I am not sure if the value 31% has a serious impact on the other app. So that I would ask for your advice. Previously, I originally expected to lower the cpu percentage by reducing the model op. when I put a model with only 6 biliear_interpolation ops into coreml, the cpu percentage is 20%(equal on cpu, cpuandgpu&all), so I consider if the only coreML scheduling occuppy the 20% cpu? And I am not meaning that coreML occupy more cpu than other's AI engine framework. Thank you very much.

I am not sure if the value 31% has a serious impact on the other app. So that I would ask for your advice. Previously, I originally expected to lower the cpu percentage by reducing the model op. when I put a model with only 6 biliear_interpolation ops into coreml, the cpu percentage is 20%(equal on cpu, cpuandgpu&all), so I consider if the only coreML scheduling occuppy the 20% cpu? And I am not meaning that coreML occupy more cpu than other's AI engine framework. Thank you very much.