Editorial: Samsung's new Exynos 990 isn't fast enough to maintain its custom M core

Posted:
in iPhone
Samsung just introduced its latest Exynos 990, destined to power certain versions of its most premium Galaxy S11 flagship next spring. What's most interesting about the new chip how little attention Samsung paid to its CPU performance, a race where it's losing so badly that it appears to be throwing in the towel on its custom M core efforts entirely.


Samsung's scant mention of M

Since 2010, Samsung's Exynos mobile processors have sought to deliver ARM chips that could compete with Qualcomm's Snapdragon in the market for Android phones and tablets and Chromebook netbooks. Samsung once sought to position its Exynos SoCs as rivaling the performance and sophistication of Apple's Ax-series of mobile Application Processors.

Samsung has now delivered five generations of its custom ARM core since the M1 "Mongoose" first appeared in 2015. But its latest M5 core used in the new Exynos 990 is apparently its last. The custom "M" ARM cores the company has been designing at its Samsung Austin R&D Center (SARC) in Texas have simply not been competitive in either their performance or efficiency, the two most important benchmarks of mobile CPU capability.

Earlier this month, Samsung reportedly laid off hundreds of SARC chip designers. At its Samsung Tech Day media event this week, it didn't even bother to name its latest core, instead simply referring to the new Exynos 990 as having two "powerful custom cores" in addition to the off-the-shelf A76 and A55 cores it licenses from ARM.

Pay no attention to the CPU behind the curtain

Samsung promoted its new chip as delivering a 20% increase in performance over its previous generation, but as Android Police noted, "seeing as how the Exynos 9820 SoC got trounced by the Snapdragon 855 earlier this year, we wonder if a 20% improvement will be enough for Samsung to catch up to Qualcomm's performance levels."

The relative performance of Samsung's custom "M" cores to the Kyro cores used in Qualcomm's latest Snapdragon 855 Plus is easy to see because Samsung ships virtually identical versions of its Galaxy S flagships with both chips. It uses its own Exynos chip internationally-- and domestically in Korea-- while being required to use Snapdragon chips in its premium models sold in the U.S., Japan, and China.

Samsung's M-based Exynos CPUs don't compare favorably with Qualcomm's chips, but look particularly weak next to Apple's A13 Bionic, which is beating Qualcomm's latest CPU tech by an insane 77 percent margin in superior CPU core performance. Apple noted a similar 20% jump in CPU and GPU performance while achieving even greater improvements in power efficiency on its A13 Bionic.


Apple's A13 Bionic CPU, GPU, and Neural Engine are all more powerful and power efficient


Samsung focused its attention on other features of its SoC, including a refreshed ARM Mali GPU, a new NPU for AI tasks such as facial recognition, and an improved ISP with support for five cameras with up to 108 megapixel sensors. The company also promoted its new integrated 5G modem. All together, these details suggest the appearance of fancy new products, perhaps next spring.

There are, however, some problems.

First, Samsung's premium phone sales have collapsed. Also, the Chromebooks, premium Android tablets, and other third party buyers that Samsungs once sold its Exynos chips to have also dried up and blown away, a problem Exynos shares with Qualcomm's high-end Snapdragons. On top of that, even Samsung will only be able to ship its new Exynos chip in phones outside of the U.S., China, and Japan, limiting its potential impact to Korea and other international markets where a Qualcomm modem isn't required.

This adds up to an increasingly dire future outlook for Samsung's Exynos line of chips. With high-end sales already in trouble, it increasingly makes less sense for the company to be dumping money into its custom "M" core architecture that isn't paying off but is increasingly falling behind.

An apparent end of M

Samsung first delivered its custom "Mongoose" M1 core design in 2015, which it used in some models of the Galaxy S7 and Note 7. It was followed by M2, M3, M4 and the latest M5 generations across the last five years. But these Exynos chips were only usable in a small slice of Samsung's premium-priced Galaxy S and Note models sold outside of the largest markets for smartphones -- where Qualcomm's CDMA patents made it impractical to sell an Exynos with Samsung's integrated modem.

Samsung also knew that CPU speed wasn't a major driver of its smartphone sales. For buyers who wanted to see fast benchmarks, Samsung could simply cheat to provide impressive numbers, which was much cheaper than developing entirely new chip architectures.

The company has also preferred to show off its other technical achievements, including its lead in OLED panels, Qi charging, and elsewhere. Adding a licensed NPC that promises to accelerate artificial intelligence is easy to do, as demonstrated by Huawei. No need to custom design a CPU core. And focusing attention on 5G also gains media attention, even if 5G networks are not available and won't materially benefit most users for years.

Samsung's System LSI chip fab was also working to stay in the lead in chip fab process, which could help even a sub-optimal core design run fast simply by scaling it down and ramping up its clock speed. Samsung also faced undifferentiated commodity competition from Chinese phone makers who were using basic ARM designs of their own. Sales of middle-tier Androids have been destroying demand for high-end Galaxy S options.

So for Samsung, spending vast amounts of money on custom core design it could only really use on a fraction of its newest, most expensive phones, while it was also dealing with post-peak premium Galaxy S sales in a maturing market, was sort of like changing the tires on a car that was currently on fire. Five years of limited M-core development have only resulted in a third-place runner-up that it could sell in select markets anyways.

Custom ARM core design isn't a cake walk

In contrast to Samsung's odd avoidance of even mentioning "M5," Qualcomm name-drops its own "Kyro" custom core as often as possible, and Apple loves to come up with fast sounding marketing names for each major new generation of its custom CPU core designs: this year it was Lightning and Thunder, the A12 Bionic introduced Tempest and Vortex, A11 Bionic used Monsoon and Mistral; A10 Fusion blew out Hurricane and Zephyr and A9 spun up Twister.

But Apple's storming deluge of ARM-twisting custom-core development hasn't just been clever marketing. Industry observers have been in awe of the amount of work the company has devoted to building its custom Ax ARM chips across the last decade, noting that Apple's fastest chips are now bumping up into the raw performance territory of Intel's x86 offerings, while crushing x86 in power efficiency.

The fact that Apple is catching up to Intel should highlight how incredibly complex and expensive it is to play in the big leagues of state-of-the-art CPU design. Intel has ruled the roost in PC CPU performance since the 1990s, even in the face of the very determined consortium of IBM, Motorola and Apple to defeat it with Power PC in the 1990s, and despite intense competitive efforts more recently by AMD.

There are several universities actively working on launching satellites, but none are developing their own state-of-the-art CPU processor designs. Advanced custom silicon processor architecture design is beyond even space research.

Why has Samsung fallen behind in ARM chip design, despite years of world-leading hit sales volume of smartphones? The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.
MisterKitd_2Rayz2016berndogGG1

Comments

  • Reply 1 of 20
    Rayz2016Rayz2016 Posts: 6,957member
    The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    MisterKitGG1Dan_Dilgertmaywatto_cobrajony0
  • Reply 2 of 20
    blastdoorblastdoor Posts: 3,580member
    Rayz2016 said:
    The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    Money+time+management focus = success. 

    watto_cobra
  • Reply 3 of 20
    auxioauxio Posts: 2,763member
    Rayz2016 said:
    The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    My guess is that it's due to a couple of factors:

    • The market for mobile devices is far larger than PCs (Intel's core market), which gave Apple a lot more money to work with.  Apple bet big on mobile and it paid off
    • They didn't have to compete with Intel head-on like they did in the PowerPC days.  Mobile devices weren't expected to do everything PCs do.  So they could start from scratch and scale up the performance over time.  Unlike Intel who were still entrenched in PC CPU design (and trying to make PC CPUs more power efficient for mobile)
    • They control the whole stack: from CPU to OS to app APIs.  Even if Intel came up with a great new mobile CPU design, they still have to work with mobile OS creators to ensure they're making use of the new features.  Same with Qualcomm.  Samsung was the only one who could compete here, but they still have to work with Google to have Android take advantage of their CPU features
    foregoneconclusionDan_DilgerzhiroFileMakerFellerwatto_cobra
  • Reply 4 of 20
    avon b7avon b7 Posts: 8,024member
    As chipsets for deployment into space were mentioned, this is an easy read. Slightly OT but interesting:

    https://www.esa.int/Enabling_Support/Space_Engineering_Technology/Father_of_the_chips_steering_Europe_s_space_missions
  • Reply 5 of 20
    GG1GG1 Posts: 483member
    blastdoor said:
    Rayz2016 said:
    The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    Money+time+management focus = success. 

    IMO PA Semi is the single most important prescient acquisition Apple have ever made. https://en.wikipedia.org/wiki/List_of_mergers_and_acquisitions_by_Apple

    I would love to see the Keynote slides presented to Apple's board of directors about acquiring PA Semi.
    jwdawsoMacQcDan_DilgerzhirochaickagregoriusmnetmageFileMakerFellerwatto_cobrajony0
  • Reply 6 of 20
    GG1 said:
    blastdoor said:
    Rayz2016 said:
    The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    Money+time+management focus = success. 

    IMO PA Semi is the single most important prescient acquisition Apple have ever made. https://en.wikipedia.org/wiki/List_of_mergers_and_acquisitions_by_Apple

    I would love to see the Keynote slides presented to Apple's board of directors about acquiring PA Semi.
    I agree, with Intrinsity right behind... https://en.wikipedia.org/wiki/Intrinsity

    PA Semi brought CPU architecture knowledge to Apple in 2008, and Intrinsity brought optimization expertise (depriving Samsung of same) in 2010. That's a pretty powerful one-two punch.
    MacQcDan_Dilgerzhirochaickagregoriusmnetmagelolliverwatto_cobra
  • Reply 7 of 20
    coolfactorcoolfactor Posts: 2,338member
    I do not envy today's chip designers. SoC's are the unsung heroes in our modern technology – massive complexity reduced to one square inch of space. Same with our screens. Seriously... individual pixels controlled separately, so small that the eye can not distinguish one from the next? Truly truly astounding how far technology has come.
    Dan_Dilgerzhirogregoriusmlolliverwatto_cobra
  • Reply 8 of 20
    blastdoor said:
    Rayz2016 said:

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    Money+time+management focus = success. 

    While well meaning, and maybe incomplete, this statement seems to be founded on the false idea that ‘you can do anything you put your mind to’. Everyone is equal in value but equality isn’t sameness. Everyone has different skills and limitations, and no amount of money or time or management focus will enable even well-skilled workers to produce ‘genius’ level results. Meaning, it’s doubtful Samsung would have been able to produce the same results if they had as much money, time, and focus as Apple.

    Apple has an excellent and unique combination of specific people, and a well organised ‘machine’ created the environment to enable these people to produce excellent results.
    watto_cobra
  • Reply 9 of 20
    MplsPMplsP Posts: 4,041member
    auxio said:
    • They control the whole stack: from CPU to OS to app APIs.  Even if Intel came up with a great new mobile CPU design, they still have to work with mobile OS creators to ensure they're making use of the new features.  Same with Qualcomm.  Samsung was the only one who could compete here, but they still have to work with Google to have Android take advantage of their CPU features
    This is probably a big reason. Processor design is expensive. Apple has invested heavily and each time they come out with a new processor, they have a phone that uses it exclusively. If QC, Samsung or Intel spend the time and money to develop a new processor, they have to try and sell it to all the various phone manufacturers. and also have it compete with older, cheaper processors. The variability in the Android market also makes it more difficult for manufacturers. I suspect the end result is a smaller net market, meaning a smaller return on investment. 
    watto_cobra
  • Reply 10 of 20
    auxio said:
    Rayz2016 said:
    The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    My guess is that it's due to a couple of factors:

    • The market for mobile devices is far larger than PCs (Intel's core market), which gave Apple a lot more money to work with.  Apple bet big on mobile and it paid off
    • They didn't have to compete with Intel head-on like they did in the PowerPC days.  Mobile devices weren't expected to do everything PCs do.  So they could start from scratch and scale up the performance over time.  Unlike Intel who were still entrenched in PC CPU design (and trying to make PC CPUs more power efficient for mobile)
    • They control the whole stack: from CPU to OS to app APIs.  Even if Intel came up with a great new mobile CPU design, they still have to work with mobile OS creators to ensure they're making use of the new features.  Same with Qualcomm.  Samsung was the only one who could compete here, but they still have to work with Google to have Android take advantage of their CPU features
    The first couple of factors are clearly a big part of this. Your third, however, is off-base. It's correct, and important in other contexts, but not really very relevant here. It's not like Apple's huge lead in core performance is due to their ability to win big on specialized applications that depend on holistic product design. They kick everyone's ass on basic benchmarks (SPEC2006, for example) that measure very fundamental aspects of a CPU's performance. APIs aren't relevant, and even the OS takes a back seat (or should).

    At the level of those benchmarks, the OS shouldn't really be a factor, having a real impact only if there's a big screwup. For example, last year's (or was it two years ago's?) Galaxy with Exynos was severely throttled by bad DVFS, in a way that the QC variant wasn't. This had a significant impact on some benchmarks. But other than that, the OS shouldn't have much impact on low-level performance measurements.

    Every time someone trots out the "whole stack" argument, they're missing a key point: Apple's silicon is just *that much better*. At this point, the only performance competition Apple's got are the high-end i7 and i9s from Intel, and the Zen2 Ryzen 3xxxs from AMD (I'm ignoring small-market CPU's like POWER). Neither of those, of course, comes even close in power efficiency.
    edited October 2019 chaickanetmagewatto_cobra
  • Reply 11 of 20
    auxioauxio Posts: 2,763member

    Every time someone trots out the "whole stack" argument, they're missing a key point: Apple's silicon is just *that much better*. At this point, the only performance competition Apple's got are the high-end i7 and i9s from Intel, and the Zen2 Ryzen 3xxxs from AMD (I'm ignoring small-market CPU's like POWER). Neither of those, of course, comes even close in power efficiency.
    The key point with my statement isn't that "controlling the whole stack" makes the CPU itself better, it's that, even if Intel/QC/Samsung could make a CPU as good as Apple's, they'll have a hard time trying to sell it to vendors when those vendors won't see many of the benefits of that CPU because the rest of the stack isn't set up to take advantage of them.

    Sure, if they boost the raw number of instructions per second the CPU can process it will help everything, or the cache speed, etc.  However, there's a lot more to Apple's performance and power efficiency lead than simply the raw instruction execution pipeline.  For example, I attended a WWDC talk given by Bud Tribble about how iOS (in conjunction with CPU features) is designed to coalesce interrupt handling to avoid energy loss due to the time it takes to transition the CPU between powered and unpowered states (less transitioning = less energy loss).
    edited October 2019 watto_cobra
  • Reply 12 of 20
    mattinozmattinoz Posts: 2,485member
    bsimpsen said:
    GG1 said:
    blastdoor said:
    Rayz2016 said:
    The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    Money+time+management focus = success. 

    IMO PA Semi is the single most important prescient acquisition Apple have ever made. https://en.wikipedia.org/wiki/List_of_mergers_and_acquisitions_by_Apple

    I would love to see the Keynote slides presented to Apple's board of directors about acquiring PA Semi.
    I agree, with Intrinsity right behind... https://en.wikipedia.org/wiki/Intrinsity

    PA Semi brought CPU architecture knowledge to Apple in 2008, and Intrinsity brought optimization expertise (depriving Samsung of same) in 2010. That's a pretty powerful one-two punch.
    I do wonder if the knock out blow was LLVM in that mix. To work on both the hardware and software an optimise then together.
    watto_cobra
  • Reply 13 of 20
    I remember, before Jobs returned, when Apple would almost get it right when they’d do something. Then Jobs returned and even before Apple started teaching his philosophy of planning, and Apple started doing everything perfectly! That Apple started down the road that gave then the technology edge they have today is due to that Jobs visioning that Apple instills into their leaders. 
    watto_cobra
  • Reply 14 of 20
    No competition from old chips is a big advantage of Apple - and I never thought of it before!

    Say A13 is 20% faster but A12 got 30% cheaper to produce over a year. A general phone maker will choose A12 as we can see from Google Pixel and other flagships starting with a previous-year processors. Apple devices don't face that choice, everyone gets the latest and greatest CPU however cost-inefficient it is compared to last gen.
    watto_cobra
  • Reply 15 of 20
    blastdoorblastdoor Posts: 3,580member
    georgie01 said:
    blastdoor said:
    Rayz2016 said:

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    Money+time+management focus = success. 

    While well meaning, and maybe incomplete, this statement seems to be founded on the false idea that ‘you can do anything you put your mind to’. Everyone is equal in value but equality isn’t sameness. Everyone has different skills and limitations, and no amount of money or time or management focus will enable even well-skilled workers to produce ‘genius’ level results. Meaning, it’s doubtful Samsung would have been able to produce the same results if they had as much money, time, and focus as Apple.

    Apple has an excellent and unique combination of specific people, and a well organised ‘machine’ created the environment to enable these people to produce excellent results.
    You can’t do anything you put your mind to if you lack time, money, and management focus. Those are not small things. 

    Consider — how did Apple end up with the great people you reference? 
    watto_cobra
  • Reply 16 of 20
    wizard69wizard69 Posts: 13,377member
    mattinoz said:
    bsimpsen said:
    GG1 said:
    blastdoor said:
    Rayz2016 said:
    The next article will take a closer look at how Apple was able to sneak past larger more entrenched silicon experts at Intel, Qualcomm, and Samsung while the media doubted its progress and bet that rivals would easily catch up.

    Yup, I'm a lot more interested in how Apple did it, rather than how Samsung couldn't. But I guess it's a question of context.

    Money+time+management focus = success. 

    IMO PA Semi is the single most important prescient acquisition Apple have ever made. https://en.wikipedia.org/wiki/List_of_mergers_and_acquisitions_by_Apple

    I would love to see the Keynote slides presented to Apple's board of directors about acquiring PA Semi.
    I agree, with Intrinsity right behind... https://en.wikipedia.org/wiki/Intrinsity

    PA Semi brought CPU architecture knowledge to Apple in 2008, and Intrinsity brought optimization expertise (depriving Samsung of same) in 2010. That's a pretty powerful one-two punch.
    I do wonder if the knock out blow was LLVM in that mix. To work on both the hardware and software an optimise then together.
    LLVM is an interesting endeavor all on its own.   It’s primary goal in My opinion Was to work around the hideous GPL3.   A huge secondary factor was simply to bring modern technology to compilers and the tool chain, LLVM has bee a huge success here.  

    However as someone above has tried to point out the software stack (which ever stack you might consider) and the control of the complete system has little to do with the high performance of Apples  chips.   Apples chips are amazing all on their own and I’m certain they would run other operating systems just fine.   In fact it would be huge to see Linux running on one of these chips.  

    By the way this isn’t to say that iOS isn’t optimized in many ways, obviously it is.  But that is additive to the already impressive intrinsic performance that Apples cores have.  Ultimately I don’t think people always understand what some of the benchmarks are showing them!   Raw CPU performance is very impressive out of Apples newer cores.    Effectively Apples cores compete with some of the best from AMD and Intel.   

    By the way I suspect that this author isn’t well informed about what is going on in industry and research.  RISC-V for instance is a new architecture.  As for universities new students are as like to be learning to implement new technologies such as array processors as they are to learn about generic ALU design.    These sorts of new computational units are only going to become more important in the future.  
    watto_cobra
  • Reply 17 of 20
    wizard69wizard69 Posts: 13,377member
    I remember, before Jobs returned, when Apple would almost get it right when they’d do something. Then Jobs returned and even before Apple started teaching his philosophy of planning, and Apple started doing everything perfectly! That Apple started down the road that gave then the technology edge they have today is due to that Jobs visioning that Apple instills into their leaders. 
    Apple has never done anything perfectly!   In fact there is little that humanity can do perfectly and it becomes  almost impossible to come even near perfection in a corporate environment.  On top of all of that you seem to ignore Jobs screw ups ( which everyone makes by the way).  

    What Apple does do is make a cell phone that arguably out classes everything else on the market.  That doesn’t mean it is perfect just that the competition can’t compete.  
    watto_cobra
  • Reply 18 of 20
    Interesting article, my only criticism is that the Exynos 990 is the successor to the Exynos 980, a mere mid range SoC utilised in the mid tier Galaxy "A" range of devices.

    The Galaxy S10 on the other hand is fitted with an Exynos 9820 which will most likely be superseded by a SoC called Exynos 9830 on the Galaxy S11.

    And although the Apple Ax SoC' are benchmark masters, the more real world like speed comparisons done by phonebuff on you tube tell a different story.


     
    muthuk_vanalingam
  • Reply 20 of 20
    This article failed to mention that samsung is partnering up with AMD to develop a mobile gpu to pair up with their exynos procssor, which would make things more interesting as their arm mali gpus are not very good comared to qualcomm's adreno gpu. While samsung hasn't been impressive lately in terms of their processors, I feel that they understand what they need to do to step it up, and they are taking some interesting steps towards it. Also, the exynos 990 is not meant for the next galaxy S11 phone. It will probably be used for their mid-range offerings. 

    Speaking of the exynos processor's downfall, there was a time when the exynos processor was better than qualcomm's snapdragon. You all remember the 2015 snapdragon 810 overheating fiasco. The exynos 7 performed a lot better at that time, and in 2016, the exynos 8 processor performed better than the snapdragon 820 as well. It's only the previous 2-3 years where the exynos got worse.
    edited October 2019
Sign In or Register to comment.