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
When incremental results are disabled for network scans,
update the API documentation to allow implementations to
ignore range checking for the incremental scan interval.
Bug: 112486807
Test: compilation - docstring-only change
Merged-In: I901335550b4b8c2cf75f91b39fd031f03ffae982
Change-Id: I901335550b4b8c2cf75f91b39fd031f03ffae982
(cherry picked from commit 944efca78d)
The documentation said that cell-to-input weights are required to be
present when input-to-input weights, recurrent-to-input weights and
input gate bias are present. This was incorrect since this weights can
be omitted if peephole connections are not used even if all the other
tensors are present.
Another bug that is fixed in this change is that for output #0 the docs
said "of shape [batch_size, num_units * 4] with CIFG, or [batch_size,
num_units * 3] without CIFG" when in fact it is the opposite, i.e. "of
shape [batch_size, num_units * 3] with CIFG, or [batch_size, num_units *
4] without CIFG."
Existing CTS/VTS tests expect behaviour described in the fixed documentation.
Existing CPU implementation is also compliant with the fixed documentation.
Fix: 111842951
Test: mma
Change-Id: Id011783e33672ae65dc6fe3784cb26feb832acf9
Merged-In: Id011783e33672ae65dc6fe3784cb26feb832acf9
(cherry picked from commit e0537f09fb)
We had no tests for quantized PAD in NNAPI 1.1 and think that vendors might have implemented different behaviors.
Bug: 122243484
Test: N/A
Change-Id: Ibfc0801ab746fc271dc5f8efc764b818c6d49df4
Merged-In: Ibfc0801ab746fc271dc5f8efc764b818c6d49df4
(cherry picked from commit b01ce9644e)
RESIZE_NEAREST_NEIGHBOR
- The CPU implementation always had the order of {width, height}.
- In P, the documentation was incorrectly changed to {height, width}.
Bug: 131623949
Bug: 130035110
Test: mm
Change-Id: I6c79459fa73347fb51fc34a76ad78d5ac207f210
Merged-In: I6c79459fa73347fb51fc34a76ad78d5ac207f210
(cherry picked from commit 286339b4c8)
This is causing C++ compiles of this interface to fail now that these
comments get copied into the output.
Bug: 130911129
Test: compilation now succeeds
Change-Id: Iaa3877620b032b7144e3bab114fbcd1e1483bc8e
Update the docs for ops:
- LOG_SOFTMAX
- LOCAL_RESPONSE_NORMALIZATION
The docs mentioned possibility to use float16 as an input type but
didn't specify that other inputs must be float16 as well in that case.
Fix: 123500722
Test: mma
Change-Id: I9028c4a109c80f0b8571fab45555818e9e4bc783
Merged-In: I9028c4a109c80f0b8571fab45555818e9e4bc783
(cherry picked from commit 6d13ba258b)
In case of CIFG LSTM, input layer norm weights are not used in the
computation.
Bug: 129126572
Test: mma
Change-Id: I57bc578606132a2c44c71ab63dd7645dcc001302
Merged-In: I57bc578606132a2c44c71ab63dd7645dcc001302
(cherry picked from commit 0480af9aa8)
Both framework BatteryService and all implementations (that uses
BatteryMonitor) uses millivolts for batteryVoltage.
maxChargingVoltage is microvolts and that is correct.
Fixes: 115881119
Test: treehugger
Change-Id: I64044489fe6d56e0d211085d9536fe5cfd95efc4
- 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)
Also updates documentation for this op and UnidirectionalSequenceLSTM
op.
Bug: 123644584
Test: in ag/6758764
Change-Id: I72d029fef6d890eb1771c21814b028b09af280c7
Merged-In: I72d029fef6d890eb1771c21814b028b09af280c7
(cherry picked from commit f404a1e894)
Performance information in Capabilities is used by the runtime when
it selects the appropriate processor to distribute work to. Prior to
this CL, Capabilities can only distinguish between float and non-float
data types -- so, for example, float16 and float32 performance is
considered to be the same, and performance for all non-float data types is
considered to be the same.
Bug: 124041010
Test: NeuralNetworksTest_static
Test: VtsHalNeuralnetworksV1_2TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Change-Id: I83fb5920c1c75afbd7750d793a0b8f3e72a0552c
Merged-In: I83fb5920c1c75afbd7750d793a0b8f3e72a0552c
(cherry picked from commit 632b4bd9b0)
No good place in generated docs.
Bug: 124382459
Test: ./update-makefiles.sh
Change-Id: I7802d12c34b33be192c83fc46ffed5a6a7385a0a
Merged-In: I7802d12c34b33be192c83fc46ffed5a6a7385a0a
The spec of setLayerDataspace never specifies the types of layer it should be
call on, however, the spec has the implication that this method will only work
for layers with buffer, which is mis-leading. This patch changes the wording of
setLayerDataspace spec, removes the implication. Note that this change won't
break backward compatability.
BUG: 126713799
Test: N/A
Change-Id: I97f22469897cb687dcb64a3d419bcb48a3668e5a
subsysName, railName, powerEntityName, and powerEntityStateName are all
opaque to the Android framework. Emphasizing the opaque nature of these
members in the HAL definition will help developers more quickly
understand the intent of the interface.
Bug: 125380339
Test: make
Change-Id: I42ed1f3cc928726ae146b6be849947b631ae48e6
Modify the document for 'hasKnownUserIntentEmergency'.
In the scenarios that the 'address' in the 'dialInfo' field has other
functions besides the emergency number function, if the
'hasKnownUserIntentEmergency' field is true, the user's intent for this
dial request is emergency call, and the modem must treat this as an
actual emergency dial; if the 'hasKnownUserIntentEmergency' field is
false, Android does not know user's intent for this call.
Test: compile
Bug: 121345950
Change-Id: I3457e7519be564ac5043e06380e9450a1b12425f
(cherry picked from commit 7208840ec0148ad5a01bdf419170282cd1b32437)
When fields are inapplicable, they should not
be set to a clearly out-of-range value to signal
to the framework that those fields are not used.
In some cases, there is an in-range invalid value
that has been defined by the standards. The docs
are inconsistent in calling out INT_MAX as the
value to be used when something is inapplicable
vs the case when a measurement is simply not
reported. In all cases, INT_MAX can be used to
denote an invalid value, and in cases where the
field/structure is inapplicable, it is the correct
value. This CL updates all the docstrings for
SignalStrength-related fields to clarify that
INT_MAX is the correct "invalid" value for cases
when fields are inapplicable.
Bug: 123088652
Test: compilation (docstring-only change); CTS
naturally enforces this change on devices with
newer HALs; backwards compatibility is preserved
for existing HAL versions.
Change-Id: I5cfa917f504d15691ab3f2c298189bdd47794a42
If there are more than one metadata entities being passed
via FMQ, specify the framework read order.
Test: Build
Bug: 119575429
Change-Id: Ia34ac69ce670b1ebeda12d92af490c347f33c15b
Merged-In: Ia34ac69ce670b1ebeda12d92af490c347f33c15b
