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
diff --git a/neuralnetworks/1.0/IDevice.hal b/neuralnetworks/1.0/IDevice.hal
index 91a9555..49c2967 100644
--- a/neuralnetworks/1.0/IDevice.hal
+++ b/neuralnetworks/1.0/IDevice.hal
@@ -16,8 +16,7 @@
package android.hardware.neuralnetworks@1.0;
-import IEvent;
-import IPreparedModel;
+import IPreparedModelCallback;
/**
* This interface represents a device driver.
@@ -37,10 +36,9 @@
/**
* Gets the supported operations in a model.
*
- * getSupportedSubgraph provides a more nuanced indication on whether a
- * model is able to be compiled by the driver. Having the entire model
- * allows for additional information such as tensor shapes to inputs or
- * tensor strides, information which is not known in "initialize".
+ * getSupportedSubgraph indicates which operations of a model are fully
+ * supported by the vendor driver. If an operation may not be supported for
+ * any reason, getSupportedOperations must return false for that operation.
*
* @param model A model whose operations--and their corresponding
* operands--are to be verified by the driver.
@@ -48,7 +46,7 @@
* - NONE if successful
* - DEVICE_UNAVAILABLE if driver is offline or busy
* - GENERAL_FAILURE if there is an unspecified error
- * - INVALID_ARGUMENT when provided model is invalid
+ * - INVALID_ARGUMENT if provided model is invalid
* @return supportedOperations A list of supported operations, where true
* indicates the operation is supported and
* false indicates the operation is not
@@ -60,29 +58,60 @@
generates (ErrorStatus status, vec<bool> supportedOperations);
/**
- * Prepares a model for execution.
+ * Creates a prepared model for execution.
*
* prepareModel is used to make any necessary transformations or alternative
- * representations to a model for execution, possible including
+ * representations to a model for execution, possiblly including
* transformations on the constant data, optimization on the model's graph,
- * or compilation into the device's native binary format.
+ * or compilation into the device's native binary format. The model itself
+ * is not changed.
+ *
+ * The model is prepared asynchronously with respect to the caller. The
+ * prepareModel function must verify the inputs to the prepareModel function
+ * are correct. If there is an error, prepareModel must immediately invoke
+ * the callback with the appropriate ErrorStatus value and nullptr for the
+ * IPreparedModel, then return with the same ErrorStatus. If the inputs to
+ * the prepareModel function are valid and there is no error, prepareModel
+ * must launch an asynchronous task to prepare the model in the background,
+ * and immediately return from prepareModel with ErrorStatus::NONE. If the
+ * asynchronous task fails to launch, prepareModel must immediately invoke
+ * the callback with ErrorStatus::GENERAL_FAILURE and nullptr for the
+ * IPreparedModel, then return with ErrorStatus::GENERAL_FAILURE.
+ *
+ * When the asynchronous task has finished preparing the model, it must
+ * immediately invoke the callback function provided as an input to
+ * prepareModel. If the model was prepared successfully, the callback object
+ * must be invoked with an error status of ErrorStatus::NONE and the
+ * produced IPreparedModel object. If an error occurred preparing the model,
+ * the callback object must be invoked with the appropriate ErrorStatus
+ * value and nullptr for the IPreparedModel.
*
* The only information that may be unknown to the model at this stage is
- * the shape of the tensors, which may only be known at execution time.
+ * the shape of the tensors, which may only be known at execution time. As
+ * such, some driver services may return partially prepared models, where
+ * the prepared model can only be finished when it is paired with a set of
+ * inputs to the model. Note that the same prepared model object can be
+ * used with different shapes of inputs on different (possibly concurrent)
+ * executions.
+ *
+ * Multiple threads can call prepareModel on the same model concurrently.
*
* @param model The model to be prepared for execution.
- * @param event A synchronization callback that must be signaled once the
- * execution has finished.
- * @return status Error status of the call, must be:
+ * @param callback A callback object used to return the error status of
+ * preparing the model for execution and the prepared model
+ * if successful, nullptr otherwise. The callback object's
+ * notify function must be called exactly once, even if the
+ * model could not be prepared.
+ * @return status Error status of launching a task which prepares the model
+ * in the background; must be:
* - NONE if preparation task is successfully launched
* - DEVICE_UNAVAILABLE if driver is offline or busy
* - GENERAL_FAILURE if there is an unspecified error
- * - INVALID_ARGUMENT when one of the input arguments is
+ * - INVALID_ARGUMENT if one of the input arguments is
* invalid
- * @return preparedModel A handle to the resultant prepared model.
*/
- prepareModel(Model model, IEvent event)
- generates (ErrorStatus status, IPreparedModel preparedModel);
+ prepareModel(Model model, IPreparedModelCallback callback)
+ generates (ErrorStatus status);
/**
* Returns the current status of a driver.