diff options
author | Mike Kelly <mike.kelly@arm.com> | 2020-09-30 20:22:56 +0100 |
---|---|---|
committer | mike.kelly <mike.kelly@arm.com> | 2020-09-30 19:41:56 +0000 |
commit | 7ed56dd5808d483ab8e294f36e3ecf8e8ddd84f1 (patch) | |
tree | b53d5499204280f539e17e7f66d0d4e7790863c2 /DriverOptions.hpp | |
parent | 9b088d9c275ed11ca39f8b035e02a68f681c5d45 (diff) | |
download | android-nn-driver-7ed56dd5808d483ab8e294f36e3ecf8e8ddd84f1.tar.gz |
MLCE-233 Added ability to enable fast_math through the NNAPI driver
* Added -a command line option to enable fast_math on Neon/CL when launching the NNAPI driver
* The invocation will look something like:
/vendor/bin/hw/android.hardware.neuralnetworks@1.3-service-armnn -v -c GpuAcc -n arm-armnn -a
* Enabling fast_math may cause an increase in VTS or CTS test failures due to a change in precision
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ifd8931f95efd65d3ae3aca9d9d61bd381e4e24a5
Diffstat (limited to 'DriverOptions.hpp')
-rw-r--r-- | DriverOptions.hpp | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/DriverOptions.hpp b/DriverOptions.hpp index b05647c5..ba0919c1 100644 --- a/DriverOptions.hpp +++ b/DriverOptions.hpp @@ -31,6 +31,7 @@ public: armnn::IGpuAccTunedParameters::Mode GetClTunedParametersMode() const { return m_ClTunedParametersMode; } armnn::IGpuAccTunedParameters::TuningLevel GetClTuningLevel() const { return m_ClTuningLevel; } bool IsGpuProfilingEnabled() const { return m_EnableGpuProfiling; } + bool IsFastMathEnabled() const { return m_FastMathEnabled; } bool GetFp16Enabled() const { return m_fp16Enabled; } void SetBackends(const std::vector<armnn::BackendId>& backends) { m_Backends = backends; } @@ -45,6 +46,7 @@ private: armnn::IGpuAccTunedParameters::TuningLevel m_ClTuningLevel; bool m_EnableGpuProfiling; bool m_fp16Enabled; + bool m_FastMathEnabled; }; } // namespace armnn_driver |