SPEC2006: Performance Parity At Different Efficiency

Having shed a bit of light on the new microarchitectural aspects of the memory subsystems of the new Snapdragon 855 and Exynos 9820, the question is now how the new chipsets perform in more significant macro workloads. For a continued reference CPU workload we’re again falling back to using SPEC.

The SPEC harness we’re using is compiled with simple and straightforward “-Ofast” compilation flag with the Android devices having an instruction tuning to Cortex-A53s as I’ve found this to give the highest average scores across a the wide range of SoCs.

It’s to be noted that SPEC2006 has been deprecated in favour of SPEC2017, however as the 2006 variant is well understood in terms of its workload characterisation for this article I’m still sticking the older version. We’ll be switching over to SPEC2017 later this spring/summer and covering any new data in a separate article.

In the SPECint2006 suite of integer workloads, both chipsets don’t showcase any big surprises in performance. The new Snapdragon 855 variant of the Galaxy S10+ confirms the performance figures we were able to measure on the QRD platform back in January with little to no deviation. The Snapdragon posted excellent performance improvements over the Snapdragon 845 of last year and ties in with the Kirin 980 as the fastest Android SoCs for this year.

The Exynos 9820’s performance figures are also relatively unsurprising for me as I had muted expectations. Here we do see some relatively healthy performance improvements considering that we’re talking about mostly IPC gains on the part of the new Cheetah cores, as the new chipset is a mere 30MHz faster than last year’s chip.

The biggest improvements are found in 429.mcf as well as 471.omnetpp where the new M4 cores perform respectively 32% and 27% better. Both these workloads are the most latency and memory sensitive workloads in the SPECint2006 suite, so given the new chip’s improved memory subsystem it’s no wonder that it’s here where we see the biggest performance jumps. Mcf is also one of the rare tests where the Exynos manages to beat the Cortex A76’s in the S855 and K980 by a more significant amount. Unfortunately for the rest of the workloads being tied is the best-case scenario as it loses out by a small amount in all other workloads.

One thing that I have to note is that it’s possible that big parts of the benchmark probably weren’t run at the peak 2.73GHz clocks of the new M4 cores. Samsung has now enabled a current limiter circuit on the CPU cores and will now more aggressively throttle down the frequency of the CPU in high-power workloads. This means that needy workloads will only see the peak frequencies in the range of 5-10 seconds before throttling down to frequencies of 2.3-2.5GHz. I didn’t have time to have a more thorough monitoring of what the chip is doing during SPEC so it’s something I’ll have to follow up on.

When it comes to power efficiency, the new Exynos 9820 does improve notably compared to last year’s Exynos 9810. It seems that the biggest power efficiency improvements happened on the most memory intensive workloads, in particular 462.libquantum’s 74% efficiency improvement all while improving performance is quite impressive.

Having said that, as I had theorized back based on Samsung’s own marketing numbers, the efficiency gains just aren’t enough to actually compete against the 7nm Cortex A76 cores in the new Snapdragon and Kirin chipsets as Samsung’s chip loses out in every workload.

In the C/C++ workloads of SPECfp2006 we see a similar picture as in the integer workloads. The Snapdragon 855 distinguishes itself here as being able to distance itself more from the Kirin 980 in a few workloads such as 447.dealII and 453.povray, all while maintaining almost equal excellent power efficiency.

The Exynos 9820 here has a hard time showcasing big performance improvements compared to its predecessor, but the one workload where we see a massive jump is 470.lbm, with an 84% jump in performance compared to the M3 cores of last year. This workload is particularly latency and bandwidth intensive so the new load/store unit arrangement of the M4 cores seem to favour it a lot.

In terms of power efficiency, what is interesting is that the new Exynos doesn’t lose as badly as in some of the integer workloads, although it still very much loses to the Snapdragon and Kirin.

Again to have a wider range of performance comparison across ARMv8 cores in mobile here’s a grand overview of the most relevant SoCs we’ve tested:

Finally it’s important to have a wider overview of the performance and efficiency of the current generation chipsets:

In the SPECint2006 geomean score, the Exynos 9820 slightly loses out in the to the Snapdragon 855. More importantly, it uses 47% more energy and power to achieve this same performance. In SPECfp2006 this efficiency difference drops to 21% - although the performance on the M4 cores is also 7% less.

What is most interesting about the new Snapdragon 855 and Exynos 9820 chips is that they have multiple CPU groups, so I went ahead and also measured performance and power of the middle Cortex A76 cores of the Qualcomm chipset against the Cortex A75 cores of the Samsung silicon.

Unexpectedly, the Snapdragon chipset’s “middle” cores beat the Exynos’ middle cores by a hefty amount. At 2.4GHz, the three middle cores of the Snapdragon actually aren’t weak by any means, and only fall behind the Prime core by 15-19% in performance, for an 18% frequency deficit. The Cortex A75 cores on the Exynos chip are 35% weaker than the middle cores of the Snapdragon. Here a more even comparison probably would have been the 1.92GHz middle A76 cores of the Kirin 980, however I wasn’t able to benchmark them separately on Huawei’s devices.

Energy efficiency of Samsung’s A75 cores are good – although it comes at a larger performance deficit, they’re in line with the energy consumption of the A76 cores in the competition.

In the quest to find an answer on how much the actual process node impacts power efficiency between the 7nm Snapdragon and 8nm Exynos, I also went ahead and ran SPEC on the Cortex A55 cores of both chipsets. After a gruelling 11.5 hours of runtime we finally see that the little cores only post a fraction of the performance of the big core siblings. What is actually quite embarrassing though is that the power efficiency is also quite atrocious for the given performance. Here other blocks of the SoC as well as other active components are using up power without actually providing enough performance to compensate for it. This is a case of the system running at a performance point below the crossover threshold where racing to idle would have made more sense for energy.

Apple’s small cores are just such an incredible contrast here: Even though the absolute power isn’t that much bigger than the Cortex A55 cores, the Tempest and Mistral cores are 2.5x faster than an A55, which also results in energy efficiency that is around 2x better.

Finally getting back to the reason why I measured the A55 cores: The Exynos 9820 here again loses out not only in performance but also in power efficiency. Even though the chip’s A55 cores are clocked in higher at 1.95GHz, it’s likely the lack of L2 caches is handicapping the CPUs in IPC, and thus falls behind the 1.78GHz Snapdragon A55’s. Power efficiency here is better on the Snapdragon SoC by 15-18%.

During last summer’s Hot Chips presentation of the M3 CPU core Samsung had remarked to me that the M4 would be the competing against the Cortex A76, and not the M3. While in terms of power efficiency there’s the matter of us not having a valid apples-to-apples process node comparison at hands, at least from a performance perspective it doesn’t look like the new M4 cores are all that impressive, as they just barely manage hold up against the A76 in the Snapdragon and Kirin. Samsung’s CPU just looks to still have too many rough edges and bottlenecks, and thus ends up performing far below of what we’d expect of a microarchitecture that fundamentally on paper is wider than Arm’s Cortex A76.

Memory Subsystems Compared - Bandwidth & MLP Inference Performance: APIs, Where Art Thou?
Comments Locked


View All Comments

  • Azurael - Saturday, March 30, 2019 - link

    "the M4 cores should very much be quite a lot more efficiency than the A75 cores"

    *brain explodes*
  • Samus - Sunday, March 31, 2019 - link

    They should have gone with a pop-out camera than the hole punch. Hate to say it but apples notch was the best solution other than a pop-up camera.
  • Javert89 - Sunday, March 31, 2019 - link

    Just a precisation. Adreno 640 do not have 50% more execution units, indeed it should be the usual 2 core design seen in the 630.. only the Adreno of the bigger Snapdragon 8cx has 3 cores plus a 128 bit memory controller
  • Andrei Frumusanu - Sunday, March 31, 2019 - link

    It *does* have 50% more execution units / ALUs; https://images.anandtech.com/doci/13680/Screenshot...
  • bjtags - Sunday, March 31, 2019 - link

    Huawei Mate SE 99% of this for 1/4 the Price.....
  • s.yu - Monday, April 1, 2019 - link

    Entirely laughable.
  • tipoo - Sunday, March 31, 2019 - link

    The efficiency + performance of the A12 even in comparison to this continues to be crazy, and we're on the other side of the year of that launching.

    I'd be really interested to see that put against x86 cores in SPEC2006
  • name99 - Monday, April 1, 2019 - link

    Here you are. Not a PERFECT comparison but the best currently available:



    Would be great if we had comparison graphs, and if it were compiler to compiler (both LLVM) and if it were desktop cores, and if it were Coffee Lake, and ...
    But as I said it's the best available right now.

    Basically (especially if Apple adds SVE to their desktop ARM core) they probably have nothing to fear in terms of reduced performance by switching to the A12 successor.
  • s.yu - Monday, April 1, 2019 - link

    I gotta say I'm surprised from the first sample that the S9+ was the best among the Samsung's and very, very close to Pixel performance which is still overall No.1, S10PS only comes second, S10PE is about as bad as the Note9, I think some of these have defective lenses with especially bad resolution on the edge(s)...the difference is much smaller in the center of the frame. So it could be said that even with the f/2.4 aperture, the Samsung's lens has QC issues that aren't masked. It would be interesting to see how P30P's f/1.6 lens fares.
    S9+ didn't stand out so much in the HDR scenes though, but from the landscapes I'd say the S9+ probably got an especially good lens sample, better than the S10PS and much better than the S10PE. How the Pixel reproduces texture is just incredible, though many of the scenes are rendered darker, there's little sign of the crushed black issue, i.e. it's just darker, but high quality, it's still my definition of realistic among almost any smartphone output, it would obviously stand better to sharpening or NR in post.
    Regarding the wide shots...HDR's the differential. The S10PS outperformed the Mate20P despite a wider FoV in most of the landscape samples, but failed to do so in the shot under the bridge.
    IMO in low light shots the PS still wins overall, to the PE, PE seems to have issues mapping black (with minimal actual shadow advantage) while in the midtones as both win in certain instances it's a toss. Still nothing beats the Pixel...Mate20P's auto was especially bad in the maintenance center shot, that was interesting considering the sensor size.
    And I have to disagree just from the first night sample that the PS isn't matching Mate20P's night mode, it's evident that it did a poor job on the sand, but *everything else* on the frame is better, the subject, the houses in the background, the light posts. It is clear in the second night mode shot with a low DR range though, that the Samsung's messed up.
  • lty0432 - Monday, April 1, 2019 - link

    Hi author !
    I think this kind of technical articles on Exynos and SD has been best out there.
    Can I possible get your opinion on how mobile processors stack up against PC processors ?
    Are there any benchmark comparison articles ?

Log in

Don't have an account? Sign up now