diff options
| author | Matthew Bentham <matthew.bentham@arm.com> | 2019-04-09 13:10:46 +0100 |
|---|---|---|
| committer | Matteo Martincigh <matteo.martincigh@arm.com> | 2019-04-15 15:29:37 +0000 |
| commit | 3e68b97946bfee3c89ec2d4363a22550a10b2e55 (patch) | |
| tree | d7d9be27aff46a18ac9442092d908223f435dcd7 /tests/ExecuteNetwork | |
| parent | 200e38039cf2cef21ae9ba6f86fab6fd524e5077 (diff) | |
| download | armnn-3e68b97946bfee3c89ec2d4363a22550a10b2e55.tar.gz | |
IVGCVSW-2928 Fix issue with GPU profiling
Correctly enable GPU profiling when test profiling is enabled.
Remove extra copy of the profiling-enabled flag from InferenceModel::Params
and correctly pass around the copy that is in InferenceTestOptions.
!referencetests:180329
Change-Id: I0daa1bab2e7068fc479bf417a553183b1d922166
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
Diffstat (limited to 'tests/ExecuteNetwork')
| -rw-r--r-- | tests/ExecuteNetwork/ExecuteNetwork.cpp | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/tests/ExecuteNetwork/ExecuteNetwork.cpp b/tests/ExecuteNetwork/ExecuteNetwork.cpp index 9ac66d1cd3..1de22ed5d0 100644 --- a/tests/ExecuteNetwork/ExecuteNetwork.cpp +++ b/tests/ExecuteNetwork/ExecuteNetwork.cpp @@ -236,10 +236,9 @@ int MainImpl(const char* modelPath, params.m_OutputBindings.push_back(outputName); } - params.m_EnableProfiling = enableProfiling; params.m_SubgraphId = subgraphId; params.m_EnableFp16TurboMode = enableFp16TurboMode; - InferenceModel<TParser, TDataType> model(params, runtime); + InferenceModel<TParser, TDataType> model(params, enableProfiling, runtime); for(unsigned int i = 0; i < inputTensorDataFilePaths.size(); ++i) { |