diff options
| author | Ryan OShea <ryan.oshea3@arm.com> | 2022-11-07 16:20:48 +0000 |
|---|---|---|
| committer | ryan.oshea3 <ryan.oshea3@arm.com> | 2022-11-16 15:22:50 +0000 |
| commit | 31441595009182c985dacbedc70c41ee6664d070 (patch) | |
| tree | 248a85295aeff4022c9b395fc97748b0a0aa6b35 /src/backends/neon/NeonLayerSupport.hpp | |
| parent | bd18eab07a8f30492de1e462b1815189014cb8d5 (diff) | |
| download | armnn-31441595009182c985dacbedc70c41ee6664d070.tar.gz | |
IVGCVSW-7214 Disable BF16-Turbo-Mode and remove conversion layers
- Remove Bf16ToFp32 Conversion Layer
- Remove Fp32ToBf16 Conversion Layer
- Remove B16 Conversion tests
* Throw exception if m_ReduceFp32ToBf16 optimzer option is set to true
* Provide comments to enable fast math in order to use bf16
* Update docs to inform users to enable fast math for bf16
Execute Network Changes
* Require bf16_turbo_mode to also have fast_math_enabled set to true
- Remove setting m_ReduceFp32ToBf16 optimizer option
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Ibaa6da9d29c96a1ce32ff5196b0847fde9f04a1c
Diffstat (limited to 'src/backends/neon/NeonLayerSupport.hpp')
| -rw-r--r-- | src/backends/neon/NeonLayerSupport.hpp | 8 |
1 files changed, 0 insertions, 8 deletions
diff --git a/src/backends/neon/NeonLayerSupport.hpp b/src/backends/neon/NeonLayerSupport.hpp index e916162f93..374a9049c8 100644 --- a/src/backends/neon/NeonLayerSupport.hpp +++ b/src/backends/neon/NeonLayerSupport.hpp @@ -84,18 +84,10 @@ public: bool IsConstantSupported(const TensorInfo& output, Optional<std::string&> reasonIfUnsupported = EmptyOptional()) const override; - bool IsConvertBf16ToFp32Supported(const TensorInfo& input, - const TensorInfo& output, - Optional<std::string&> reasonIfUnsupported = EmptyOptional()) const override; - bool IsConvertFp16ToFp32Supported(const TensorInfo& input, const TensorInfo& output, Optional<std::string&> reasonIfUnsupported = EmptyOptional()) const override; - bool IsConvertFp32ToBf16Supported(const TensorInfo& input, - const TensorInfo& output, - Optional<std::string&> reasonIfUnsupported = EmptyOptional()) const override; - bool IsConvertFp32ToFp16Supported(const TensorInfo& input, const TensorInfo& output, Optional<std::string&> reasonIfUnsupported = EmptyOptional()) const override; |