| commit | a0b45bf21b1d6dbd6c8d1e14857dd1ad85ac757a | [log] [tgz] |
|---|---|---|
| author | Michael Butler <butlermichael@google.com> | Wed Apr 11 18:05:31 2018 -0700 |
| committer | Michael Butler <butlermichael@google.com> | Thu Apr 12 19:18:23 2018 -0700 |
| tree | b58e5d356398b5a3afc4414eca9830c3bcc758fd | |
| parent | e53c0471ee34ec5e1e41038e8f6a901722adb7c6 [diff] |
NNAPI: Add execution preference to prepareModel (runtime) A model can be compiled in different ways to optimize for different use-cases. This CL propagates the execution preference across the HAL so that the NN service can better fit the users needs. Bug: 77864669 Test: mma Test: NeuralNetworksTest_static Test: VtsHalNeuralnetworksV1_1TargetTest Change-Id: I93079b18224ea10cb0a23bfbdc1ed80e302071a8