541e24311de0561a27bcba7f197f9bd46be67359 |
|
10-Apr-2018 |
David Gross <dgross@google.com> |
Fix documentation. 1. Fix documentation for Operand::numberOfConsumers. 2. Fix typos. Bug: 69055733 Bug: 76016141 Bug: 74111771 Test: NeuralNetworksTest_static Test: VtsHalNeuralnetworksV1_0TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.0::IDevice/sample-all Test: VtsHalNeuralnetworksV1_1TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.1::IDevice/sample-all Change-Id: Ib3d5bbfa701070597731992c3867f72d7b0280bd
/hardware/interfaces/neuralnetworks/1.0/IDevice.hal
|
cf22a57c1a05272d055b0deaa10094852dece797 |
|
22-Sep-2017 |
Michael Butler <butlermichael@google.com> |
NNAPI HAL: Change IEvent to explicit callbacks IEvent was a synchronization primitive which caused some confusion in the interface. Originally the event object was paired with an asynchronous task, and the asynchronous task would signal this event when the corresponding output was ready to be used. In the case of IDevice::prepareModel, the function call would return an IPreparedModel object that was not guaranteed to be prepared until the runtime had returned from waiting on the corresponding event object. The event object has been changed to two explicit callbacks-- IPreparedModelCallback and IExecutionCallback. Now, IDevice::prepareModel no longer returns an unfinished IPreparedModel; instead, it will pass the IPreparedModel object to the runtime through IPreparedModelCallback::notify. When the runtime retreives the IPreparedModel object, the asynchronous task has already finished preparing the model. The two callbacks are used for different purposes. Each has its own version of notify to pass the data back to the runtime: * IPreparedModelCallback::notify(ErrorStatus, IPreparedModel) * IExecutionCallback::notify(ErrorStatus) Bug: 63905942 Test: mm, vts, ml/nn/runtime/tests Change-Id: I0c88cd262ba762e0af15e9da31ebe813a5d150b2
/hardware/interfaces/neuralnetworks/1.0/IDevice.hal
|
926df1e1823e633090a2248be0f1ac66933750ed |
|
20-Sep-2017 |
Michael Butler <butlermichael@google.com> |
Removed WIP tag from Neuralnetworks HAL Additionally cleaned up some comments and formatting. Bug: 63905942 Test: not needed Change-Id: I0306f6d37f3c9ce9b365b5f838c27e81fa001ccd
/hardware/interfaces/neuralnetworks/1.0/IDevice.hal
|
c7821107652db4724b6c60d483824d72b8a6b663 |
|
12-Sep-2017 |
Michael Butler <butlermichael@google.com> |
Add documentation to the Neuralnetworks HIDL HAL. Bug: 63905942 Test: not needed Change-Id: I1582d20e66ef939581d82f21088f0db0bc0f5eb7
/hardware/interfaces/neuralnetworks/1.0/IDevice.hal
|
61ae6edbe635759cece1102749ec4cb6e6b7e485 |
|
12-Sep-2017 |
Michael Butler <butlermichael@google.com> |
Neuralnetworks HAL cleanup -- hardware/interfaces Does three primary cleanups: 1) Removes unused OperandTypes, creates OEM types 2) Creates explicit ErrorStatus; functions return status 3) IDevice::initialize renamed to getCapabilities, IDevice::getSupportedSubgraph renamed to getSupportedOperations Additionally fixes the corresponding VTS tests. Bug: 63905942 Test: mm, vts Change-Id: Ib4c61b9b13963ac2367f21dc3c20e5946eb955a9
/hardware/interfaces/neuralnetworks/1.0/IDevice.hal
|
e9dc1674f0b45a4a076a1161616fa66e8c784046 |
|
11-Sep-2017 |
Michael Butler <butlermichael@google.com> |
Make prepareModel asynchronous. Updated the corresponding VTS tests. Bug: 63905942 Test: mm, vts Change-Id: Ie520af845f491dbdd93ea66fd643d77cfb4703f7
/hardware/interfaces/neuralnetworks/1.0/IDevice.hal
|
376ec0c0fd4a3f6b661599f37a03d66cbde9caa7 |
|
28-Jul-2017 |
Michael Butler <butlermichael@google.com> |
Move neuralnetworks HAL to hardware/interfaces The neuralnetworks hal was placed in frameworks/ml/nn/hardware/interfaces while VTS tests were being developed. This CL moves it to hardware/interfaces and another CL removes it from frameworks/ml/nn/hardware/interfaces. VTS tests included in a sibling CL in this topic. Bug: 63905942 Test: mm -j40 Change-Id: I0e6c84de72a763edbaef3e9b3063c3ecca216337
/hardware/interfaces/neuralnetworks/1.0/IDevice.hal
|