Merge ""successful preparation means successful execution" guarantee neglects bad operation inputs" (3bb5f650) · Commits · e / os / android_hardware_interfaces

current.txt

+2 −2

Original line number	Original line	Diff line number	Diff line
	@@ -574,8 +574,8 @@ cfa81f229b69f9011c58f48264fcb552447430fe68610eac514e811e65bc306a android.hardwar
	# ABI preserving changes to HALs during Android R		# ABI preserving changes to HALs during Android R
	2410dd02d67786a732d36e80b0f8ccf55086604ef37f9838e2013ff2c571e404 android.hardware.camera.device@3.5::types		2410dd02d67786a732d36e80b0f8ccf55086604ef37f9838e2013ff2c571e404 android.hardware.camera.device@3.5::types
	b69a7615c508acf5c5201efd1bfa3262167874fc3594e2db5a3ff93addd8ac75 android.hardware.keymaster@4.0::IKeymasterDevice		b69a7615c508acf5c5201efd1bfa3262167874fc3594e2db5a3ff93addd8ac75 android.hardware.keymaster@4.0::IKeymasterDevice
	ad431c8de51c07934a068e3043d8dd0537ac4d3158627706628b123f42df48dc android.hardware.neuralnetworks@1.0::IPreparedModel		eb2fa0c883c2185d514be0b84c179b283753ef0c1b77b45b4f359bd23bba8b75 android.hardware.neuralnetworks@1.0::IPreparedModel
	fb382e986c10b8fbb797a8546e8f9ea6d1107bfe6f3fb7e57f6bbbf1f807a906 android.hardware.neuralnetworks@1.2::IDevice		fb382e986c10b8fbb797a8546e8f9ea6d1107bfe6f3fb7e57f6bbbf1f807a906 android.hardware.neuralnetworks@1.2::IDevice
	aafcc10cf04ab247e86d4582586c71c6b4c2b8c479241ffa7fe37deb659fc942 android.hardware.neuralnetworks@1.2::IPreparedModel		6c5081dd131eeb7eb02efece2187cd4d7d554197800bb520c92ff874cc238fa6 android.hardware.neuralnetworks@1.2::IPreparedModel
	1a6e2bd289f22931c526b21916910f1d4c436b7acb9556e4243de4ce8e6cc2e4 android.hardware.soundtrigger@2.0::ISoundTriggerHwCallback		1a6e2bd289f22931c526b21916910f1d4c436b7acb9556e4243de4ce8e6cc2e4 android.hardware.soundtrigger@2.0::ISoundTriggerHwCallback
	fd65298e1e09e0e3c781ab18305920d757dbe55a3b459ce17814ec5cf6dfee99 android.hardware.wifi@1.0::IWifiP2pIface		fd65298e1e09e0e3c781ab18305920d757dbe55a3b459ce17814ec5cf6dfee99 android.hardware.wifi@1.0::IWifiP2pIface

neuralnetworks/1.0/IPreparedModel.hal

+8 −5

Original line number	Original line	Diff line number	Diff line
	@@ -49,11 +49,14 @@ interface IPreparedModel {
	* must not change the content of any of the data objects corresponding to		* must not change the content of any of the data objects corresponding to
	* 'request' inputs.		* 'request' inputs.
	*		*
	* If the prepared model was prepared from a model wherein all		* If the prepared model was prepared from a model wherein all tensor
	* tensor operands have fully specified dimensions, and the inputs		* operands have fully specified dimensions, and the inputs to the function
	* to the function are valid, then the execution should launch		* are valid, then:
	* and complete successfully (ErrorStatus::NONE). There must be		* - the execution should launch successfully (ErrorStatus::NONE): There
	* no failure unless the device itself is in a bad state.		* must be no failure unless the device itself is in a bad state.
			* - if at execution time every operation's input operands have legal
			* values, the execution should 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		* Multiple threads can call the execute function on the same IPreparedModel
	* object concurrently with different requests.		* object concurrently with different requests.

neuralnetworks/1.2/IPreparedModel.hal

+18 −7

Original line number	Original line	Diff line number	Diff line
	@@ -54,11 +54,14 @@ interface IPreparedModel extends @1.0::IPreparedModel {
	* must not change the content of any of the data objects corresponding to		* must not change the content of any of the data objects corresponding to
	* 'request' inputs.		* 'request' inputs.
	*		*
	* If the prepared model was prepared from a model wherein all		* If the prepared model was prepared from a model wherein all tensor
	* tensor operands have fully specified dimensions, and the inputs		* operands have fully specified dimensions, and the inputs to the function
	* to the function are valid, then the execution should launch		* are valid, then:
	* and complete successfully (ErrorStatus::NONE). There must be		* - the execution should launch successfully (ErrorStatus::NONE): There
	* no failure unless the device itself is in a bad state.		* must be no failure unless the device itself is in a bad state.
			* - if at execution time every operation's input operands have legal
			* 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, and executeSynchronously		* Any number of calls to the execute, execute_1_2, and executeSynchronously
	* functions, in any combination, may be made concurrently, even on the same		* functions, in any combination, may be made concurrently, even on the same
	@@ -105,8 +108,9 @@ interface IPreparedModel extends @1.0::IPreparedModel {
	*		*
	* If the prepared model was prepared from a model wherein all tensor		* If the prepared model was prepared from a model wherein all tensor
	* operands have fully specified dimensions, and the inputs to the function		* operands have fully specified dimensions, and the inputs to the function
	* are valid, then the execution should complete successfully		* are valid, and at execution time every operation's input operands have
	* (ErrorStatus::NONE). There must be no failure unless the device itself is		* legal values, then the execution should complete successfully
			* (ErrorStatus::NONE): There must be no failure unless the device itself is
	* in a bad state.		* in a bad state.
	*		*
	* Any number of calls to the execute, execute_1_2, and executeSynchronously		* Any number of calls to the execute, execute_1_2, and executeSynchronously
	@@ -145,6 +149,13 @@ interface IPreparedModel extends @1.0::IPreparedModel {
	* Configure a Burst object used to execute multiple inferences on a		* Configure a Burst object used to execute multiple inferences on a
	* prepared model in rapid succession.		* prepared model in rapid succession.
	*		*
			* If the prepared model was prepared from a model wherein all tensor
			* operands have fully specified dimensions, and a valid serialized Request
			* is sent to the Burst for execution, 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.
			*
	* @param callback A callback object used to retrieve memory resources		* @param callback A callback object used to retrieve memory resources
	* corresponding to a unique identifiers ("slots").		* corresponding to a unique identifiers ("slots").
	* @param requestChannel Used by the client to send a serialized Request to		* @param requestChannel Used by the client to send a serialized Request to