Closed achigeor closed 5 years ago
@achigeor See the reply here: https://github.com/XiaoMi/mace/issues/1#issuecomment-462580008
Welcome to post the results for ARM Compute Library to make the comparison, and adding an executor will be highly appreciated.
Are there any insights as to why kirin 970 GPU is that much slower than Snapdragon 845? The compute capabilities should be around the same for these two SoCs right?
For example mobilenetsv2 benchmark runs at
~10ms
forsdm845
and47.597ms
forkirin970
(optimized). I also see big differences in my custom model. On asdm845
I get around75ms
, while onkirin980
I get around250ms
.Is it because snapdragon is actually that much faster, or because of how Mace ops / kernels are implemented? If it's the latter, what would be a good place to start working on possible optimizations? Would you expect improvements if ARM Compute is used for ARM SoCs?