diff options
| author | Xusong Wang <xusongw@google.com> | 2022-01-21 10:15:19 -0800 |
|---|---|---|
| committer | Xusong Wang <xusongw@google.com> | 2022-02-07 14:02:41 -0800 |
| commit | 8805b2d67cdbd0cea31d5aba11069f7eaec59052 (patch) | |
| tree | bc80961e06fdddd0758a8a5d6699ff6bd7b73453 /neuralnetworks/aidl/vts/functional/ValidateModel.cpp | |
| parent | e4061de77e99a1979e9e53bd81ac7f79e2e4f664 (diff) | |
Address ANAPIC review comments -- hal.
- Document that IPreparedModel::execute*WithConfig are for single-time
usages, and IPreparedModel::createReusableExecution is for reusable
usages.
- Make PrepareModelConfig::cacheToken a fixed sized array.
Fixes: 215566186
Test: VtsHalNeuralnetworksTargetTest
Test: NNT_static
Change-Id: I9c5a49c46a3eac2828b9eb666f3d742038493121
Diffstat (limited to 'neuralnetworks/aidl/vts/functional/ValidateModel.cpp')
| -rw-r--r-- | neuralnetworks/aidl/vts/functional/ValidateModel.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/neuralnetworks/aidl/vts/functional/ValidateModel.cpp b/neuralnetworks/aidl/vts/functional/ValidateModel.cpp index 931ba258b3..060434ed08 100644 --- a/neuralnetworks/aidl/vts/functional/ValidateModel.cpp +++ b/neuralnetworks/aidl/vts/functional/ValidateModel.cpp @@ -85,7 +85,7 @@ static void validatePrepareModelWithConfig(const std::shared_ptr<IDevice>& devic std::shared_ptr<PreparedModelCallback> preparedModelCallback = ndk::SharedRefBase::make<PreparedModelCallback>(); const auto prepareLaunchStatus = device->prepareModelWithConfig( - model, {preference, priority, kNoDeadline, {}, {}, kEmptyCacheToken, {}, {}}, + model, {preference, priority, kNoDeadline, {}, {}, kEmptyCacheTokenArray, {}, {}}, preparedModelCallback); ASSERT_FALSE(prepareLaunchStatus.isOk()); ASSERT_EQ(prepareLaunchStatus.getExceptionCode(), EX_SERVICE_SPECIFIC); |