Comments Locked

102 Comments

Back to Article

  • rocky12345 - Thursday, August 16, 2018 - link

    This is all well and good but if it can not run x86 code natively then it is all for nothing. We allknow Intel will not hand them a x86 license so all they will have is to be able to do it through emulation which is a lot slower than running it with true x86. ARMs CPU cores would have to be at least 40%-50% faster than Intel's to match running x86 software.

    Maybe in 6-10 years after companies like MS and Apple push for non x86 Apps they would have a chance in the market and x86 coded programs start to be less important in the market.
  • Dragonstongue - Thursday, August 16, 2018 - link

    not to mention x64 which is pretty much AMD cross license x86 backbone..I wonder where they (mobile) get 64bit compute from?
  • Dr. Swag - Thursday, August 16, 2018 - link

    What do you mean by "where"? Obviously there's ARMv8 or whatever it is that's 64 bit, but it's arm not x86
  • close - Friday, August 17, 2018 - link

    Intel and AMD do x86-64 instruction set. ARM does the A64 instruction set. Both 64bit, no connection between the 2. Intel and AMD don't have exclusivity on everything 64bit.
  • goatfajitas - Monday, August 20, 2018 - link

    "Intel and AMD don't have exclusivity on everything 64bit."

    Correct, but they do have x86 and x-86-64 exclusivity. That is what most of the world runs off of, including every manufacturing facility that makes every ARM processor, every Apple and Android device and pretty much everything else you can purchase. Its not a "straglehold" but its pretty close to it. It will take a long time to change that.
  • lartech - Thursday, February 28, 2019 - link

    @goatfajitas, I'm a little confused by your posting. You start out talking about x86/x86-64 "stranglehold" which, granted, is mostly true in the datacenter and workstation spaces.

    But then you talk about "every Apple and Android device and pretty much everything else you can purchase". However, *none* of those run on x86 -- 95% of mobile devices (including smartphones and tablets) and the vast majority of embedded processors (our cars are full of them) are Arm-based. Arm processor volume (running 12+ billion/yr, and accelerating) totally dwarfs x86 volumes.

    Arm is already making inroads in the PC (laptop) space, in the new breed of Arm-based Windows 10 laptops. Even Apple said that *it* was moving away from Intel processors in its Macs starting ~2020, but hasn't specifically said what would replace them (although there is an obvious candidate).

    Granted, long experience says to never underestimate Intel, when it is competitively challenged (just ask Transmeta, Cyrix, AMD, and others about that). But underlying instruction set architectures (ISAs) aren't as much of a lock-in as they used to be -- it looks like x86's previous "stranglehold" is weakening considerably, working its way from the laptop space upwards. (...not unlike what Intel did to PA-RISC, Alpha, MIPS, and SPARC, working its way up the chain from low-end to higher-end systems)
  • UpSpin - Thursday, August 16, 2018 - link

    I doubt it will take 6-10 years. Rumors are, that Apple will ditch Intel soon. Mobile devices running Android, iOS or any other mobile OS are optimized for ARM already. Linux can run on both x86 and ARM. Windows runs natively on ARM, too. So the only popular software stuck on x86 is old or larger Windows programs. But these programs also don't run on a low voltage Core processors but on workstation class processors, which ARM doesn't compete, yet. And the few remaining older programs should run in emulation just fine.

    I own a QNAP NAS and it's quite obvious that QNAP releases more new ARM NAS than x86 NAS. They also ported almost all the x86 only features to ARM devices now. So it's obvious, ARM is close to Intel regarding low power performance.
  • Manch - Thursday, August 16, 2018 - link

    Or maybe a NAS just doesn't require the compute power of a x86 based chip. I think that's a bit of a bad comparison without benches to put your comment in context.
  • UpSpin - Thursday, August 16, 2018 - link

    Please consider my last sentence: "ARM is close to Intel regarding low power performance." And a QNAP or Synology NAS offers more than a WD NAS, and they offer the advanced features on ARM NAS now, too, at least in the case of QNAP:
    https://www.qnap.com/event/containerx31plus/en/
    https://www.qnap.com/solution/arm-snapshots/en/
    I just wanted to point out, Intel has a hard time in this segment already, and will have an even harder time in their Ultrabooks with the upcoming ARM SoCs.
  • imaheadcase - Thursday, August 16, 2018 - link

    From that NAS article from Synology, it doesn't seem its a hard time, it's just that they have so much stock its easier for companies to use the same chip over and over. Lets face it power consumption for a normal person means exactly nothing at all. Its normally the first thing people disable on computers to get the best performance, people disable it on phones to get brighter screen, etc.
  • UpSpin - Thursday, August 16, 2018 - link

    I haven't linked to any Synology article and I only see that QNAP releases new NAS with new ARM SoCs.
    And by manually setting the display brightness one doesn't deactivate the CPU power management and most people don't know how to do this either. Contrary, I see a lot of people with dark screens to prolong battery life.
  • whataboutpereira - Friday, August 17, 2018 - link

    I see a lot of people with dark screens who don't know how to change the brightness back to normal. :)
  • close - Friday, August 17, 2018 - link

    @whataboutpereira, power consumption for plugged in devices like a NAS means nothing to most people. 4W? 5W? 10W? All the same in most people's books. Especially when electricity is cheap enough that it will never offset the extra money you pay for the more efficient device.
  • BurntMyBacon - Friday, August 17, 2018 - link

    I agree with your original statement that QNAP releases more new NAS boxes based on ARM than x86. It makes sense given the efficiency for a compute-lite device. On the other hand, they have within the past year release new NAS boxes based on x86, presumably with a more compute heavy focus in mind. One example:
    https://www.qnap.com/en/news/2017/world-s-first-ry...
  • Manch - Thursday, August 16, 2018 - link

    Fair enough, it's close, but its also lacking feature wise compared to x86. x86 is still very much relevant in NAS. Especially when it comes to transcoding and heavy lifting. Don't get me wrong, I think ARM procs are great for certain things, but I don't see Intel sitting still. They have competition from AMD as well. They can no longer rest on their laurels. As far as a x86/ARM feature compare and perf/power goes, I still think NAS is a poor choice to compare in this regard. ARM has the low power usages but x86 has the the power to provide a much more expanded feature set. Plus isn't ARM limited to EXT 4?
  • Kvaern1 - Thursday, August 16, 2018 - link

    I'd also think you'd want somewhat more horsepower for transcoding than appropriate Arm chips currently deliver.
  • xurxoham - Friday, August 17, 2018 - link

    I don't know what you mean by compute power, but in the highest end products, Intel is clearly not unbeatable any more.
    In the ARM world, you got some companies like Cavium, HPE, Fujitsu and others really pushing the architecture forward for supercomputing and high-end datacenter systems, and they have got already some numbers to prove its viability.
  • close - Friday, August 17, 2018 - link

    Intel was never unbeatable, just "unbeated" (??). It was very much possible to beat them but for various reasons it did not happen.
    And even today at the high end there's not much that can beat them performance wise. Oh, they get absolutely destroyed in price/performance ration but that's a whole different thing. And I don't know what you mean when you say "high-end datacenter systems" but since you put it next to ARM CPUs I assume you mean "rare and shiny"?
  • Manch - Monday, August 20, 2018 - link

    "Or maybe a NAS just doesn't require the compute power."

    I'm referring to NAS devices in my reply to the OP about well, NAS devices.
  • HStewart - Thursday, August 16, 2018 - link

    There have been rumors of Apple ditching Intel floating on Internet for 6 to 10 year and nothing has been real - only thing I heard is that is real is that Apple CPU was using in monitor to control the monitor. Apple business for Intel is only smaller percentage - I am not sure which one is smaller Apple business vs Game Desktop business.

    Keep in mind that x86 development is not just going be at same level - but Intel and ARM will thrust forward

    Windows on ARM is actually Windows on Snapdragon and performance is extremely slow.
    Emulation on ARM is a joke - slower than Atom CPUs.

    "So the only popular software stuck on x86 is old or larger Windows programs. But these programs also don't run on a low voltage Core processors but on workstation class processors, which ARM doesn't compete,"

    This is not true - I have full real version of Photoshop ( not CS or online stuff ) on 5W Y Series.

    Keep in mind when we talking about x86 applications - we are not just talking about Intel - we are talking also about AMD which is so conveniently left out. Not only technology in the CPU's but also in dealing with lower power.

    Of course look at graph comparing performance - so it includes ARM future performance which is total unknown and compares it old Intel processors and leaving out 8 and 9 series mobile cpus which been shown significantly faster than 7 series low end cpu. Where is this information coming from and how is predicted that ARM would be so significantly better. A real PR Job in my opinion. Take it as a grain of salt
  • rocky12345 - Thursday, August 16, 2018 - link

    Yea I think I tried to just say x86 as a whole since there is Intel & AMD to look at here. As others have also stated AMD & Intel won't be sitting still while ARM tries to release these magical CPU's that from their own slides is showing Intel's older low performance,low power chips that are also only dual core CPU's. They very much know they can not compete with Intel or AMD on the high end sector or they would have shown full desktop CPU's from Intel or AMD in their slides which they did not because they no that right now and in the future to be on the same performance level is only a pipe dream for them.

    I personally would never buy a PC based on a ARM CPU with Windows for the reason that it will be very much useless to me and very slow with the software and games I run & I do not want to have performance that I had a decade ago from Intel/AMD on my shiny new PC in 2020. Maybe for basic tasks and internet surfing such as Facebook,Twitter etc these ARM CPU's will work fine but for any serious work or play you want the tried and true AMD/Intel x86 CPU under the hood.
  • HStewart - Thursday, August 16, 2018 - link

    Agree,,,

    But I think Microsoft would have "Windows on ARM" or more specifically "Windows on Snapdragon" or "Windows on Qualcomm" because they would love to get rid of legacy so they are dependent on x86 based code - both Intel and AMD depending customer preferences.

    But I think this is a Microsoft Pipe dream just as Windows 10 S and Windows RT ( which is closer to Windows for ARM ). I have yet to see any evidence of Windows for ARM outside possibly Amazon. HP had best score on there - because probably uses stuck with Windows 10 S applications - I can see it being good for that - and that might Microsoft primary Goal.
  • close - Friday, August 17, 2018 - link

    @HStewart - "There have been rumors of Apple ditching Intel floating on Internet for 6 to 10 year"

    You're saying that 2 years after Apple switched to Intel there were rumors that they will drop them?
    In favor of what, AMD CPUs which at the time were slower and less efficient than Intel's? Or for ARM CPUs that at the time had almost 0 traction? 6 years ago there were "reports". 10 years ago they weren't rumors, they were a guy posting on a forum maybe.
  • rocky12345 - Thursday, August 16, 2018 - link

    I think the problem ARM and the likes will face is that x86 is firmly planted into the eco system it won't be going any where any time soon. Besides that if ARM even wants to think about getting a foot hold into the PC industry and try to take on Intel & AMD they need to have actual software that can match what is already on the PC desktop x86 platform which will take years to get there and even then they have to think a lot bigger than they are now.

    Applets will not cut it on the desktop platform even though Microsoft is trying hard to go that route with their MS store and the ton of crap Applets that are in there. No one that wants to get any real work done wants to use a half baked 2MB Applet that is lacking in features when you also have a choice of getting a full fledged software program that has all of the features baked into it and you do not need to use 5 or 10 Applets to get the same job done.

    ARM needs way faster cores at least 50% faster so they can emulate x86 and hope to do it at the same speed as a x86 CPU can. I do not care that Linux can run ARM code even though it is a good OS it does not have the market share to even make a dent in the market. Now with Microsoft pushing for ARM into their Windows platform yes it will speed things up some what but you still have to deal with almost useless Applets that are rather lacking.

    Alot of this is also kinda mute because we have a lot fo the industry now pushing for cloud everything including MS and to have everything subscription based. This allows them to control every aspect of the software and your PC as well. If you miss a payment your PC may stop functioning until you renew your subscription windows will most likely be subscription based by 2022 and you might be able to still buy a full copy of windows but it will be costly and probably lacking most of the features or have ad's every where if they do it for free. I think that day is for sure coming Bill Gates back in the mid 90's as much as said it was the way he envisioned the windows platform going by the early 2000's well we are here in the early 2000's and it looks like he may have been right.
  • Wilco1 - Thursday, August 16, 2018 - link

    "ARM needs way faster cores at least 50% faster so they can emulate x86"

    Where on earth do you get that idea from? Windows runs 100% native on Arm and so are practically all applications that most people actually use. Emulation of some old x86 code is not the primary use case, but it's great it exists and works transparently when you happen need it.
  • rocky12345 - Thursday, August 16, 2018 - link

    If they want to get past the front door yes they have Microsoft hand holding them with OS support for the ARM based CPU's and soon maybe Apple as well depending on if Intel tries to play ball with Apple or not. x86 based programs out number anything ARM will have on the desktop for a very long time so they need to be up to speed.

    I also found it funny that when they showed off those slides for what was it 2020 they were showing their CPU projections and had a i5 7300U dual core with hyper threading. This is one of Intel's slowest CPU's but hey they plan on beating it by 2020 yay. Mean while both Intel & AMD have CPU's on the desktop now that are 70-90 times faster than that crusty slow i5 7300U. Heck even in the laptop world both AMD and Intel have CPU's that are leagues faster now yes they use more power but I would prefer having a CPU that can run my stuff very fast and use a bit of power to do it than sit waiting for hours to get the same job done. It is going to happen whether people like me want it to or not for the most part the computer industry has gotten very stupid in the last 5-6 years and we have always found ways to get through the stupid and will with this as well. I think I most hate the thought of having to work on these machines for my customers I hate slow with a passion.
  • Wilco1 - Thursday, August 16, 2018 - link

    The slide clearly shows Cortex-A76 beating i5-7300u in 2018 on single-threaded performance. Yes that is this year. So which CPU has 100 times the single-threaded performance of i5-7300u???

    Dual-socket Arm CPUs with 256 threads are being sold already if you wanted something that has higher performance than high-end Xeons.
  • rocky12345 - Friday, August 17, 2018 - link

    And yet if you take those ARM cores run x86 emulation on them because you need a certain type of software that is not available on the ARM platform those Xeon's will be more than happy to out run those ARM cores choking on x86 code and the Xeon's will do it gracefully and with ease because that's what they were made to do.

    I do not hate ARM they have good designs the problem is them trying to show their CPU's as fast as a Intel/AMD CPU in everything when clearly they won't be because x86 software has like what 99% of the market with 1000's upon 1000's of programs made for it. Sorry but the ARM platform has to be able to support those programs as well because that is where the market has been and is at right now and will be into the future as well. If they can not run these 1000's of programs as well as their competition then they already lost. Yes there will be software made for their CPU's and already has been but that software is not even in the .5% bracket.

    Yes there will be a lot of people that just want to surf the internet or look at You tube videos or look at their pictures etc and I guess for now these ARM CPU's will serve them well but for everyone else we have much bigger and faster CPU's to serve us gamer's come to mind you can bet your bottom dollar a gamer will not be willing to lose even 1 FPS in their game if they were forced to switch to a ARM CPU.
  • Wilco1 - Sunday, August 19, 2018 - link

    There is no use case for emulation on servers. Software is recompiled and run natively. It's a non-trivial task of course but it has already been done for most server code.

    You know you can recompile software, right? High level language are a thing you know. People don't write software for a specific CPU since, well 4-5 decades now. So all popular software is recompiled for Arm.

    What's left (unpopular and rarely used older applications) can be emulated. But saying you've lost unless you can beat the fastest x86 CPUs while emulating is absolutely ridiculous. All it needs is run fast enough, and the existing Windows on Arm laptops are pretty much there already.
  • dudedud - Thursday, August 16, 2018 - link

    "Emulation of some old x86 code is not the primary use case"

    Chrome is not old... and i dont think all apps from the Microsoft store are ARM compiled.
  • MrSpadge - Friday, August 17, 2018 - link

    Not yet, but the app store makes recompilation for ARM rather easy - maybe as easy as it gets. That's one major point why it exists at all.
  • Wilco1 - Friday, August 17, 2018 - link

    And Chrome already runs on Arm in Android, so a Windows on Arm version should not be too difficult.
  • Charbax - Sunday, August 19, 2018 - link

    Google isn't eager to provide the ARM Port of Chrome for Windows on ARM, that is just Google being stupid. Most CHrome browsers run on ARM Powered devices already, there are 3 billion people using Chrome every day on ARM today. Google has Chrome ready for Windows on ARM, they are just being stupid not to yet make it available.
  • Barilla - Thursday, August 16, 2018 - link

    There's tons of people for whom the large x86 programs library is irrelevant already. I personally know people who get by with iPad, or an Android tablet as their primary "computer". And even more people who use a PC or a Mac and never use anything beyond internet browser and basic media viewing software - music, video, photo, pdf, word etc - and there are great ARM based programs to do all that.
  • imaheadcase - Thursday, August 16, 2018 - link

    That comment doesn't really matter though to massive amounts of people. What you just said is like someone saying "Well Linux can do all the things a PC does". Which if you ask a regular person what linux is they would go "Isn't that like a cat?". In the world of Electronics it doesn't matter if you have the best product on market, it matters how you market a product.
  • Barilla - Thursday, August 16, 2018 - link

    I'm not sure how that invalidates what I said. People don't care (or more precisely, mostly don't even know) what CPU architecture they are running. So if ARM can offer a CPU that can run as fast as Intel and offer them twice the battery life, they'll be happy to use it.
  • wumpus - Thursday, August 16, 2018 - link

    The other issue is that plenty of people are equally clueless about what Windows is, and probably mistake it for Chrome or Firefox that they need to get to Facebook, email, and other social media.

    I know my mother went through this huge hassle about buying a "windows 10 compatible notebook", only to later find out what she really wanted was something just like my Aunt's Chromebook. On the other hand, my dad has a few windows applications (mostly Family Tree Maker) that it is impossible to pry him off windows.
  • melgross - Friday, August 17, 2018 - link

    True. But Apple is selling 60 million iPads a year, and sales have again been rising, though slowly.

    And Linux is stuck in never never land. All the major OSs, Android, iOS, macOS and Windows are far more accessible than Linux, with all of its improvements over the years. There’s a reason why it still averages just a 1.5% marketshare over the years.
  • bug77 - Thursday, August 16, 2018 - link

    Cross compiling has come a long way ;)
  • HStewart - Thursday, August 16, 2018 - link

    As a developer for around 32 years and 22 years with same x86 application, cross compiling is not always possible in real world applications - in the professional world, application can struggle even to run across different version of Windows OS's if not CPU designs.

    This does include the folks that like playing Older games which line could be stop by developer - for example a lot EA games which pretty much EA has destroy in newer games - or stop release - the game that comes to mind is the Command and Conquer series which played since the original.

    Also keep in mind Linux market is extremely small.
  • Wilco1 - Thursday, August 16, 2018 - link

    Applications that already struggle to run correctly on x86 won't be popular so we can discount those as not being relevant. What is left are popular old applications/games which are no longer under active development. Due to being old they will have low CPU requirements and thus run more than fast enough.
  • HStewart - Thursday, August 16, 2018 - link

    So far the problem has only been with GPU - for me it with AMD GPU in my XPS 15 2in1

    Gamer's will always keep x86 base computers a live. Even the console more toward x86 chips.
  • Great_Scott - Thursday, August 16, 2018 - link

    The future doesn't come from dominating the current standards, it comes from making them irrelevant.

    Truly Intel ST performance ARM processors won't need to run x86 code because we'll be getting all our (desktop) Apps from Google Play.
  • TheJian - Thursday, August 16, 2018 - link

    Not sure what the holdup is on NV pushing this well beyond just a few models of Qcom's chips. NV should be all over this to get their mobile platform finally brought back into the fold. They were just ahead of their time for 5yrs, but gaming is there now and a major attraction. Put out a 7nm soc with Intel wireless and see what happens, while also putting out new versions of your handheld and android tv boxes with DOUBLE socs in thim hitting 100w-200w total and a replacable PSU that can be upgraded for a full 2080ti card coming soon :) A console that is TRULY lowend vid box with best features, OR maxed out gaming console the doubles as that low end vid box.

    Translation of code doesn't take 40-50% hits today. Even old FX32 (IIRC) rand Intel code pretty dang fast for PROe etc. They used it mainly instead...LOL. More stable etc.
  • mukiex - Thursday, August 16, 2018 - link

    To be fair, Microsoft's already been working on a translator since that one experient with the Snapdragon 845. If there's a use case for them (an ARM-based Surface tablet?), they could very well put a lot of dev time into it.
    https://docs.microsoft.com/en-us/windows/uwp/porti...
  • surt - Friday, August 17, 2018 - link

    I don't know ... if you're a productivity person you compile linux and all your apps these days are on javascript. If you don't play games you don't really need x86 compatibility anymore.
  • lartech - Thursday, February 28, 2019 - link

    "emulation which is a lot slower than running it with [native] x86" -- I take strong exception to this native, blanket statement. You assume that *all* x86 code has to be painstakingly emulated, yet most of the time, it *doesn't*. Often, most of an application's runtime is spent in libraries and system calls, which can be run *natively* on the host processor, no emulation required. (as an example, have you ever heard of the "Wine" Windows emulator?)

    I've talked to people who own the new crop of Windows laptops running on Qualcomm Snapdragon (Arm-based) processors. They overwhelmingly find the performance just fine -- even when running 3rd-party apps that use x86-native binaries. Obviously some x86 apps take a performance hit, but for normal "desktop productivity" apps, they don't find it that noticeable. And the far longer battery life and always-on 4G connectivity seem to be worth the cost of a small degradation in some x86 apps. One of them said that he can literally run his Arm-based laptop for _days_ without recharging it and some days doesn't even bother to bring a charger with him to work.
  • Santoval - Wednesday, December 18, 2019 - link

    I don't think Arm want a x86 license. They are a SoC design company, so if they got a x86 license they would need to ditch their own ARM ISA. They can either emulate x86, in coordination with Qualcomm and MS (like they do now) or switch their CPUs to that ISA, which would render them yet another x86 CPU / SoC company.

    I don't think there is something in between they can do (e.g make their SoCs truly dual mode and run both ARM and x86 in hardware; that would be stupid). The ARM ISA is Arm's strongest asset. They make their money from licensing it and their SoC designs based around it. So why would they just ditch it and hand Intel such a huge win? Arm have no incentive to license x86, unlike Nvidia.
  • jjj - Thursday, August 16, 2018 - link

    Why would they share this info as a good thing?
    Hitting 5W at 3GHz with single core loaded means what when all 4 cores loaded?
    And the way they make the 15%+ claim, suggests it includes process.
    Are they trying to make us less excited?
    If they would be advertising 2x the cores at half the price and same ST perf, ok we can swallow that but nobody is making those SoCs.

    They are focusing on the wrong thing, in consumer they should focus on glasses and show us what they can do at 50mW not 5W. They should focus on killing the PC. I suppose PC is server adjacent and that's enough of an excuse but it really isn't a market with a future.
  • Andrei Frumusanu - Thursday, August 16, 2018 - link

    > Hitting 5W at 3GHz with single core loaded means what when all 4 cores loaded?

    It means it'll be 15-18W. Arm didn't make any MT comparisons because the decision on how many cores to actually put into an SoC will be up to the actual SoC vendor.
  • ZolaIII - Thursday, August 16, 2018 - link

    It's ment to be at around 3W at 3GHz on 7nm. Should be around 5W on 10nm which equals 2x performance per W on the similar manufacturing process.
  • sharath.naik - Thursday, August 16, 2018 - link

    My Intel i5 8250u hits 3.4 GHz at 7 watts on a single core. Hits 2.9ghz at around 5w. So not sure if Intel is worried with this false claims. Also Intel at 2 GHz is likely to be faster than arm at 3 GHZ RISC vs CISC. Intel is in no danger from arm in the desktop space, power limit is not the top concern
  • Andrei Frumusanu - Friday, August 17, 2018 - link

    7W sounds like you're just looking at the IA cores metric - you need to account everything else for the apples-to-apples comparison.
  • eastcoast_pete - Thursday, August 16, 2018 - link

    Thanks Andrei!

    Two observations: 1. Thanks ARM for finally admitting that the performance of the A73 core is either the same or BELOW that of the A72! For proof, see their comparo slide to Intel's i5u series reproduced above in the article. Also, that's how ARM gets the 2.5x increase in (projected!) compute power, would be less from the A72 or 75.
    2. Right now, all that is projected or extrapolated; again, the A72/73 experience means a major discount is in order. Sure, the next big ARM cores will be better than current ones, but 2.5x as powerful is very optimistic. Maybe ARM should take the "underpromise, then overdeliver" route for once; looks a lot better. Also, those big ARM cores will have to throttle quickly after short bursts when used in handsets, just like Apple's chips, just to keep thermals in check.

    An remaining issue for Windows-on-ARM is that the total performance of ARM's designs live by multicore/multithread aware software; single-core/threat applications are a significant problem in the Windows market to date.
    Regardless, I welcome any new serious challenger to Chipzilla - if nothing else, it keeps them honest and on their feet. Zen and Zen+ from AMD worked like prune juice - look at Intel running to get their own higher perfomance/better value chips out there in a hurry after years of technological constipation! Go AMD!
    Lastly, I agree with others here that the first ARM-derived processor that probably will play a significant role in the laptop/ultraportable space will be from Apple, and therefore not likely to run Windows natively. Apple already has high performing wide and deep core designs, and I expect the next generation A##X chip to be the first to show up in the new MacBook Airs and similar. More battery capacity and thermal headroom in laptops means one can run bigger cores faster for longer than in phones.
  • ZolaIII - Thursday, August 16, 2018 - link

    A73 is actually a tad slower than A72 but it's also 33% more power efficient which gave it around 15% performance headroom on same power limit.
    If A76 is 66~70% faster than A73 MHz per MHz while using 2x power that is a great accomplishment on it's own. We had A72's on 28 nm planar at 2GHz, A76 should eat only 25% more power while 7nm in comparison uses only 25% of power compared to 28 nm. So you probably won't see 3GHz one's in smartphone SoC's but you should still see 70~80% performance improvement process and architecture combined improvements which is more than enough to justify upgrade for users. If it's half the size & half the DTP compared to X86 part it's more than good enough for server's. Add to that opportunity to license & make your own SoC's and it makes an it an choice which Intel simply cannot match as that (ARM A76 SoC) makes it much, much cheaper. ARM is making POP ready license for A76's on Samsungs second gen EAV 7nm FinFET which will make A76 production cost down to a level of an A73 on 14~16 nm FinFET's. TSMC will follow along with others.
  • eastcoast_pete - Thursday, August 16, 2018 - link

    This may sound surprising, but I mostly agree with you! Yes, if the A76 ends up being 70% faster per MHz using 2x the power of A73, that would be an accomplishment, and a very meaningful one. I just wish ARM would not use the "2.5x faster" eye catcher and just go with something like "70% more compute power per MHz at 2x the power envelope" or similar. This is not just about ARM: I really dislike it when chip designs are being promoted like snake oil. Make realistic promises, then, if possible, beat them. I personally saw the A73 as a step back or sideways from the A72, although it made some sense for the mobile space. In that area, I actually think Apple's approach is a good one for mobile (and I don't like IOS, and don't own any iPhone or iAnything): high performance for short, intense bursts, throttled but okay performance for sustained workloads. That makes the most sense to me in the power and thermal confines of a handheld device. Now, in a server, processors have to sustain 70-80% of the burst speed for hours or days on end, so those designs have to be different.
  • ZolaIII - Thursday, August 16, 2018 - link

    Well everyone likes to pump MHz to for given process and silicone insane levels including Intel and Apple. Saint sustainable limit for FinFET structured one's is at 2~2.2 GHz disregarding of manufacturing node & we see that only on the top server skus this day's. Let's stick to the TSMC projections & try to explain some things. TSMC says that their first gen 7nm FinFET DUV will reduce power usage for 60% compared to the 14~16 nm FinFET of their own. As the A76 is a four instructions per clock wide design compared to the A73 two instructions one it's logical to assume how the A76 will be twice the size if not even more (but I doubt that). That puts us to the figure how an A76 core on 7nm will actually use 80% power of the A73 on 14~16 nm or 33% of an A72 (which is three instructions wide) on 28 nm planar all MHz per MHz. What looks like ARM did remarkable good is rising efficiency of instructions process per cycle but we need to see actual silicone to judge of that.
    Apple is actually the last vendor (as everyone else did it before them) to introduce real heterogeneous CPU typology and scheduling (aka Big.Little) and still not so good. Only thing I agree with recent Apple SoC design (A11) is how two big cores are enough for the mobile same as two little ones would be enough to retain advantage of the Big.little on a less power restrained system (aka laptop, desktop server). Thing what we need right now for mobile is an A73 successor made for DynamIQ to replace or better say take the place of the small A55 core's which will rise a bar in user experience a lot as small one's are actually a worker's while big one's are there only for a jump start.
  • Wilco1 - Thursday, August 16, 2018 - link

    Cortex-A73 absolutely isn't slower than Cortex-A72. It has 11% higher IPC: https://www.anandtech.com/show/11088/hisilicon-kir...

    As Zolall mentioned it also reaches higher frequencies and can sustain those for far longer due to better efficiency.
  • HStewart - Thursday, August 16, 2018 - link

    From "Wendy's" famous commercial "Where is the beef"

    Or more precisely how these performance claims back up - keep in mind they are talking about future ARM CPU and comparing to only older Intel CPU's. This is obviously a PR move by ARM

    Also it really seams like title totally ignores AMD is and it should read "Taking x86 CPUs head on" or maybe AMD is not seen as competitor
  • ZolaIII - Thursday, August 16, 2018 - link

    AMD is not seen as leading competitor as Zen+ is still slower than 7th gen Intel. Don't worry AMD will jump the ship in time which is one thing Intel can't do.
  • Wilco1 - Thursday, August 16, 2018 - link

    What future Intel chips will show a large gain? It would seem the 10nm chips like i3-8121U are taking a big step backwards.
  • HStewart - Thursday, August 16, 2018 - link

    I am not talking about i3-8112U but CPU like i5-8350 since list only compare i5's and not i3;s
  • Wilco1 - Thursday, August 16, 2018 - link

    The i5-8350 is pretty much the same as i5-7300U. The extra cores don't matter since we're talking single threaded performance. So what wonders are you expecting from it?
  • Fritzkier - Friday, August 17, 2018 - link

    Because Intel is more famous and a dominant leader in x86 market share.
  • kgardas - Thursday, August 16, 2018 - link

    "Here a Cortex A76 based system running at up to 3GHz is said to match the single-thread performance of an Intel Core i5-7300U running at its maximum 3.5GHz turbo operating speed, all while doing it within a TDP of less than 5W, versus “15W” for the Intel system." -- Andrei, I've not seen any proof that ARM is going after Intel's single-threaded performance. Slide(s) are done in a clever way that you may consider that single-threaded, but it may also mean multi-threaded. I mean ARM is probably going to be better on parallel run of SPEC2006 while it assumes SoC with 8+ cores comparing that to 2+ cores Intels. That's IMHO very realistic scenario. On the other hand, catching Intel in single-threaded performance is IMHO very unrealistic. Certainly at least for next 2-3 years.
  • Andrei Frumusanu - Thursday, August 16, 2018 - link

    All the performance metrics Arm talked about A76 have always been single-threaded, this article included. It's also noted in the footnotes of the projection slide. They are very openly going after Intel ST performance and talked extensively about it during the A76 launch.

    Arm specifically omitted MT projections because how many cores in a future SoC goes is up to the SoC designer, so of course this will vary from 2 to 4 or any other configuration.
  • kgardas - Thursday, August 16, 2018 - link

    Hmm, well, if you are that sure, then OK! Looks like interesting fight in front of us. Thanks for clarification since I've not seen any footnote which would specifically mention single-threaded benchmarking.
  • HStewart - Thursday, August 16, 2018 - link

    Realistically - your previous article on A76 has projections under iPhone X - so did ARM change their projects so that A76 is great that Intel Xeon or AMD Epic CPU.
  • ZolaIII - Friday, August 17, 2018 - link

    It's greater than Falcor (QC) which is also four instructions per clock but without branch hybrid indirect predictor while probably not being larger. Falcor proven hit 76~80% of the X86 contrapart performance while staying 2x+ more power efficient. So it's expected how A76 will be 10~15% faster while being at least equally power efficient. This puts it at least ahead of current Epyc regarding performance while being there + times more power efficient. This lv of power efficiency is a key for pretty much everything; mobile SoC, thin and light to servers along with price of course.
  • drothgery - Thursday, August 16, 2018 - link

    It's great that ARM's interested in competing in the notebook (or similar power envelope) CPU space, but it seems like they're being deliberately misleading by stopping their U-series i5 comparison data points with a 7xxx dual core rather than a 8xxx quad core. Which for the highly multi-threaded workloads they're arguing performance is close to Intel on, kind of matters a bit, I'd think ...

    Though I suppose that given pricing, ARM is probably really targeting more i3s and Pentiums and Celerons, and Intel is sticking with dual cores in the 15W and lower space for them at least for now (or sometimes quad-Atom family cores).
  • Wilco1 - Thursday, August 16, 2018 - link

    All comparisons in the article are single threaded, as shown in the footnotes. For multithreaded scenarios Arm chips already win on performance just by having more, smaller cores on a more advanced process (eg. Centriq). For the target market 8 cores (4+4) will be typical.
  • HStewart - Thursday, August 16, 2018 - link

    Talk is cheap - less see some actual real numbers - real test - which ARM show none - just a set of made up graphs with no actual proof.
  • Wilco1 - Thursday, August 16, 2018 - link

    The graph already shows SPECINT scores, what more do you want, Geekbench?
  • ZolaIII - Friday, August 17, 2018 - link

    I don't doubt ARM menages to outperform X86 in integer workloads but how ever those don't scale good in SMP (actually they scale horrible). SMP scale except able good only with FP.
    This actually explains performance boost we ware all wandering about hire compared to the earlier ARM's projections as this is INTEGER only.
  • Wilco1 - Friday, August 17, 2018 - link

    Improving integer performance is much harder than floating point. It's also more important for typical mobile and laptop use since integer performance is directly related to the user experience.

    Big Arm SMP CPUs do well on FP already, for example ThunderX2 beats high-end Xeons on OpenFoam. No surprise then there are several Arm-based supercomputers being built.
  • ZolaIII - Friday, August 17, 2018 - link

    Not really. We didn't see almost any improvement on VFP unit's disregarding of architecture in last decade. SIMD's areas did see significant advancements but their is still a problem of feeding them efficiently (latency). ARM is still way behind Intel regarding SIMD's. At the end each & every program initialises on primary instruction set, which is integer & them switches to FP that's why we correlate it to user experience aka snappines. Of course we ware talking about performance per core all of this time. As the SIMD area is actually relatively small compared to the rest of the core its much better to pair larger SIMD with smaller & more power efficient core for example; six A55 will have 3x NEON FP performance of an A76 while using approximately same power.
  • Wilco1 - Friday, August 17, 2018 - link

    That's not true at all. Floating point performance on Arm has increased dramatically in the last decade, and that's mostly scalar FP, not SIMD. Aside from HPC, wide SIMD doesn't make sense since it's big and power hungry.
  • TheJian - Thursday, August 16, 2018 - link

    Blah blah, wake me when you put out an 85w-120w SOC that directly takes on Intel mainstream. Full of all the trimmings, nv 1080ti, SSD, 16GB mem, etc etc,... Then you REALLY are pursuing them and their money. After that go server, use consumer to hone your skills on desktops watt/heat/pipeline levels etc. Bring on the ANDROID/LINUX/STEAMos tri-bootable boxes :)
  • Wilco1 - Thursday, August 16, 2018 - link

    Ever heard of Thunder-X2 or Centriq? Those are not just taking on Xeon but beating Xeon.
  • HStewart - Thursday, August 16, 2018 - link

    Talk is cheap where are the actual benchmarks.
  • Wilco1 - Thursday, August 16, 2018 - link

    Being an Intel shill is cheap. I suggest you read the many articles about TX2 and Centriq with loads of benchmark scores.
  • Fritzkier - Friday, August 17, 2018 - link

    Try 'Qualcomm Centriq 2400 Server Chip Takes On Intel Xeon In Cloudflare Benchmark Gauntlet' by HotHardware.
  • ZolaIII - Friday, August 17, 2018 - link

    Lol you always go to the original source when possible. I put newer one with tuning cuple comments up.
  • ZolaIII - Friday, August 17, 2018 - link

    Hire you go, knock your self out.
    https://blog.cloudflare.com/neon-is-the-new-black/
    It shows also what can be done & how the ARM 64 can take a lead. Don't think for a moment how their X86 used implementation isn't one also costume optimized. This is a benchmark that actually relies on FP SIMD instructions where ARM is actually considered weak, as it's much better in integer one's. FP is the key for SMP & SIMD for boosting FP with an penalty in latency.
  • shabby - Thursday, August 16, 2018 - link

    Forward looking indeed, does anyone belive their cpus will scale like that graph? Lol
  • HStewart - Thursday, August 16, 2018 - link

    You guess is as good as mind on that one.
  • Wilco1 - Thursday, August 16, 2018 - link

    You don't believe Apple A10 and A11 exist then?
  • shabby - Friday, August 17, 2018 - link

    The similarities between apple socs and arm are slim to none.
  • Wilco1 - Friday, August 17, 2018 - link

    It's not about similarity but the fact that Apple have already beaten Intel on performance while using less power. So why wouldn't Arm be able to do exactly the same?
  • shabby - Saturday, August 18, 2018 - link

    Because the similarities between the socs are vastly different, read the 6th reply here https://www.pcper.com/reviews/Editorial/ARM-Reveal... he explains it perfectly.
  • Wilco1 - Saturday, August 18, 2018 - link

    If you mean the post by the guy who has an issue with SMT, then no, he has no clue. We're talking CPU performance, not SoC similarity - the key techniques to improve CPU performance are well known. There is no magic, if you're willing to invest lots of money, increase die area and design for higher power consumption, you can increase performance dramatically.
  • maroon1 - Thursday, August 16, 2018 - link

    LOL they are comparing it to last generation 7th gen i5 (and probably in benchmark that favor ARM CPU)

    The new i5 has more cores and threads.
  • Wilco1 - Thursday, August 16, 2018 - link

    LOL This is a single threaded comparison...
  • zodiacfml - Thursday, August 16, 2018 - link

    Crippled by Windows. What is it like running Android in a laptop form factor? It seems a lot of productivity can be done with Android these days.
    I'd take an Arm laptop at the same price as an Intel Core i5. Arm has to remove the insane price premium.
  • Fritzkier - Friday, August 17, 2018 - link

    I agree with this guy. ARM should've remove the price premium to compete.
    Well, considering ARM progressing more than Intel in the last decade, if Intel don't do anything, they'll be doomed.
  • sgeocla - Friday, August 17, 2018 - link

    This is all fine and dandy for ARM and Intel but nobody mentions that the Ryzen 2700u with it's 12nm process is offering 4 cores/8 threads and 10 GPU cores at 15W. Next year that is going to move to 7nm and get a huge efficiency boost, probably going to 10W at the same performance level.

    Also, there are battery improvements every year. Sure, the new Windows on ARM laptops get 20+ hours of battery life, but can you really play the latest games or even have a lot of browser tabs opened without slowing performance to a crawl? Hell no.

    By 2020 the battery capacity will increase and other components of the system will also consume less power but the PC user buying Windows on ARM devices will get 30 hours of battery life but still unable to play the latest games, and the OEMs support hotlines will still be plagued with calls about apps not working / emulating properly. Meanwhile AMD (and even Intel in 2020+ after they fix 10nm) powered laptops will still get 15+ hours of battery life and all the benefits.

    MS already learned their lesson so the new Surface Go is still x86 and not ARM.
    And Qualcomm is already in a partnership with AMD to get its modems into Ryzen mobile chips because compatibility is still the largest perk of x86.
  • Yojimbo - Friday, August 17, 2018 - link

    I wonder if Sony or Microsoft would consider putting out an ARM-based console for their next generation. These laptop-grade CPUs might be perfect for that. I also wonder if Intel's discrete GPU would be in a position to vie for the next gen console contracts. It could get interesting.
  • A5 - Friday, August 17, 2018 - link

    Depends on when R&D work started. If, say, PS5 is already deep in the pipeline it is probably a Zen+Vega design.
  • dromoxen - Friday, August 17, 2018 - link

    At this point in time , x86 is the most efficient steam train on the market But surely intel has been cooking up something the labs to replace it, smeltdown and all other attacks just hasten its demise. it CAN be done , and will be a necessity beyond 5nm.
  • milkod2001 - Friday, August 17, 2018 - link

    Love this ARM on Windows laptops initiatives but on the end of day if they price them same as Intel laptops i really don't see point with it. Why to bother with something what is not 100% compatible with Windows apps if price is the same.

    Either significantly lower the price of just don't bother.
  • Dr. Swag - Saturday, August 18, 2018 - link

    Why is this article no longer showing up on the home screen of anandtech?
  • shabby - Saturday, August 18, 2018 - link

    Seems they moved it to pipeline rather than on the main page.

Log in

Don't have an account? Sign up now