Documentation improvements.
Fix Model::pools documentation.
Specify that an output cannot overlap with an output/input/constant.
Document circumstances under which a prepared model should be expected to execute correctly.
Bug: 87805381
Bug: 79888238
Bug: 77237715
Test: mma at tree root
Change-Id: Ibf3daacad79f1d7e6127acf3887bd98b7c6bdf4e
Merged-In: Ibf3daacad79f1d7e6127acf3887bd98b7c6bdf4e
diff --git a/neuralnetworks/1.0/IPreparedModel.hal b/neuralnetworks/1.0/IPreparedModel.hal
index ee406fb..ecaa7f8 100644
--- a/neuralnetworks/1.0/IPreparedModel.hal
+++ b/neuralnetworks/1.0/IPreparedModel.hal
@@ -42,6 +42,12 @@
* execute function. This callback must be provided with the ErrorStatus of
* the execution.
*
+ * 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, then the execution should launch
+ * and complete successfully (ErrorStatus::NONE). There must be
+ * no failure unless the device itself is in a bad state.
+ *
* Multiple threads can call the execute function on the same IPreparedModel
* object concurrently with different requests.
*