FastMessageQueue is a Treble-compliant data structure that enables fast
communication between two processes. The FMQ object itself is an atomic
circular buffer that is optionally synchronized with a futex. However,
FMQ has no notion of ownership or lifetime across processes, so it must
be paired with higher-level constructs to manage the lifetime and
ownership.
The NNAPI is introducing the notion of an "Execution Burst" object (or
more simply a "Burst" object), which is similar to an
ANeuralNetworksExecution, but is intended to be reused across multiple
executions and has lower IPC overheads. It achieves this low IPC
overhead by replacing HIDL HwBinder calls with FMQ messages.
Specifically, it replaces IPreparedModel::executeSynchronously's call
from the client into the service with fmq_sync<FmqRequestDatum> (an FMQ
channel used to pass a serialized Request object) and it replaces
the return from the service into the client with
fmq_sync<FmqResultDatum> (an FMQ channel used to return serialized
result status and OutputShapes information).
Each channel is a unidirectional flow of information with exactly one
producer and exactly one consumer. The channels are created by the NN
runtime and passed to the service via
IPreparedModel::configureExecutionBurst.
This CL tests the Burst in both the execution path and validation path
in the Vendor Test Suite (VTS) in neuralnetworks/1.*/vts/functional/.
The VTS binary--VtsHalNeuralnetworksV1_2TargetTest--can be built and run
as any previous version could.
Bug: 119570067
Test: mma
Test: VtsHalNeuralnetworksV1_2TargetTest
Change-Id: I3a36484eff9565c2d028c07c099804a0289f294a
Merged-In: I3a36484eff9565c2d028c07c099804a0289f294a
(cherry picked from commit 814d8372f3)
Enable VTS unit test for dynamic output shape deduction.
Only test dynamic output shape for V1_2::IDevice with V1_2::Model.
Bug: 73506513
Test: VtsHalNeuralnetworksV1_xTargetTest with 1.2 sample driver
Change-Id: I4134e1ec54a15554eb8533134897279651b57da3
Merged-In: I4134e1ec54a15554eb8533134897279651b57da3
(cherry picked from commit a316581b21)
FastMessageQueue is a Treble-compliant data structure that enables fast
communication between two processes. The FMQ object itself is an atomic
circular buffer that is optionally synchronized with a futex. However,
FMQ has no notion of ownership or lifetime across processes, so it must
be paired with higher-level constructs to manage the lifetime and
ownership.
The NNAPI is introducing the notion of an "Execution Burst" object (or
more simply a "Burst" object), which is similar to an
ANeuralNetworksExecution, but is intended to be reused across multiple
executions and has lower IPC overheads. It achieves this low IPC
overhead by replacing HIDL HwBinder calls with FMQ messages.
Specifically, it replaces IPreparedModel::executeSynchronously's call
from the client into the service with fmq_sync<FmqRequestDatum> (an FMQ
channel used to pass a serialized Request object) and it replaces
the return from the service into the client with
fmq_sync<FmqResultDatum> (an FMQ channel used to return serialized
result status and OutputShapes information).
Each channel is a unidirectional flow of information with exactly one
producer and exactly one consumer. The channels are created by the NN
runtime and passed to the service via
IPreparedModel::configureExecutionBurst.
This CL defines the FmqRequestDatum and FmqResultDatum types in
types.hal. IBurstContext.hal defines IBurstContext, a HIDL object used
by the service to manage the resources of a Burst. IBurstCallback.hal
defines IBurstCallback, a HIDL callback object that can be used to
retrieve the handle to a resource the service has either not yet seen or
has evicted from its cache. Finally, IPreparedModel.hal is extended with
IPreparedModel::configureExecutionBurst to create the burst object.
Bug: 119570067
Test: mma
Change-Id: I333da70201531b1396efc714d096c277e8e1d47b
Merged-In: I333da70201531b1396efc714d096c277e8e1d47b
(cherry picked from commit 7e91e24fe1)
Added ExtraParams union for extra Operand parameters.
It's a more sensible approach than adding more fields
to the Operand struct.
Bug: 119249581
Test: NeuralNetworksTest_static
Test: VtsHalNeuralnetworksV1_0TargetTest
Test: VtsHalNeuralnetworksV1_1TargetTest
Test: VtsHalNeuralnetworksV1_2TargetTest
Change-Id: I59731134cf0ea34cf9e10342686d331da9e9c3b3
Merged-In: I59731134cf0ea34cf9e10342686d331da9e9c3b3
(cherry picked from commit faa59b8a2c)
Bug: 119274127
Test: all of the following, with the appropriate android.hardware.neuralnetworks@1.${X}::IDevice/sample-all
VtsHalNeuralnetworksV1_0TargetTest
VtsHalNeuralnetworksV1_0TargetTest
VtsHalNeuralnetworksV1_1CompatV1_0TargetTest
VtsHalNeuralnetworksV1_1CompatV1_0TargetTest
VtsHalNeuralnetworksV1_1TargetTest
VtsHalNeuralnetworksV1_1TargetTest
VtsHalNeuralnetworksV1_2CompatV1_0TargetTest
VtsHalNeuralnetworksV1_2CompatV1_0TargetTest
VtsHalNeuralnetworksV1_2CompatV1_1TargetTest
VtsHalNeuralnetworksV1_2CompatV1_1TargetTest
VtsHalNeuralnetworksV1_2TargetTest
VtsHalNeuralnetworksV1_2TargetTest
Change-Id: Iedfa485b4008d9cec3b81ff4c0ce3ebc0b83c823
(cherry picked from commit 49e41678f5)
Moves comments for type range values into their enums to make it harder
to forget to update them.
Adds missing float16 types for ARGMAX/ARGMIN/CAST.
Test: VtsHalNeuralnetworksV1_2TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Test: [ PASSED ] 2519 tests.
Change-Id: Ic7c3df8c8fbff45fe497f304b6b2c7a09e7dc5a6
Merged-In: Ic7c3df8c8fbff45fe497f304b6b2c7a09e7dc5a6
(cherry picked from commit bbdab2feee)
Create 1.2 version IPreparedModel, IPreparedModelCallback, and
IExecutionCallback.
Currently the new interfaces are created the same as 1.0 version,
but will have more methods introduced in later CLs.
Bug: 73506513
Test: VtsHalNeuralnetworksV1_xTargetTest with 1.2 sample driver
Change-Id: Icf4d04c22f88e825d87562f1489377fdf6bf585d
Merged-In: Icf4d04c22f88e825d87562f1489377fdf6bf585d
(cherry picked from commit b5cb8f7632)
* changes:
Replace TENSOR_QUANT16_ASYMM with TENSOR_QUANT16_SYMM
Fix VTS ValidationTest for 1.2 ops.
Adds float16 support to generated tests.
Autogenerates VTS ValidationTest tests.
Fix VTS ValidationTest for 1.2 ops.
Separates VTS tests by HAL version.
This removes the use of a separately updated list of models
that has fallen out of sync.
Bug: 119293899
Test: VtsHalNeuralnetworksV1_2TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Test: VtsHalNeuralnetworksV1_2CompatV1_1TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Test: VtsHalNeuralnetworksV1_2CompatV1_0TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Test: VtsHalNeuralnetworksV1_1TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.1::IDevice/sample-all
Test: VtsHalNeuralnetworksV1_1CompatV1_0TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.1::IDevice/sample-all
Test: VtsHalNeuralnetworksV1_0TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.0::IDevice/sample-all
Change-Id: I2d8804d78331b8fceab4c622c871802aa0f0a4b4
Merged-In: I2d8804d78331b8fceab4c622c871802aa0f0a4b4
(cherry picked from commit b5fe58b95a)
This abstracts the boundary values for OperandType and
OperationType to avoid the need to update them in the
model validation functions.
Test: VtsHalNeuralnetworksV1_2TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Test: VtsHalNeuralnetworksV1_2CompatV1_1TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Test: VtsHalNeuralnetworksV1_2CompatV1_0TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Change-Id: I39155148d67215e32b4eb1991b885f65d5eeaca8
Merged-In: I39155148d67215e32b4eb1991b885f65d5eeaca8
(cherry-pick from c785d46eb6)
This makes it easier to find all the places that need to be changed
after adding a new type to MixedTyped.
Test: VtsHalNeuralnetworksV1_2TargetTest
Change-Id: I92867de6574ec6dc1a17e30d889c79501ea93063
Merged-In: I92867de6574ec6dc1a17e30d889c79501ea93063
(cherry picked from commit 9b490f4833)
Divide BBOX_TRANSFORM op into 2 ops
- AXIS_ALIGNED_BBOX_TRANSFORM
- ROTATED_BBOX_TRANSFORM
Rotated bounding boxes use different tensor format than axis-aligned
bounding boxes, and it would be less confusing if they were represented
by a separate operator code.
Bug: 113562630
Test: NeuralNetworksTest_static
Test: VtsHalNeuralnetworksV1_xTargetTest with sample driver
Change-Id: Ie08f2e0d0da77f6750766a394969653478d054d5
Merged-In: Ie08f2e0d0da77f6750766a394969653478d054d5
(cherry picked from commit d2bae1c268)
