The Nubia Red Magic 3 Review: A 90Hz Gaming Phone With Active Cooling
Machine Learning Inference Performance
AIMark 3
AIMark makes use of various vendor SDKs to implement the benchmarks. This means that the end-results really aren’t a proper apples-to-apples comparison, however it represents an approach that actually will be used by some vendors in their in-house applications or even some rare third-party app.

In AIMark, the Red Magic 3 performs alongside the top Snapdragon 855 devices on the market, which is again a good sign of the software optimisations of the phone’s BSP.
AIBenchmark 3
AIBenchmark takes a different approach to benchmarking. Here the test uses the hardware agnostic NNAPI in order to accelerate inferencing, meaning it doesn’t use any proprietary aspects of a given hardware except for the drivers that actually enable the abstraction between software and hardware. This approach is more apples-to-apples, but also means that we can’t do cross-platform comparisons, like testing iPhones.
We’re publishing one-shot inference times. The difference here to sustained performance inference times is that these figures have more timing overhead on the part of the software stack from initialising the test to actually executing the computation.
AIBenchmark 3 - NNAPI CPU
We’re segregating the AIBenchmark scores by execution block, starting off with the regular CPU workloads that simply use TensorFlow libraries and do not attempt to run on specialized hardware blocks.

In AI Benchmark’s CPU workloads, the RM3 fares average amongst its S855 counterparts, but nothing too much out of line that it’d be an issue.
AIBenchmark 3 - NNAPI INT8

AIBenchmark 3 - NNAPI FP16

AIBenchmark 3 - NNAPI FP32

On the INT8, FP16 and FP32 side, the RM3 performs very well and is amongst the top performing phones. This advantage should simply be due to the RM3 having the latest software stack employed.
Originally published at https://www.anandtech.com/show/14717/the-red-magic-3-review (Wayback Machine).