HiSilicon Kirin 970 - Android SoC Power & Performance Overview
by Andrei Frumusanu on January 22, 2018 9:15 AM ESTFinal Thoughts
What I wanted to showcase with this article was not only the particular advances of the Kirin 970, but also to use it as an opportunity to refresh everyone on the competitive landscape of the high-end Android SoC market. As the modern, post-iPhone smartphone ecosystem enters its 10-year anniversary, we’re seeing the increasing consolidation and vertical integration of the silicon that power today’s devices.
I wouldn’t necessarily say that Apple is the SoC trend setter that other companies are trying to copy, as much as other vendors are coming to the same conclusion Apple has: to be able to evolve and compete in a mature ecosystem you need to be able to control the silicon roadmap yourself. Otherwise you fall into the risk of not being able to differentiate from other vendors using similar component stacks, or risk not being competitive against those vendors who do have vertical integration. Apple was early to recognize this, and to date Huawei has been the only other OEM able actually realize this goal towards quasi-silicon independence.
I say quasi-independence because while the companies are designing their own SoCs, they are still relying on designs from the big IP licensing firms for key components such as the CPUs or GPUs. The Kirin 970 for example doesn’t really manage to differentiate itself from the Snapdragon 835 in regards to CPU performance or efficiency, as both ARM Cortex-A73 powered parts end up end up within margins of error of each other.
Snapdragon 820’s Kryo CPU core was a hard sell against a faster, more efficient, and smaller Cortex-A72. Samsung’s custom CPU efforts fared slightly better than Qualcomm’s, however the Exynos M1 and M2 haven’t yet managed to present a proper differentiating advantage against ARM’s CPUs. Samsung LSI’s performance claims for the Exynos 9810 are definitely eye-brow raising and might finally mark the point where years of investment and development on a custom CPU truly pay off, but Samsung’s mobile division has yet to demonstrate true and committed vertical integration. Considering all of this, HiSilicon’s decision to stick with ARM CPUs makes sense.
While Qualcomm has backpedalled on using its custom CPU designs in mobile, the company does demonstrate the potential and advantages of controlling your own IP designs when it comes to the GPU. To draw parallels, on the desktop GPU side of things we already see the competitive and market consequences of one vendor having a ~33% efficiency advantage (Nvidia GeForce GTX 1080 vs AMD Radeon Vega 64). Just imagine that disparity increasing to over 75-90%, and that’s currently the state that we have in the mobile landscape (Snapdragon 835 vs Kirin 970). In both cases silicon vendors can compensate for efficiency and performance by going with a larger GPU, something that is largely invisible to the experience of the end-user but definitely an unsustainable solution as it eats into the gross margin of the silicon vendor. With PPA disparities on the high end nearing factors of 4x it definitely gives moment to pause and wonder where we’ll be heading in the next couple of years.
Beyond CPU, GPU and modem IP, SoCs have a lot more component blocks that are generally less talked about. Media blocks such as encoder/decoders eventually end up summarized as feature-checkboxes going up to X*Y resolution at Z frames per second. Even more esoteric are the camera pipelines such as the ISPs of modern SoCs. Here the lack of knowledge of how they work of what the capabilities are both part due to the silicon vendor’s secrecy but also due to the fact that currently truly differentiating camera experiences are defined by software algorithm implementations. The Kirin 970’s new use a Cadence Tensilica Vision P6 DSP definitely uplifts the camera capabilities of the devices powered by the new SoC, but that’s something that we’ll cover in a future device-centric review.
The NPU is a new class of IP whose uses are still in its infancy. Did the Kirin 970 need to have it included to be competitive? No. Does its addition make it more competitive? Yes. Well, maybe. With the software ecosystem lagging behind it’s still early to say how crucial neural network acceleration IPs in smartphones will become, and we have sort of a chicken-or-egg sort of situation where certain use-cases might simply not be feasible without the hardware. The marketing advantages for Huawei have been loud and clear, and it looks industry wide adoption is inevitable and on its way. I don’t foresee myself recommending or not recommending a device based on its existing, or lack of “AI” capabilities for some time to come, and similarly consumers should apply a wait & see approach to the whole topic.
While going on a lot of tangents and comparisons against competitors, the article’s main topic was the Kirin 970. HiSilicon’s new chipset proves itself as an excellent smartphone SoC that's well-able to compete with Qualcomm’s and Samsung’s best SoCs. There’s still a looming release schedule disadvantage as Huawei doesn’t follow the usual spring Android device refresh cycle, and we expect newer SoCs to naturally leapfrog the Kirin 970. This might change in the future as both semiconductor manufacturing and IP roadmaps might become out of sync with the spring device product launches.
I come back to the fact that Huawei is only one of two OEM vendors – and the only Android vendor – whom is leveraging vertical integratation between their SoC designs and the final phones. The company has come a long way over the past few years and we’ve seen solid, generational improvements in both silicon as well as the complete phones. What is most important is that the company is able to put both reasonable goals and execute on its targets. Talking to HiSilicon I also see the important trait of self-awareness of short-comings and the need to improve in key areas. Intel’s Andy Grove motto of “only the paranoid survive” seems apt to apply to Huawei as I think the company is heading towards the right directions in the mobile business and a key reason for their success.
Facebook
Twitter
RSS
116 Comments
View All Comments
lilmoe - Monday, January 22, 2018 - link
Unfortunately, they're not "fully" vertical as of yet. They've been held back since the start by Qualcomm's platform, because of licensing and "other" issues that no one seems to be willing to explain. Like Andrei said, they use the lowest common denominator of both the Exynos and Snapdragon platforms, and that's almost always lower on the Snapdragons.Where I disagree with Andrei, and others, are the efficiency numbers and the type of workloads used to reach those results. Measuring efficiency at MAX CPU and GPU load is unrealistic, and frankly, misleading. Under no circumstance is there a smartphone workload that demands that kind of constant load from either the CPU or GPU. A better measure would be running a actual popular game for 30 mins in airplane mode and measuring power consumption accordingly, or loading popular websites, using the native browser, and measuring power draw at set intervals for a set period of time (not even a benchmarking web application).
Again, these platforms are designed for actual, real world, modern smartphone workloads, usually running Android. They do NOT run workstation workloads and shouldn't be measured as such. Such notions, like Andrei has admitted, is what pushes OEMs to be "benchmark competitive", not "experience competitive". Apple is also guilty of this (proof is in the latest events, where they're power deliver can't handle the SoC, or the SoC is designed well above sustainable TDP). I can't stress this enough. You just don't run SPEC and then measure "efficiency". It just doesn't work that way. There is no app out there that stresses a smartphone SoC this much, not even the leading game. In the matter of fact, there isn't an Android (or iPhone) game that saturates last year's flagship GPU (probably not even the year before).
We've reached a point of perfectly acceptable CPU and GPU performance for flagships running 1080p and 1440p resolution screens at this point. Co-processors, such as the decoder, ISP, DSP and NPU, in addition to software optimization are far, FAR more more important at this time, and what Huawei has done with their NPU is very interesting and meaningful. Kudos to them. I just hope these co-processors are meant to improve the experience, not collect and process private user data in any form.
star-affinity - Monday, January 22, 2018 - link
Just curious about your claims about Apple – so you think it's a design fault? I'm thinking that the problem arise only when the battery has been worn out and a healthy battery won't have the problem of not sustaining enough juice for the SoC.lilmoe - Monday, January 22, 2018 - link
Their batteries are too small, by design, so that's the first design flaw. But that still shouldn't warrant unexpected slowdowns within 12-18 months of normal usage; their SoCs are too power hungry at peak performance, and the constant amount of bursts was having its tall on the already smaller batteries that weren't protect with a proper power delivery system. It goes both ways.Samus - Monday, January 22, 2018 - link
Exactly this. Apple still uses 1500mah batteries in 4.7" phones. When more than half the energy is depleted in a cell this small, the nominal voltage drops to 3.6-3.7v from the 3.9-4.0v peak. A sudden spike in demand for a cell hovering around 3.6v could cause it to hit the low-voltage cutoff, normally 3.4v for Li-Ion, and 3.5v for Li-Polymer, to prevent damage to the chemistry the internal power management will shut the phone down, or slow the phone down to prevent these voltage drops.Apple designed their software to protect the hardware. It isn't necessarily a hardware problem, it's just an inherently flawed design. A larger battery that can sustain voltage drops, or even a capacitor, both of which take up "valuable space" according to Apple, like that headphone jack that was erroneously eliminated for no reason. A guy even successfully reinstalled a Headphone jack in an iPhone 7 without losing any functionality...it was just a matter of relocating some components.
ZolaIII - Wednesday, January 24, 2018 - link
Try with Dolphine emulator & you will see not only how stressed GPU is but also how much more performance it needs.Shadowfax_25 - Monday, January 22, 2018 - link
"Rather than using Exynos as an exclusive keystone component of the Galaxy series, Samsing has instead been dual-sourcing it along with Qualcomm’s Snapdragon SoCs."This is a bit untrue. It's well known that Qualcomm's CDMA patents are the stumbling block for Samsung. We'll probably see Exynos-based models in the US within the next two versions once Verizon phases out their CDMA network.
Andrei Frumusanu - Monday, January 22, 2018 - link
Samsung has already introduced a CDMA capable Exynos in the 7872 and also offers a standalone CDMA capable modem (S359). Two year's ago when I talked to SLSI's VP they openly said that it's not a technical issue of introducing CDMA and it'll take them two years to bring it to market once they decide they need to do so (hey maybe I was the catalyst!), but they didn't clarify the reason why it wasn't done earlier. Of course the whole topic is a hot mess and we can only speculate as outsiders.KarlKastor - Thursday, January 25, 2018 - link
Uh, how many devices have shipped yet with the 7872?Why do you think they came with a MDM9635 in the Galaxy S6 in all CDMA2000 regions? In all other regions their used their integrated shannon modem.
The other option is to use a Snapdragon SoC with QC Modem. They also with opt for this alternative but in the S6 they don't wanted to use the crappy Snapdragon 810.
It is possible, that Qualcomm today skip their politics concerning CDMA2000 because it is obsolete.
jjj - Monday, January 22, 2018 - link
Don't forget that Qualcomm is a foundry customer for Samsung and that could be why they still use it.Also, cost is a major factor when it comes to vertical integration, at sufficient scale integration can be much cheaper.
What Huawei isn't doing is to prioritize the user experience and use their high end SoCs in lower end devices too, that's a huge mistake. They got much lower costs than others in high end and gaining scale by using these SoCs in lower end devices, would decrease costs further. It's an opportunity for much more meaningful differentiation that they fail to exploit. Granted, the upside is being reduced nowadays by upper mid range SoCs with big cores and Huawei might be forced into using their high end SoCs more as the competition between Qualcomm and Mediatek is rather ferocious and upper mid becomes better and better.
Got to wonder about A75 and the clocks it arrives at ... While at it, I hope that maybe you take a close look at the SD670 when it arrives as it seems it will slightly beat SD835 in CPU perf.
On the GPU side, the biggest problem is the lack of real world tests. In PC we have that and we buy what we need, in mobile somehow being anything but first is a disaster and that's nuts. Not everybody needs a Ferrari but mobile reviews are trying to sell one to everybody.
HStewart - Monday, January 22, 2018 - link
This could be good example why Windows 10 for ARM will failed - it only works for Qualcomm CPU and could explain why Samsung created Intel based Windows TabletsI do believe that ARM especially Samsung has good market in Phone and Tablets - I love my Samsung Tab S3 but I also love my Samsung TabPro S - both have different purposes.