NN HAL: Upgrade IPreparedModel::executeSynchronously to 1.3.
Bug: 143242728
Test: 1.3 VTS with sample driver
Change-Id: I4b74e8ac031c5d793cf7e5d66190734949367538
diff --git a/neuralnetworks/1.3/IPreparedModel.hal b/neuralnetworks/1.3/IPreparedModel.hal
index c04809f..7aea416 100644
--- a/neuralnetworks/1.3/IPreparedModel.hal
+++ b/neuralnetworks/1.3/IPreparedModel.hal
@@ -18,9 +18,11 @@
import @1.0::ErrorStatus;
import @1.0::Request;
-import @1.2::MeasureTiming;
import @1.2::IExecutionCallback;
import @1.2::IPreparedModel;
+import @1.2::MeasureTiming;
+import @1.2::OutputShape;
+import @1.2::Timing;
/**
* IPreparedModel describes a model that has been prepared for execution and
@@ -62,8 +64,8 @@
* values, the execution should complete successfully (ErrorStatus::NONE):
* There must be no failure unless the device itself is in a bad state.
*
- * Any number of calls to the execute, execute_1_2, execute_1_3, and executeSynchronously
- * functions, in any combination, may be made concurrently, even on the same
+ * Any number of calls to the execute* and executeSynchronously* functions,
+ * in any combination, may be made concurrently, even on the same
* IPreparedModel object.
*
* @param request The input and output information on which the prepared
@@ -87,4 +89,60 @@
*/
execute_1_3(Request request, MeasureTiming measure, IExecutionCallback callback)
generates (ErrorStatus status);
+
+ /**
+ * Performs a synchronous execution on a prepared model.
+ *
+ * The execution is performed synchronously with respect to the caller.
+ * executeSynchronously_1_3 must verify the inputs to the function are
+ * correct. If there is an error, executeSynchronously_1_3 must immediately
+ * return with the appropriate ErrorStatus value. If the inputs to the
+ * function are valid and there is no error, executeSynchronously_1_3 must
+ * perform the execution, and must not return until the execution is
+ * complete.
+ *
+ * The caller must not change the content of any data object referenced by
+ * 'request' (described by the {@link @1.0::DataLocation} of a
+ * {@link @1.0::RequestArgument}) until executeSynchronously_1_3
+ * returns. executeSynchronously_1_3 must not change the content of any of the
+ * data objects corresponding to 'request' inputs.
+ *
+ * If the prepared model was prepared from a model wherein all tensor
+ * operands have fully specified dimensions, and the inputs to the function
+ * are valid, and at execution time every operation's input operands have
+ * legal values, then the execution should complete successfully
+ * (ErrorStatus::NONE): There must be no failure unless the device itself is
+ * in a bad state.
+ *
+ * Any number of calls to the execute* and executeSynchronously* functions,
+ * in any combination, may be made concurrently, even on the same
+ * IPreparedModel object.
+ *
+ * @param request The input and output information on which the prepared
+ * model is to be executed.
+ * @param measure Specifies whether or not to measure duration of the execution.
+ * The duration runs from the time the driver sees the call
+ * to the executeSynchronously_1_3 function to the time the driver
+ * returns from the function.
+ * @return status Error status of the execution, must be:
+ * - NONE if execution is performed successfully
+ * - DEVICE_UNAVAILABLE if driver is offline or busy
+ * - GENERAL_FAILURE if there is an unspecified error
+ * - OUTPUT_INSUFFICIENT_SIZE if at least one output
+ * operand buffer is not large enough to store the
+ * corresponding output
+ * - INVALID_ARGUMENT if one of the input arguments is
+ * invalid
+ * @return outputShapes A list of shape information of model output operands.
+ * The index into "outputShapes" corresponds to the index
+ * of the output operand in the Request outputs vector.
+ * outputShapes must be empty unless the status is either
+ * NONE or OUTPUT_INSUFFICIENT_SIZE.
+ * @return Timing Duration of execution. Unless measure is YES and status is
+ * NONE, all times must be reported as UINT64_MAX. A driver may
+ * choose to report any time as UINT64_MAX, indicating that
+ * measurement is not available.
+ */
+ executeSynchronously_1_3(Request request, MeasureTiming measure)
+ generates (ErrorStatus status, vec<OutputShape> outputShapes, Timing timing);
};