diff options
| author | Matthew Sloyan <matthew.sloyan@arm.com> | 2021-02-10 16:50:53 +0000 |
|---|---|---|
| committer | Matthew Sloyan <matthew.sloyan@arm.com> | 2021-02-12 17:56:58 +0000 |
| commit | 0a7dc6bba5d0810fe2ed6f84b0376a8b0674c0b3 (patch) | |
| tree | 6931067f0e0ff25be7d6a01d379f4b1497dff424 /src/backends/neon/NeonBackendModelContext.hpp | |
| parent | b454c5c65efb238c130b042ace390b2bc7f0bf75 (diff) | |
| download | armnn-0a7dc6bba5d0810fe2ed6f84b0376a8b0674c0b3.tar.gz | |
IVGCVSW-5685 Add CpuAcc specific configuration option numberOfThreads
* Added ability to set number of threads used in CpuAcc backend
* Enabled number-of-threads option in ExecuteNetwork
* Added TfLiteDelegate ModelOptions test
* Added unsigned int type to BackendOptions.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ia576d4f45cbe5df3654bc730bb5ebd5181d82b5a
Diffstat (limited to 'src/backends/neon/NeonBackendModelContext.hpp')
| -rw-r--r-- | src/backends/neon/NeonBackendModelContext.hpp | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/src/backends/neon/NeonBackendModelContext.hpp b/src/backends/neon/NeonBackendModelContext.hpp index 430ae45a6f..e736efc1d8 100644 --- a/src/backends/neon/NeonBackendModelContext.hpp +++ b/src/backends/neon/NeonBackendModelContext.hpp @@ -14,6 +14,8 @@ namespace armnn /// - "FastMathEnabled"\n /// Using the fast_math flag can lead to performance improvements in fp32 and fp16 layers but may result in\n /// results with reduced or different precision. The fast_math flag will not have any effect on int8 performance. +/// - "NumberOfThreads"\n +/// Specify the number of threads used by the CpuAcc backend. class NeonBackendModelContext : public IBackendModelContext { public: @@ -21,8 +23,11 @@ public: bool IsFastMathEnabled() const; + unsigned int GetNumberOfThreads() const; + private: bool m_IsFastMathEnabled; + unsigned int m_NumberOfThreads; }; } // namespace armnn
\ No newline at end of file |