Under certain circumstances, we guarantee that a prepared model can be
executed successfully. In describing those circumstances, we
neglected to specify that operation input operands must have legal
values for the guarantee to hold. For example, the guarantee doesn't
hold if an ADD operation has an activation input that is not one of
the defined values; or if a RESHAPE operation has a shape input in
which two or more components are -1.
This change modifies the guarantee to apply only when operation input
operands have legal values. It also documents this guarantee for
burst execution.
Note that if an operation has an input operand that can be proven to
have an illegal value at preparation time (e.g., a constant value that
is illegal), model preparation might (but is not required to) fail for
that reason.
Bug: 135933040
Test: $ cd neuralnetworks ; mma
Change-Id: I8b421550dd89e4bbbdae899e7cb5e9e88a46d2fb
Bug: 121347610 document that NNAPI Execution inputs/outputs and HAL Request inputs/outputs must not be modified
Test: cd hardware/interfaces/neuralnetworks/1.0/vts/functional ; mma
Test: cd hardware/interfaces/neuralnetworks/1.2/vts/functional ; mma
Change-Id: Iac71d6d5ad92a90afd1b6babb7cfa128d7484c64
- Instead of isCachingSupport returning a single boolean, switch to
getNumberOfCacheFilesNeeded returning the number of cache files. This
is to support use cases when driver needs more than one cache file for
each type, or when driver does not need data cache.
- Instead of a separate saveToCache, pass cache info along with
prepareModel_1_2 to save into cache as well as perform compilation.
This is to avoid a potential additional copy of cache files.
Bug: 123780248
Test: VtsHalNeuralnetworksV1_xTargetTest with 1.2 sample driver
Test: VtsHalNeuralnetworksV1_xTargetTest with a test driver that can
read and write cache entries
Change-Id: I921b7b8ccc3c66af19f6589f7213c6870d6f07bf
Merged-In: I921b7b8ccc3c66af19f6589f7213c6870d6f07bf
(cherry picked from commit b61ba1ed0b)
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)
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)
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)
