diff options
| author | Anthony Barbier <anthony.barbier@arm.com> | 2018-07-20 17:49:35 +0100 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:54:54 +0000 |
| commit | eaefd002a5d6509dd5f12e98b538c99b33c2c1ee (patch) | |
| tree | 18951e67cf2c0c0b91e88d9174d0c350890456a1 /src/core/NEON/kernels/NEFillBorderKernel.cpp | |
| parent | c8e84b5a3872eda6748d77dbaf8548ad99f4c0cd (diff) | |
| download | ComputeLibrary-eaefd002a5d6509dd5f12e98b538c99b33c2c1ee.tar.gz | |
COMPMID-1419: Make NEGEMMAssemblyDispatch dynamically typed instead of templated
This makes it easier to integrate in GEMMLowpMatrixMultiplyCore
Change-Id: Ibf80803f016a2e6a24d943ffafb50b48f04ec545
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/140868
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/NEFillBorderKernel.cpp')
| -rw-r--r-- | src/core/NEON/kernels/NEFillBorderKernel.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/src/core/NEON/kernels/NEFillBorderKernel.cpp b/src/core/NEON/kernels/NEFillBorderKernel.cpp index 3d08cafa93..aef4d4865a 100644 --- a/src/core/NEON/kernels/NEFillBorderKernel.cpp +++ b/src/core/NEON/kernels/NEFillBorderKernel.cpp @@ -105,6 +105,7 @@ NEFillBorderKernel::NEFillBorderKernel() void NEFillBorderKernel::configure(ITensor *tensor, BorderSize border_size, BorderMode border_mode, const PixelValue &constant_border_value) { + //Note: ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED(input) is not needed here as this kernel doesn't use NEON FP16 instructions. ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(tensor, 1, DataType::U8, DataType::QASYMM8, DataType::U16, DataType::S16, DataType::U32, DataType::S32, |