AI-Benchmark - The fastest AI chip's AI Performance Ranking

During the past months, AI Benchmark scores were used in a number of events and publications, rising many questions regarding the performance of some newly presented chipsets and phones. We are providing our official explanation of the results and score updates for February 2019 below.

 

AI rush:  Snapdragon 855, MediaTek P90, Kirin 980 or Exynos 9820  —  who rules the game?

AI rush:  Snapdragon 855, MediaTek P90, Kirin 980 or Exynos 9820  —  who rules the game?

1  -  This SoC provides acceleration support for both float and quantized AI models ( via NNAPI )
2  -  This SoC provides native acceleration support for float AI models ( via NNAPI )
3  -  This SoC provides native acceleration support for quantized AI models ( via NNAPI )
4  -  This SoC might be using unofficial / prototype hardware or drivers
5  -  These are the results of an early prototype. The results of the commercial SoC might be different

 

Snapdragon 855, currently placed on top of our ranking, is without a doubt one of the fastest chipsets available on the market. It is demonstrating very strong AI performance and provides hardware acceleration for both float and quantized neural networks: in the first case inference is done on Adreno 640 GPU, while quantized networks are running on its built-in Hexagon 690 DSP. This combination of GPU and DSP allows Qualcomm to omit the necessity of using a separate NPU for accelerating AI computations, which leads to smaller SoC size and its easier development. However, this decision also has its costs - Snapdragon's GPU cannot be fully utilized for running neural networks as its design was originally developed for pure computer graphics tasks, and thus only a small amount of its power can be used when running AI computations. This might also cause some difficulties in their future products development, as there are generally two ways of improving Snapdragon's AI capabilities: increasing GPU performance or radically changing its design, though the latter will also cause the change of the whole graphical system and drivers. And the third option is to introduce a separate dedicated AI chip, which actually might be the case in the next Qualcomm high-end SoC.

MediaTek P90 was quite a surprise for the market. Why this mid-range chipset from MediaTek is on top of our rating? The answer is simple - because its AI performance is completely comparable to the one of Snapdragon 855. In contrast to Qualcomm, MediaTek decided to go for a separate AI chip that was built based on their in-house GPU design significantly modified for deep learning tasks. The results are more than impressive - though P90's theoretical GMACs performance is notably lower compared to Snapdragon 855, their real speed in AI tasks is almost the same. We should also mention that the accuracy of the computations was not sacrificed for the sake of speed - sometimes it is even higher than with default Android drivers. The only downsides that this SoC has are its 30% lower CPU performance compared to Qualcomm's and Kirin's flagship SoCs and quite mediocre GPU, though it is not used in AI tasks and thus is actually irrelevant for our tests.

HiSilicon Kirin 980 was presented almost half a year ago and is showing somewhat lower scores than SDM855 and Helio P90. Does this mean that it is doing a worse job? Not really. Its float performance is almost the same as in case of the above SoCs, which means that you will get comparable speed when running float neural networks. We should emphasize that this is still the main type of models used in AI research and development: every network architecture can be trained as a float model. Instead, only some of them can be transformed into quantized models as this is often associated with a huge accuracy drop not acceptable for tasks like face recognition, image super-resolution or photo enhancement. And here the performance of Kirin chipset is still very strong.

 

You can read the full news from below site.

http://ai-benchmark.com/news_2019_02_05_february_updates.html

AI-Benchmark

http://ai-benchmark.com/ranking_processors.html#footnote

AI-Benchmark

https://play.google.com/store/apps/details?id=org.benchmark.demo

AI Benchmark - Google Play 앱