tequilaOS/platform_hardware_interfaces
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
9892 commits 1 branch 0 tags 121 MiB
Commit graph

8 commits

Author SHA1 Message Date
David Gross
7a76d8a7a8 Add validation tests for consistency of model inputs and outputs. 
Test: VtsHalNeuralnetworksV1_1TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.1::IDevice/sample-all --gtest_filter=Flavor/NeuralnetworksInputsOutputsTest.*
Test: VtsHalNeuralnetworksV1_1TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.1::IDevice/sample-float-fast --gtest_filter=Flavor/NeuralnetworksInputsOutputsTest.*
Test: VtsHalNeuralnetworksV1_1TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.1::IDevice/sample-quant --gtest_filter=Flavor/NeuralnetworksInputsOutputsTest.*

Bug: 67828197
Change-Id: I245227dce095b9cbbb9b527ad99aa71d11f77c4f
 2018-03-23 10:12:47 -07:00
Nathan Harold
c893754c0d Update Makefiles Missed In Previous Commits 
When calling update-makefiles.sh there are
some unrelated changes that were missed in
previous commits.

Bug: 8675309
Test: compilation
Change-Id: I5bf67fbcc809de36bde1869ada7b835566a5198b
 2018-03-19 16:37:46 -07:00
Pirama Arumuga Nainar
cca38c56f4 Disable arm32 asan for VtsHalNeuralnetworksV1_1TargetTest 
Bug: http://b/74200014

Building this module with asan triggers an internal error in gold.

Test: mma SANITIZE_TARGET=address in
hardware/interfaces/neuralnetworks/1.1/vts/functional

Change-Id: I3ce5352a6c86c8dca257d35af06989e57f871749
 2018-03-06 19:30:40 +00:00
Michael Butler
4d5bb1097a Relax NeuralNetwork's VTS positive and negative base tests 
There are some NN VTS tests that assume a service is able to generate a
model consisting only of a floating point add operation. However, some
drivers do not support floating point operations. This CL relaxes the
test requirements to allow a test to be skipped if the service does not
support floating point add.

Bug: 72764145
Test: mma
Test: VtsHalNeuralnetworksV1_0TargetTest
Change-Id: I6b0644432680fc2f8098b5187795dc2953df03f9
 2018-02-26 15:24:46 -08:00
David Gross
4b458caa4e Add Capabilities::relaxedFloat32toFloat16Performance for 1.1. 
Test: VtsHalNeuralnetworksV1_0TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.0::IDevice/sample-all
Test: VtsHalNeuralnetworksV1_0TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.0::IDevice/hvx
Test: VtsHalNeuralnetworksV1_1TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.1::IDevice/sample-all
Test: NeuralNetworksTest_static

Bug: 63911257

Change-Id: I040b68d84504180ba3039e4690d0cd43c2c2649f
 2018-02-26 19:01:19 +00:00
Michael Butler
7ffe78ba76 NNAPI narrow evaluation for P -- HAL 
We have determined that for Android P it is sufficient to have a
mechanism for a developer to specify on a per-model basis that it is
acceptable for FLOAT32 operations to be carried out as if they were
FLOAT16 operations. This CL extends the model to include information on
these precision requirements.

Bug: 63911257
Test: mm
Test: NeuralNetworksTest
Test: VtsHalNeuralnetworksV1_0TargetTest
Change-Id: I5331e69c05c20c588035897322a6c7dceca374a0
 2018-02-20 19:06:37 -08:00
Miao Wang
a2d04c828e Refactor NN API VTS tests and add v1.1 tests 
- Create VtsHalNeuralnetworksTest_utils module to be shared between
    v1.x tests.
  - Split the existing tests into two categories: basic, and generated.
  - Created v1.1 VTS tests ensuring no regression in existing ML models.

Bug: 63911257
Test: mm
Test: NNAPI VTS tests pass on v1.0 and v1.1 sample drivers

Change-Id: Ic77c90a3a5bbd96b0ce2acd03764dde4b3034cc9
 2018-02-09 18:07:37 -08:00
Michael Butler
5c6ee9ecef Create NeuralNetworks HAL v1.1 for new OperationTypes 
Test: mm
Change-Id: I08efaba79ec28a2f89e94a84ab88b0fa701b7d98
 2018-01-29 22:24:13 -08:00