Evolution-x/hardware_interfaces
1
0
Fork 0
mirror of https://github.com/Evolution-X/hardware_interfaces synced 2026-02-01 11:36:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge "Improve documentation related to execution."

Browse Source
This commit is contained in:
David Gross
2019-06-21 18:40:03 +00:00
committed by Gerrit Code Review
parent 102e02fbae f406bf9b1e
commit b575cedd74
3 changed files with 31 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
current.txt
View File

@@ -478,4 +478,6 @@ b53ac9d61c24efb16a2d63a861cef20680f6d57adb244a03b9778c675550628b android.hardwar
# ABI preserving changes to HALs during Android R
b69a7615c508acf5c5201efd1bfa3262167874fc3594e2db5a3ff93addd8ac75 android.hardware.keymaster@4.0::IKeymasterDevice
ad431c8de51c07934a068e3043d8dd0537ac4d3158627706628b123f42df48dc android.hardware.neuralnetworks@1.0::IPreparedModel
aafcc10cf04ab247e86d4582586c71c6b4c2b8c479241ffa7fe37deb659fc942 android.hardware.neuralnetworks@1.2::IPreparedModel
1a6e2bd289f22931c526b21916910f1d4c436b7acb9556e4243de4ce8e6cc2e4 android.hardware.soundtrigger@2.0::ISoundTriggerHwCallback

7
neuralnetworks/1.0/IPreparedModel.hal
View File

@@ -42,6 +42,13 @@ interface IPreparedModel {
* execute function. This callback must be provided with the ErrorStatus of
* the execution.
*
* If the launch is successful, the caller must not change the content of
* any data object referenced by 'request' (described by the
* {@link DataLocation} of a {@link RequestArgument}) until the
* asynchronous task has invoked the callback object. The asynchronous task
* 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, then the execution should launch

25
neuralnetworks/1.2/IPreparedModel.hal
View File

@@ -47,6 +47,13 @@ interface IPreparedModel extends @1.0::IPreparedModel {
* execute_1_2 function. This callback must be provided with the ErrorStatus of
* the execution.
*
* If the launch is successful, 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 the
* asynchronous task has invoked the callback object. The asynchronous task
* 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, then the execution should launch
@@ -90,6 +97,12 @@ interface IPreparedModel extends @1.0::IPreparedModel {
* 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
* returns. executeSynchronously 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, then the execution should complete successfully
@@ -135,9 +148,15 @@ interface IPreparedModel extends @1.0::IPreparedModel {
* @param callback A callback object used to retrieve memory resources
* corresponding to a unique identifiers ("slots").
* @param requestChannel Used by the client to send a serialized Request to
* the Burst for execution. requestChannel must not be
* used to pass a second Request object until a result
* has been received from resultChannel.
* the Burst for execution. The client must not change
* the content of any data object referenced by the
* Request (described by the {@link @1.0::DataLocation}
* of an {@link OperandInformation}) until a result
* has been received from resultChannel. Execution
* must not change the content of any of the data
* objects corresponding to Request inputs. requestChannel
* must not be used to pass a second Request object
* until a result has been received from resultChannel.
* @param resultChannel Used by the service to return the results of an
* execution to the client: the status of the execution
* and OutputShape of all output tensors. resultChannel