We don't have a framework for handcrafting tests resulting in execution
failure. To produce this test, I created
strided_slice_invalid_output_dims.mod.py and used our VTS test generator
to create the corresponding example.cpp and model.cpp files. I put those
under the new directory neuralnetworks/1.2/vts/functional/generated to
distinguish them from the streamlined generated tests.
Bug: 79856511
Bug: 132155416
Test: VtsHalNeuralnetworksV1_2TargetTest
Change-Id: Ib331778605c2e3828195e1e7d1651091873985a0
Prior to this CL, the VTS compilation caching tests are using float32
models. However, there exists several drivers that only support QUANT8
operations, and most of the tests are simply skipped.
This CL makes the CompilationCachingTest fixture parameterized that
every test will run twice, with the first pass running with float32
models and the second pass running with quant8 models.
Bug: 132112463
Test: 1.2 VTS with sample drivers
Test: 1.2 VTS with test drivers that can read and write cache entries
Change-Id: Iaf28065e46c2d90ab8b347b9848be1e6546cce86
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
FmqResultDatum::OperandInformation has padding that may not be
initialized by an NN HAL service instance. This CL adds a validation
check to ensure that services are not leaking uninitialized data through
this padding region.
Bug: 131356202
Test: mma
Test: atest VtsHalNeuralnetworksV1_2TargetTest
(for ValidationTest with sample-all)
Test: altered sample-driver to randomly set a padding byte to 1;
the new validation test successfully failed the test
Change-Id: I6661945392b3fc773493d8f2f306f29b39e09bab
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
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
This CL adds the following two types of validation tests on the NNAPI
Burst serialized format:
(1) it directly modifies the serialized data (invalidating it) to ensure
that vendor driver services properly validates the serialized
request
(2) it ensures that vendor driver services properly fail when the result
channel is not large enough to return the data
This CL additionally includes miscellaneous cleanups:
(1) having a generic "validateEverything" function
(2) moving the "prepareModel" function that's common across
validateRequest and validateBurst to a common area
Fixes: 129779280
Bug: 129157135
Test: mma
Test: VtsHalNeuralnetworksV1_2TargetTest (with sample-all)
Change-Id: Ib90fe7f662824de17db5a254a8c501855e45f6bd
Before this change, getSupportedOperations_1_2 was invoked in
saveModelToCache prior to prepareModel_1_2, which delayed the model
preparation and cache overwriting always ran faster in
SaveToCache_TOCTOU test.
This change increases the chance that the model is overwritten after it
is saved in SaveToCache_TOCTOU test by moving getSupportedOperations_1_2
out of saveToCache.
Bug: 123433989
Test: VtsHalNeuralnetworksV1_xTargetTest with 1.2 sample driver
Test: VtsHalNeuralnetworksV1_xTargetTest with a test driver that can
read and write cache entries
Test: TOCTOU tests with a sample driver that is deliberately broken
Change-Id: Ieba6a82252623ac429d5fcb6950b99db949f9886
We only expect the driver to not crash.
Bug: 123433989
Test: VtsHalNeuralnetworksV1_xTargetTest with 1.2 sample driver
Test: VtsHalNeuralnetworksV1_xTargetTest with a test driver that can
read and write cache entries
Change-Id: Ic9bd7ad6e42d77d505955cb9dda597a39e95cdb6
Two tests are added into VTS:
1. The TOCTOU test, for a fixed number of iterations.
We try to attack the driver by replacing the model cache with another
cache entry from a similar model while the driver is saving to or
preparing from cache, and see if the driver crashes or falsely prepares
an unexpected model (by checking the execution result). Either of the
following results are acceptable
* Fails -> the driver detects this corruption.
* Succeeds and produces correct execution result -> the corruption
happens before saving to cache or after preparing from cache.
Due to the racy nature, this test is probabilistic and we run it several
times.
2. Similar to the TOCTOU test but replace the content between
compile-to-cache and compile-from-cache (once only).
Additionally, remove tmp cache directory if test succeeds.
Bug: 123433989
Test: VtsHalNeuralnetworksV1_xTargetTest with 1.2 sample driver
Test: VtsHalNeuralnetworksV1_xTargetTest with a test driver that can
read and write cache entries
Test: Check /data/local/tmp and confirm that
* dirs are preserved on failure
* dirs are removed on success
Change-Id: Ie04fa905f465c3775979f0ca74359d185dcacea9
