Bug: http://b/74200014
This is no longer broken after switching to lld.
Test: mmma SANITIZE_TARGET=address
hardware/interfaces/neuralnetworks/1.0/vts/functional
Change-Id: I0920da7db83222d089c7a571e9478fb7ad9ad9d4
hidl-generated makefiles are now generated such that bpfmt(file) == file.
Bug: 67417008
Test: enable bpfmt hook
Change-Id: I1f69d292bc23a7cc293a66110cb02d597e1019ad
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)
This CL adapts the VTS code to the corresponding changes made in the NN
utility library.
Bug: 128319484
Test: mma
Test: atest VtsHalNeuralnetworksV1_0Target
Test: atest VtsHalNeuralnetworksV1_1Target
Test: atest VtsHalNeuralnetworksV1_2Target
Change-Id: I470e8228cde2b75620ad851e4fe408f8e8329e7c
Merged-In: I470e8228cde2b75620ad851e4fe408f8e8329e7c
(cherry picked from commit 102e0442d8)
This CL adapts the VTS code to the corresponding changes made in the NN
utility library.
Bug: 119570067
Test: mma
Test: atest VtsHalNeuralnetworksV1_0Target
Test: atest VtsHalNeuralnetworksV1_1Target
Test: atest VtsHalNeuralnetworksV1_2Target
Change-Id: I7cbc1d7025c0352aa1ed29d71dc84c2fcfc20a4f
Merged-In: I7cbc1d7025c0352aa1ed29d71dc84c2fcfc20a4f
(cherry picked from commit e68668f65b)
Test importing of an Elliptic Curve P-256 key, encoded using the RFC5915
specification (which requires the curve OID in key in addition to the
wrapper) and the same key encoded using SEC1 (which allows omitting the
OID if it's known from the wrapper).
Test: atest VtsHalKeymasterV4_0TargetTest ImportKeyTest
Bug: 124437839
Bug: 127799174
Bug: 129398850
Change-Id: I5f5df86e55a758ed739403d830baa5c7308813a3
Merged-In: I5f5df86e55a758ed739403d830baa5c7308813a3
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)
The filter tensor is not always operand 1 if there are multiple
operations in the model.
Test: 1.2 VTS tests with sample driver
Change-Id: I8925dfd18072ae5579657e8aa13128e7d9f58324
Merged-In: I8925dfd18072ae5579657e8aa13128e7d9f58324
(cherry picked from commit 8804423ca1)
operator< on hidl_vec<uint8_t> violates strict weak ordering in the case
that one oparand is shorter that the other and the shorter is a prefix
of the longer.
if x and y are incomparable, i.e., neither x < y nor y < x and
y and z are incomparable, i.e., neither y < z nor z < y, then
x and z must be incomparable.
As for the current implementation the first two statements are true but
the third is not given the following example input:
x:="aa", y:="a", z:="ab".
This patch fixes the issue by defining a < b if a is a prefix of b.
As this relation is used in a std::sort algorithm which demands strict
weak ordering this bug leads to undefined behavior.
Change-Id: I4961bb35e2fd4f5fcf561ec0c7c536f81830aab8
added Y16 (depth) support for the external provider.
refactored initOutputCharsKeys to support both depth and color metadata according to the connected camera.
the VTS changes will be pushed to pie-vts-dev
Test: tested on intel depth camera D415 manually in addition to the VTS tests.
Change-Id: I358686e7c4330bb180dec4a9cce3bc1cf5475260
Merged-In: I358686e7c4330bb180dec4a9cce3bc1cf5475260
Signed-off-by: Emil Jahshan <emil.jahshan@intel.com>
No good place in generated docs.
Bug: 124382459
Test: ./update-makefiles.sh
Change-Id: I7802d12c34b33be192c83fc46ffed5a6a7385a0a
Merged-In: I7802d12c34b33be192c83fc46ffed5a6a7385a0a
gtest in Android P tree does not have GTEST_SKIP. Implement
a naive version of it.
Bug: 118852225
Test: manually undefine GTEST_SKIP, test with and without --force
Change-Id: I8df1154d8a94a67ae28e8024de6022fcfe76384d
