| Age | Commit message (Collapse) | Author |
|---|
|
The following AIDL types are added:
- TokenValuePair
- PrepareModelConfig
- ExecutionConfig
The following AIDL methods are added:
- IDevice::prepareModelWithConfig
- IPreparedModel::executeSynchronouslyWithConfig
- IPreparedModel::executeFencedWithConfig
- IBurst::executeSynchronouslyWithConfig
The compilation and execution hints are being stored as a list of
token-value pairs as part of the PrepareModelConfig / ExecutionConfig.
And the PrepareModelConfig / ExecutionConfig parcelables are created in
order to make future extensions to the execution related interfaces
easier.
It is the drivers responsibility to verify the hints, and it is allowed
for the driver to ignore them.
Bug: 203248587
Test: neuralnetworks_utils_hal_aidl_test
Change-Id: I98240fd75089fc85cdfcaa0be28aab8a6f0dfca5
|
|
This CL modifies the canonical/AIDL adapter to use IExecution object
if available.
Bug: 202405342
Bug: 202431255
Test: NNT_static
Test: CtsNNAPITestCases
Test: VtsHalNeuralnetworksTargetTest
Change-Id: I6aac3c57f97ac87a5ba3f78cfd843fcc403decff
|
|
This CL modifies the canonical interface for reusable executions:
- Add new interface: IExecution with compute and computeFenced methods
- Add new method IPreparedModel::createExecution
In NNAPI runtime, the new interface IExecution is used to
memoize request-specific execution resources (e.g. converted HAL
request). The expected usage is that, IPreparedModel::createExecution
will be invoked in the first computation of a reusable NDK ANNExecution
object, and IExecution::compute* will be invoked repeatedly.
The IPreparedModel::execute* methods are preserved to avoid redundant
object creation and memoization overhead for a single-time
(non-reusable) execution.
For a vendor implementing the canonical interfaces, only the
IPreparedModel::execute* methods will be called because there is
currently no reusable execution at HAL interface. A DefaultExecution
implementation is provided to reduce the work needed on the vendor side.
Bug: 184073769
Test: NNT_static
Test: neuralnetworks_utils_hal_1_0_test
Test: neuralnetworks_utils_hal_1_1_test
Test: neuralnetworks_utils_hal_1_2_test
Test: neuralnetworks_utils_hal_1_3_test
Test: neuralnetworks_utils_hal_common_test
Test: neuralnetworks_utils_hal_aidl_test
Change-Id: I91790bb5ccf5ae648687fe603f88ffda2c9fd2b2
|
|
The change adds "Ns" suffix to timeOnDevice, timeInDriver,
loopTimeoutDuration, deadline and duration.
Fix: 183118329
Test: mm
Change-Id: Id1f9ee4b8e41873c97690bb19a5e84572dd9ccf1
|
|
Bug: 180492058
Bug: 177267324
Test: mma
Test: NeuralNetworksTest_static
Change-Id: I2947faeb3820faa963e4df1eaf7aefec57b66c79
Merged-In: I2947faeb3820faa963e4df1eaf7aefec57b66c79
(cherry picked from commit 504f44926c0e0ce0a5b5a591dbb848fdb732d8b2)
|
|
Adds deadline and loopTimeoutDuration to nn::IBurst::execute.
This CL additionally adds a test case for
IPreparedModel::configureExecutionBurst and adds the suffix "_H" to
the header guards that were missing "_H".
Bug: 180492058
Bug: 177267324
Test: mma
Test: NeuralNetworksTest_static
Change-Id: Ic9ba2fb9b4dee4e40d99ae91bb9555a58d0508d2
Merged-In: Ic9ba2fb9b4dee4e40d99ae91bb9555a58d0508d2
(cherry picked from commit bbbdb0d5f118efa8159c3cc98304208fd7631609)
|
|
Also:
* Add missing AIDL<->CT conversions
* Add AIDL-specific info to neuralnetworks/utils/README.md
* Add mock classes and tests AIDL adapters
Bug: 179015258
Test: neuralnetworks_utils_hal_test
Change-Id: Ifa98fadd46dca5dbf9b3ceb4da811aa8da45b6e4
Merged-In: Ifa98fadd46dca5dbf9b3ceb4da811aa8da45b6e4
(cherry picked from commit 3b93b0b56a4f5128eaa942d804dd490317c0abcb)
|
