Inference Performance: APIs, Where Art Thou?

Having covered the new CPU complexes of both new Exynos and Snapdragon SoCs, up next is the new generation neural processing engines in each chip.

The Snapdragon 855 brings big performance improvements to the table thanks to a doubling of the HVX units inside the Hexagon 690 DSP. The HVX units in the last two generations of Snapdragon chips were the IP blocks who took the brunt of new integer neural network inferencing work, an area the IP is specifically adept at.

The new tensor accelerator inside of the Hexagon 690 was shown off by Qualcomm at the preview event back in January. Unfortunately one of the issues with the new block is that currently it’s only accessible through Qualcomm’s own SDK tools, and currently doesn’t offer acceleration for NNAPI workloads until later in the year with Android Q.

Looking at a compatibility matrix between what kind of different workloads are able to be accelerated by various hardware block in NNAPI reveals are quite sad state of things:

NNAPI SoC Block Usage Estimates
SoC \ Model Type INT8 FP16 FP32
Exynos 9820 GPU GPU GPU
Exynos 9810 GPU? GPU CPU
Snapdragon 855 DSP GPU GPU
Snapdragon 845 DSP GPU GPU
Kirin 980 GPU? NPU CPU

What stands out in particular is Samsung’s new Exynos 9820 chipset. Even though the SoC promises to come with an NPU that on paper is extremely powerful, the software side of things make it as if the block wouldn’t exist. Currently Samsung doesn’t publicly offer even a proprietary SDK for the new NPU, much less NNAPI drivers. I’ve been told that Samsung looks to address this later in the year, but how exactly the Galaxy S10 will profit from new functionality in the future is quite unclear.

For Qualcomm, as the HVX units are integer only, this means only quantised INT8 inference models are able to be accelerated by the block, with FP16 and FP32 acceleration falling back what should be GPU acceleration. It’s to be noted my matrix here could be wrong as we’re dealing with abstraction layers and depending on the model features required the drivers could run models on different IP blocks.

Finally, HiSilicon’s Kirin 980 currently only offers NNAPI acceleration for FP16 models for the NPU, with INT8 and FP32 models falling back to the CPU as the device are seemingly not using Arm’s NNAPI drivers for the Mali GPU, or at least not taking advantage of INT8 acceleration ine the same way Samsung's GPU drivers.

Before we even get to the benchmark figures, it’s clear that the results will be a mess with various SoCs performing quite differently depending on the workload.

For the benchmark, we’re using a brand-new version of Andrey Ignatov’s AI-Benchmark, namely the just released version 3.0. The new version tunes the models as well as introducing a new Pro-Mode that most interestingly now is able to measure sustained throughput inference performance. This latter point is important as we can have very different performance figures between one-shot inferences and back-to-back inferences. In the former case, software and DVFS can vastly overshadow the actual performance capability of the hardware as in many cases we’re dealing with timings in the 10’s or 100’s of milliseconds.

Going forward we’ll be taking advantage of the new benchmark’s flexibility and posting both instantaneous single inference times as well sequential throughput inference times; better showcasing and separating the impact of software and hardware capabilities.

There’s a lot of data here, so for the sake of brevity I’ll simply put up all the results up and we’ll go over the general analysis at the end:

AIBenchmark 3 - 1a - The Life - CPU (FP) AIBenchmark 3 - 1b - The Life - NNAPI (INT8) AIBenchmark 3 - 1c - The Life - NNAPI (FP16) AIBenchmark 3 - 2a - Zoo - NNAPI (INT8) AIBenchmark 3 - 2b - Zoo - CPU (FP) AIBenchmark 3 - 2c - Zoo - NNAPI (FP16) AIBenchmark 3 - 3a - Pioneers - CPU (INT) AIBenchmark 3 - 3b - Pioneers - NNAPI (INT8) AIBenchmark 3 - 3c - Pioneers - NNAPI (FP16) AIBenchmark 3 - 4 - Let's Play! - CPU (FP) AIBenchmark 3 - 5a - Masterpiece - NNAPI (INT8) AIBenchmark 3 - 5b - Masterpiece - NNAPI (FP16) AIBenchmark 3 - 6b - Cartoons - NNAPI (FP16) AIBenchmark 3 - 7a - Ms.Universe - CPU (INT) AIBenchmark 3 - 7b - Ms.Universe - CPU (FP) AIBenchmark 3 - 8 - Blur iT! - CPU (FP) AIBenchmark 3 - 9 - Berlin Driving - NNAPI (FP16) AIBenchmark 3 - 10a - WESPE-dn - NNAPI (FP16) AIBenchmark 3 - 10b - WESPE-dn - NNAPI (FP32)

As initially predicted, the results are extremely spread across all the SoCs.

The new tests also include workloads that are solely using TensorFlow libraries on the CPU, so the results not only showcase NNAPI accelerator offloading but can also serve as a CPU benchmark.

In the CPU-only tests, we see the Snapdragon 855 and Exynos 9820 being in the lead, however there’s a notable difference between the two when it comes to their instantaneous vs sequential performance. The Snapdragon 855 is able to post significantly better single inference figures than the Exynos, although the latter catches up in longer duration workloads. Inherently this is a software characteristic difference between the two chips as although Samsung has improved scheduler responsiveness in the new chip, it still lags behind the Qualcomm variant.

In INT8 workloads there is no contest as Qualcomm is far ahead of the competition in NNAPI benchmarks simply due to the fact that they’re the only vendor being able to offload this to an actual accelerator. Samsung’s Exynos 9820 performance here actually has also drastically improved thanks to the new Mali G76’s new INT8 dot-product instructions. It’s odd that the same GPU in the Kirin 980 doesn’t show the same improvements, which could be due to not up-to-date Arm GPU NNAPI drives on the Mate 20.

The FP16 performance crown many times goes to the Kirin 980 NPU, but in some workloads it seems as if they fall back to the GPU, and in those cases Qualcomm’s GPU clearly has the lead.

Finally for FP32 workloads it’s again the Qualcomm GPU which takes an undisputed lead in performance.

Overall, machine inferencing performance today is an absolute mess. In all the chaos though Qualcomm seems to be the only SoC supplier that is able to deliver consistently good performance, and its software stack is clearly the best. Things will evolve over the coming months, and it will be interesting to see what Samsung will be able to achieve in regards to their custom SDK and NNAPI for the Exynos NPU, but much like Huawei’s Kirin NPU it’s all just marketing until we actually see the software deliver on the hardware capabilities, something which may take longer than the actual first year active lifespan of the new hardware.

SPEC2006: Almost Performance Parity at Worse Efficiency System Performance
POST A COMMENT

228 Comments

View All Comments

  • luca.costantino - Friday, March 29, 2019 - link

    Way too much bloatware on Samsung products for my taste. I would never consider buying a phone from them. Reply
  • shabby - Friday, March 29, 2019 - link

    Are you offended or something? That's the dumbest comment I ever read, I just sold an s9 and wiped it, the buyer said I thought it would have more bloatware but it doesn't. Reply
  • liteon163 - Friday, March 29, 2019 - link

    No need to be so harsh simply because you disagree with someone's opinion, dude. Don't be a jerk (that's not an opinion, that's a FACT proven by your initial reply). Reply
  • close - Sunday, March 31, 2019 - link

    Samsung has their own equivalent of every single piece of software that comes with Android and you already didn't want in your phone. @shabby just wanted to tell us he knows how to follow a decrapify tutorial. The phone is still crappy software-wise but after putting in a lot of effort you can make it marginally less crappy. Yay? Reply
  • Vermite - Sunday, May 19, 2019 - link

    You're an idiot. Yay? Reply
  • s.yu - Sunday, March 31, 2019 - link

    There are smarter opinions and stupider opinions. Reply
  • goatfajitas - Friday, March 29, 2019 - link

    Yes, it does have alot of bloat. Reply
  • mazook - Friday, March 29, 2019 - link

    Dude, the ROM is about 4 GIGS.
    Think there's just a BIT of bloat in there?
    Reply
  • Samus - Sunday, March 31, 2019 - link

    I figured Android users are just used to bloat at this point. I’d you want a clean optimized mobile experience you either buy a Google phone, install a 3rd party ROM, or just buy an iPhone. Reply
  • notashill - Monday, April 1, 2019 - link

    The "bloatware free" Android One ROMs are like 12 gigs though they do keep 2 entire copies of the system partition for the seamless update feature. Very annoying especially considering how many Android One devices have 32GB storage. Reply

Log in

Don't have an account? Sign up now