday, June 10, 2020 - link

    Neah, you would believe that but Intel is doing just fine. Winning in a market is not only about silicon, it is also about software, firmware, integration, validation, quality, testing, end2end solutions, trust, etc.
    AMD has only a few of these traits. They happen to have good products, but they are far and away of eating Intel snack.
  • Irata - Thursday, June 11, 2020 - link

    Hmmm....one thing is missing from this list. What could it be ?

    Security pehaps?
  • Deicidium369 - Friday, June 12, 2020 - link

    If you allow someone lab unfettered access to your system you deserve to be hacked. There are ZERO exploits in the wild - they are more theoretical than practical.
  • Spunjji - Tuesday, June 16, 2020 - link

    Your knee-jerk defence ignored ARM...
  • eastcoast_pete - Wednesday, June 10, 2020 - link

    Yeah, but that would invite comments about Intel being up a creek without a paddle, so maybe they should stick with other bodies of water.
  • Byte - Wednesday, June 10, 2020 - link

    They should just call it Pentium 5800 ++!
  • kaidenshi - Thursday, June 11, 2020 - link

    You forgot the metallic submodel. Intel Pentium Silver 5800 ++ is less expensive than Intel Pentium Gold 5999 ++++ but almost as performant. Buy the Gold for the bragging rights.
  • Deicidium369 - Friday, June 12, 2020 - link

    Sunny Cove - not Sonny Cove.
  • Samus - Wednesday, June 10, 2020 - link

    ^^^
  • clemsyn - Wednesday, June 10, 2020 - link

    I am very interested in this CPU, will probably upgrade my e6430 to one but I'll wait for a second generation so intel can iron out the issues.
  • Jon Tseng - Wednesday, June 10, 2020 - link

    Cute. Those overlapping voltage curve charts are a dead ringer for the ones ARM used to have for big.Little. Imitation.. Flattery etc.

    Such a shame the Surface Book Neo got pushed out. It was a perfect device for my use case.
  • close - Wednesday, June 10, 2020 - link

    Wonder how this stands up against a similar ARM CPU.
  • yeeeeman - Wednesday, June 10, 2020 - link

    Worse but it can run full Windows at decent speeds.
  • close - Wednesday, June 10, 2020 - link

    For an arbitrary definition of "decent" :). I used Windows on m3 and m5 CPUs, similar clocks, similar power envelope, and 2 (big) cores (4 threads) rather than 1+4. And it's the kind of experience I *do* wish on people I strongly dislike. I doubt that in the past 18 months Intel made leaps and bounds but I'm curious if the 4 small cores can compensate for the missing big core and presumably the 2 additional "big" threads.
  • yeeeeman - Wednesday, June 10, 2020 - link

    I don't know what are your expectations from a tablet but I have an atom z3735f tablet from 2014 and for YouTube, Facebook, word, PowerPoint and even some older games it works very well. I can't see why you would be unhappy with a 5 core chip, that has the smaller cores with ipc comparable to ivy bridge, one big core that can boost to 3ghz for the special cases when you really need some extra performance but generally for what people usually do on a tablet this chip will be more than up to the job
  • dotjaz - Thursday, June 11, 2020 - link

    So is 8CX, what's your point then?
  • Spunjji - Tuesday, June 16, 2020 - link

    I believe you might be right. I have a couple of devices with Ivy Bridge dual-core 15W CPUs running at around 1.8Ghz, and they're intolerably slow when it comes to tasks like Windows updates. With an extra pair of cores handling background threads and that Sunny Cove core up front, this might actually do a decent imitation of a usable device for light workloads - especially with that GPU, which is substantially larger than anything previously attached to this level of CPU design from Intel.
  • PaulHoule - Wednesday, June 10, 2020 - link

    This is telling: "Lakefield will use the Tremont cores for almost everything, and only call on the Sunny Cove core for user-experience type of interactions, such as typing or interacting with the screen."

    It's a real problem today that computer applications do not feel responsive; it's a problem on top-of-the-line machines, but it is worse on weaker machines. A better CPU has something to do with perceived latency, but more often it is that the embedded flash is slow, doesn't support trim, the network seized up for 5 seconds, ...

    Intel has identified the problem but it is a software problem as opposed to hardware problem. I'd like to have a "computer user's bill of rights" which will always let me know if an operation in progress is progressing or not. For instance on a very powerful Win 10 laptop I might start an application such as PyCharm, Firefox, or CMD.exe and wait anywhere from two to twenty seconds to have any visual indication that the computer was still working on starting it. If you get impatient you might try it more than once and then have five windows pop open all of a sudden.

    Of course we love to complain about Electron applications but it is astonishing how long it takes Adobe products, mostly written in C++, to start. Or even a little CMD.EXE program that uses a 50k binary for that matter. The Linux command line is as snappy as it was in 1994, but X Windows and the ecosystem around it is insufferable. MacOS at least gets the font metrics right.
  • LiKenun - Wednesday, June 10, 2020 - link

    The root of the problem is that applications have to do all of this extra work at all before showing a usable interface. Just-in-time compilation, loading a bitmap for the splash screen, loading all of the plug-ins at start-up (even the ones I never touch for the lifetime of the process), checking license/activation, fancy UI that is totally out-of-place with respect to the native UI, etc.

    As my boss liked to say at meetings, “Why do I have to wait for these delays? The whole day’s schedule is there. Just get all the things ready to go so that I can have them when they’re needed.”

    I suppose this is why some operating systems have begun to pick some of the low-hanging fruit like pre-compilation and pre-loading executable code based on learned usage patterns. But single-threaded performance isn’t improving as fast as it did in the previous decade. Developers should be focus on cutting out the pork from UI (which is not amenable to parallelization).
  • lmcd - Wednesday, June 10, 2020 - link

    Size of app on disk and loading speed don't have that much correlation given the bandwidth available to apps at every point in loading the app. If you're getting 2-20 seconds for firefox launch you should do a reinstall. Cold start Firefox takes me ~2s or less, reliably.

    Pycharm, like all IntelliJ products, depends on OpenJDK. This sort of tradeoff enables running on Mac and Linux easily while slowing their load time. Again, though: I have an upper midrange laptop. 2s for IntelliJ. There's something wrong with your install or you're incredibly impatient and can't count time. Ryzen 2700U, 8GB RAM, Evo 970 SSD.

    If CMD.exe takes 2-20s please just reinstall Windows lol.
  • edzieba - Friday, June 12, 2020 - link

    It's nut a software problem, it's a fundamental mathematical problem: good ol' Amdahl's Law. If you need to perform X tasks one after the other to go from capacitive touch input to display update, and those tasks need to be performed in sequence (i.e. you can't start rendering the update before you know where on the screen the input occurred), then more cores will never help you. The only way to reduce that total sequence time is to run the serial sequence faster.
  • PeachNCream - Wednesday, June 10, 2020 - link

    It would be interesting for Intel to shed the larger core and then just run for Atom cores and maybe ~32 iGPU EUs for smaller, conventional notebooks that are not attempting to impress on premium design features. 7W TDP is a bit too high for comfortable, passively cooled usage. ~4W at max turbo and full load of all CPUs + GPU would make for a better fanless experience.
  • lmcd - Wednesday, June 10, 2020 - link

    7W is absolutely an easy target for passively cooled usage. It's only boosting past 7W that would run into issues.

    I've owned two passively cooled m3/m5 laptops. The m5 ended up being more like a tablet, and that was a bit too excessive. Frankly though that was due to other tradeoffs -- it was somehow user-accessible which meant there was no battery. The m3, which had more space in the design, was well able to cool its chip and keep the unit powered.

    Given the peak power is 7W, but the average power should be much lower, this looks like an excellent chip. I'm excited.
  • PeachNCream - Wednesday, June 10, 2020 - link

    It really is design dependent. I just dislike feeling a device emit heat and when you're peak is 7W there isn't a good way to sustain that sort of load for multiple hours and not expect to feel a noteworthy warm spot on a laptop. 4W makes a lot more sense with a large, wide heat spreader plate and would give the end user a much better result in a ventilation-free chassis like you find on HP Stream laptops. Besides that, there is not much reason for the big core to begin with. Most compute tasks can be accomplished pretty well on Atom cores. I'm using a Celeron N2840 which is a dual core Bay Trail (mind you with 8GB thanks to a user-replacable DIMM and a 1TB SATA drive) as my primary laptop. Its passively cooled and while it handles full load, I would prefer it not feel warm to the touch when I put that CPU to use. On the same note, I don't feel like there is a shortage of processor power or much need for an increase in performance that a bigger core would offer. Four more modern small cores would be more than good enough and maybe twice the iGPU performance so it can handle 720p60 content off Youtube. The only time I really feel it might be a tad slow is when I'm putting together a video in Kdenlive. Playback before rendering is slow and rendering jobs take a little while to complete, but other workloads like running VMs in VirtualBox or trivial stuff like gaming (what works under Linux anyhow) don't really expose much performance weakness yet, but it does make my legs feel warm which is annoying and the TDP for that Bay Trail chip is 7.5W according to ARK.
  • brantron - Wednesday, June 10, 2020 - link

    You're not going to see 7 watts sustained at all, certainly not for hours lol.

    My archaic Skylake dual-core is using 2 watts between the CPU cores and GPU, combined, and I have 10 tabs open, visual studio, and two games minimized.

    These new CPUs have all sorts of power reducing sorcery, in addition to a peak CPU voltage likely under 1.0v. They'll be fine.
  • lmcd - Wednesday, June 10, 2020 - link

    The bigger Sunny Cove core should help with light gaming and "bursty" activity. From my understanding, Atom cores never got any sort of "dynamic overclock" burst mode, and the additions to include that feature would substantially increase the size of the core.
  • Irata - Thursday, June 11, 2020 - link

    Judging by Ian's Twitter posts, 7W does not seem to be the max power consumption, but rather base.
  • IBM760XL - Wednesday, June 10, 2020 - link

    Agreed, 7W is a good target. My passively cooled laptop (and namesake on this forum) runs a Pentium MMX in that power bracket, and while it does get toasty if I run SuperPi on it for too long, for common tasks like creating documents in Word or Visio, it stays at quite reasonable temperatures.

    Admittedly most laptops are thinner nowadays, so the heat is probably more noticeable.
  • lmcd - Wednesday, June 10, 2020 - link

    I feel like heatsink designs have gotten more clever, if not also more efficient. As long as you have a full laptop base to use as a heatsink (and not just a rubber-coated tablet back), 7W in a thinner form factor is totally possible.
  • JayNor - Wednesday, June 10, 2020 - link

    Intel introduced the snow ridge/p5900 family earlier this year which has 8 to 24 Tremont cores.
  • tkSteveFOX - Wednesday, June 10, 2020 - link

    The Tremont cores are a joke and with just one Sunny Cove core, I really don't see what Intel are aiming at in putting all of those iGPU cores.
    A more sensible solution would have been 2 Sunny Cove + 4 Tremnont cores and 32 and max 48 iGPU cores.
  • Tabalan - Wednesday, June 10, 2020 - link

    Well, according to Intel graphs these joke Tremont cores offer 65-70% of Sunny Cove performance. I'd say its damn solid performance for Atom core. Also, 2 SNC + 4 TNT would throttle much harder during CPU intensive tasks.
  • lmcd - Wednesday, June 10, 2020 - link

    Also would jump die size substantially. Not worth the tradeoff I'd imagine. For a stacking design, changing the dimensions could be fatal. Part of the point is how tiny this package is! Add UFS, audio circuitry, I/O and wireless and that's the whole board.

    Honestly the external LTE modem defeats the purpose of this from my vantage. I'd rather the space go toward an extra port or something.
  • yeeeeman - Wednesday, June 10, 2020 - link

    The joke Tremont cores are similar in IPC to Sandy-Ivy Bridge, so 2nd-3rd gen. So for watching videos, editing documents and browsing the web they should more than enough.
  • rrinker - Wednesday, June 10, 2020 - link

    Yeah, that's the thing. The various Atom iterations have gotten all kinds of scorn over the years from 'enthusiasts' - well, news flash, they aren't made for those people. I still have an old machine I put together to run my model railroad, it uses one of the first dual core Atoms and I think I splurged and put 4GB on it. No SSD, not back when I built that. Granted, it runs Linux (with GUI, not command line only), but it was more than up for the task.
    The latest Tremonts blow that thing away. For Mom and Pop to look up recipes, email the grandkids, or post on Facebook about their latest bus trip to the casino, a machine like that is more than powerful enough. They don't need Threadrippers with dual graphics cards. So what if the system with a Tremont only goes up to 8GB RAM, or has no PCIx16,
    As an 'enthusiast' - I like to build different types of machines based on their use. Something like this won;t work for a gaming machine, even for the more lightweight games I tend to play. But as a replacement for that old railroad control machine? I bet it would be fine. My primary machine has a discrete GPU for gaming. My workbench system just uses the integrated Intel graphics - it works just fine for electronic drawings, controlling test gear, and programming microcontrollers. My 'server' is the same basic system as my main desktop, less the discrete GPU, in a larger case with more drive bays. 7 of 8 SATA ports are used, plus the system boots from mirrored NVME drives. It's the last system I have with a DVD drive in it.
  • lmcd - Wednesday, June 10, 2020 - link

    The in-between era of PowerVR Atoms were actually the worst though. That's what people are often scarred by.
  • Spunjji - Tuesday, June 16, 2020 - link

    @lmcd - you're right about that one. Or the early single-core designs that had to have an Nvidia GPU and chipset welded to them to produce anything like usable performance.
  • PeachNCream - Wednesday, June 10, 2020 - link

    I'm an enthusiast and I am perfectly happy with a Bay Trail dual core as my main PC though it is running Linux Mint rather than Windows. When it was on Windows 8.1, it was okay from a performance perspective. I'm not really sure if that would be true on Win10 since I understand that 10 does a lot more Google-like data collection in the background and that might gulp down CPU cycles that would otherwise be put to use doing end user tasks. At any event, not all enthusiasts are interested in high wattage, expensive, and heat intensive hardware. Those kinds of performance or nothing people are usually younger, less practical, and somewhat lacking in wisdom. You can find the same sorts of people running around in loud cars or huge redneck pickup trucks, boasting about performance to an audience of people that are faking interest to be polite to their coworker or family member.
  • ajp_anton - Wednesday, June 10, 2020 - link

    How is Tremont a joke? Its IPC is Sandy Bridge level. Sure, clock speeds will be lower, but a Sandy is still OK performance even if seriously underclocked.

    For iGPU, more is always better. 64EUs at 500MHz is as fast as 32EUs at 1000MHz (because you don't have to worry about parallelization), but draws less power. It's just more expensive, but there you have a reason to have 64EUs.
  • eddman - Thursday, June 11, 2020 - link

    This guy tested a Pentium J5005 (Goldmont Plus) with a Vega 64 and got pretty good results, even with a measly PCIe 2.0 x1.

    https://rk.edu.pl/en/testing-fanless-pentium-j5005...

    Tremont should perform considerably better.

    https://nucblog.net/2018/05/gemini-lake-pentium-nu...
  • Spunjji - Tuesday, June 16, 2020 - link

    That's 4 cores with performance equivalent to a ~1.8Ghz Ivy Bridge part. It's certainly not setting the world alight, but I know plenty of people doing standard office work on systems with that kind of power.

    The GPU core count is high so they can run the cores slower for greater efficiency, while retaining enough performance for displays with high pixel counts. It also gives them more room to salvage imperfect parts. It seems like a sensible trade-off.
  • stephenbrooks - Wednesday, June 10, 2020 - link

    Trying to imagine what natively parallel computer code would do on this. My programs would probably start 5 threads (or 10 with HT) but one of them would finish faster because it's on the Sunny Cove core!
  • lmcd - Wednesday, June 10, 2020 - link

    Since Atom cores have rarely (never?) had HT, I think the whole CPU doesn't have HT.
  • IntelUser2000 - Wednesday, June 10, 2020 - link

    The original in-order Atoms had Hyperthreading but they were so slow it didn't matter. Intel ditched it with the out of order Atoms. They were decent enough to use.
  • trivik12 - Wednesday, June 10, 2020 - link

    I hope Anandtech does review Samsung Galaxy Book s which is available to order in some countries to be shipped early July. I hope press gets hold of these devices early. I am curious if its efficient enough for Surface Neo factor. We dont have a date for that yet right?
  • lmcd - Wednesday, June 10, 2020 - link

    Later than 2020 at minimum.
  • zmatt - Wednesday, June 10, 2020 - link

    "Lakefield" is a very oldschool sounding name. Maybe I've just gotten used to everything they make follow the -lake formula for the last four years but calling it Lakefield instead of the obvious Fieldlake (lol) reminds me of something from the early Core era Like Bloomfield and Yorkfield.
  • Oxford Guy - Wednesday, June 10, 2020 - link

    7 W, eh?

    Is that real-world or "Intel TDP math"?
  • Spunjji - Tuesday, June 16, 2020 - link

    I'm betting that's just code running on the 4 small cores and a bit of GPU activity. That Sunny Cove core at full turbo can use 3W all by itself.
  • abufrejoval - Wednesday, June 10, 2020 - link

    I'd certainly pay €150 for these vs the J5005 on the €99 ASrock mainboards I am using now (among many others).

    But Intel wants premium money for these with 8GB max DRAM, while I am putting 32GB of RAM on the J5005 (tested 48GB yesterday to see if 64GB would work, but it doesn't seem to like 32GB sticks).

    I see these competing with a Jetson Nano, another €99 buy, which kicks some serious GPU ass at similar Wattage while several process nodes older.

    Too little for too much, it will break their neck. Apple seems able to do that, but they have a captive clientele, the rest of us enjoy choice too much to follow either of the two.

    Mind you, Qualcom deserves some competition and I'm more than a little sad I can't have a Kirin 990 for €99 on a Mini-ITX or in a clamshell.
  • lmcd - Wednesday, June 10, 2020 - link

    It's not like the presence of Lakefield prevents Intel from releasing an Atom-only product as you're describing. But the whole point of Lakefield is the PoP package, so you can't expect the product you're describing re: ITX form factor.

    As an expensive SBC, it could work. There aren't that many choices for a small device with widespread distribution compatibility. It'd be pleasant for virtualization, especially if the iGPU can be virtualized like many Intel iGPUs can.
  • trivik12 - Wednesday, June 10, 2020 - link

    One question is why is intel releasing lakefield with sunnycove when Tigerlake with willow cove is around the corner and is supposedly way more efficient. Couldn't intel update Lakefiled to use willow cove core with tremont.

    I hope there is a plan for Gen 2 with Golden Cove and next gen Atom(Gracemont).
  • brantron - Thursday, June 11, 2020 - link

    Tiger Lake has larger caches, so may not fit in the dinky package.

    It's also tuned for higher clocks, so higher leakage. Note that Intel's 14nm low TDP CPUs do not use the ++++++++++ or whatever it is now.
  • Spunjji - Tuesday, June 16, 2020 - link

    It's a bit like AMD's APU dilemma - they need so much time to integrate the components on a working SoC that by the time it comes out, newer tech is already available (or close to becoming available).

    In this case that's magnified by them trying on a bunch of new manufacturing techniques for size.
  • JayNor - Wednesday, June 10, 2020 - link

    gracemont+golden cove = alder lake, right?
  • trivik12 - Wednesday, June 10, 2020 - link

    That wont be low powered one. I am asking for something similar to this chip. So not so high clocked golden cove and 4 gracemont cores.
  • JayNor - Wednesday, June 10, 2020 - link

    Intel spokesperson stated there is an lte chiplet that can go into Lakefield's foveros stack.
  • serendip - Wednesday, June 10, 2020 - link

    This Intel big.little combo might be groundbreaking for Intel but it could end up like most other Atom-based efforts, stuck in niche markets with no mainstream traction even after billions of dollars being spent. Lakefield isn't competing against Atom or Ice Lake chips. It's going up against the Snapdragon 7cx/8cx with higher core counts and built-in LTE. The software situation for Linux and Windows on ARM is improving greatly and who knows, MacOS could join the fray too.
  • Jon Tseng - Thursday, June 11, 2020 - link

    TBH I think since early cherry trail, atom has really been aimed more at embedded markets like comm equipment (analogous to how Tegra is more an auto thing nowadays than a consumer part). Whatever consumer parts have come out have been more of an afterthought...
  • serendip - Thursday, June 11, 2020 - link

    Cherry Trail was supposed to get an upgrade to Willow Trail to be an LTE-capable tablet SoC but that was cancelled. Apollo Lake took its place and that's mainly aimed at servers, embedded and automotive. I've seen Apollo Lake laptops by low end Chinese manufacturers but they're rare and battery life isn't great, probably because of the higher TDP. Intel's loss with Atom is a net gain for ARM licensees.
  • Deicidium369 - Friday, June 12, 2020 - link

    The Nintendo Switch is built on Tegra X1 - quite consumer - but yeah outside of that - mostly auto
  • Spunjji - Tuesday, June 16, 2020 - link

    I feel like this is a pretty concerted attempt to get Atom back where they wanted it in the first place. It's certainly not looking like an embedded-first proposition.

    I guess we'll see whether or not it catches on, though.
  • 69369369 - Thursday, June 11, 2020 - link

    https://ark.intel.com/content/www/us/en/ark/produc...

    AVX/AVX2 not supported, 8GBs of memory max

    Lame asf
  • jruhe - Thursday, June 11, 2020 - link

    Might be due to the need of an uniform instructions set over all cores.
  • dontlistentome - Thursday, June 11, 2020 - link

    Is the TDP 7 real watts or 7 intel TDP watts (~89w in real life)?
  • Deicidium369 - Friday, June 12, 2020 - link

    An example of giving people without a clue information they are unable to process. OK - you got your little "joke" in - now run along.
  • Spunjji - Tuesday, June 16, 2020 - link

    Intel watts are like dog years :D

    In seriousness, though, I'd be surprised if this thing could draw much over 12W even if it wanted to. The Sunny Cove core probably maxes out around 3W at its 3Ghz boost limit, and the Tremont cores are likely to be around half that; that leaves 3 or 4W for the heavily underclocked GPU.
  • Fr@nk - Thursday, June 11, 2020 - link

    Wonder how this first-gen Foveros Lakefield stands up against an ARM Qualcomm 8cx on x86 workload? Qualcomm 8cx cannot emulate x64 apps, only 32 bits x86 apps, right?

    Samsung has the Qualcomm 8cx on the Galaxy Book S and ditched it for the Lakefield for the next Book S. Comparing both would be great!
  • eastcoast_pete - Thursday, June 11, 2020 - link

    I really look forward to the first reviews of one of these! As much as Intel has screwed up in recent years with the seemingly endless wait for their 10 nm process to become mainstream, this design is really innovative! So, now the wait begins to see if they got the cooling right and the transition from 4 little to one big core snappy enough to make a difference.
    Assuming all that works out, one question I'd have is if these SoC designs positively exclude adding memory outside the packaging. Something tells me that having Intel package the RAM right in there means that 8 GB will cost ya, and 16 GB might not even be in the cards.
  • shelbystripes - Saturday, June 13, 2020 - link

    This is one of those cases where Intel’s segmentation drives me batty. They’re only targeting this at mobile device makers—but it sounds absolutely ideal for a SOHO/SMB NAS. It could potentially boost the performance of existing x86 NAS in that range (which use Atom-based Celeron/Pentium, aka “little” cores only) without substantially increasing system power. I’m sure there are tasks (disk scrubbing, RAID rebuild, docker instanced, etc.) that would run faster with the “big” core, but you’d still be running most of the core NAS OS on the little cores, and a GPU for Plex HW acceleration.

    But Intel probably isn’t making it convenient for those vendors to get at all.
  • Spunjji - Tuesday, June 16, 2020 - link

    I suspect you'll see more activity on that front later. Right now they have a very specific target for this: "always connected" mobile devices. In the likelihood that market fails to live up to expectations, they'll need somewhere to shuffle these off to. The tiny boards this can live on could make for a really compact NAS with staggeringly low idle power.

Log in

Don't have an account? Sign up now