diff options
| author | Gian Marco <gianmarco.iodice@arm.com> | 2017-11-08 12:24:09 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:35:24 +0000 |
| commit | e75a02b60736f37c34388c23c0ccee230f65da59 (patch) | |
| tree | f8e9423e40589e99bd8be6c1e740b17792e2058e /src/core/NEON/kernels/NEGEMMInterleave4x4Kernel.cpp | |
| parent | 6c0348f4cbf6e30a715780f50aebf6dd0a2a8fc3 (diff) | |
| download | ComputeLibrary-e75a02b60736f37c34388c23c0ccee230f65da59.tar.gz | |
COMPMID-675 - Reworked NEGEMMLowp interface/function
The new interface makes NEGEMMLowp able to work with ASYMM8 data types.
Implemented 2 new functions:
- NEGEMMLowpMatrixMultiplyCore
- NEGEMMLowpOutputStage
These functions should make the integration in android NN doable
For more information about GEMMLowp:
https://github.com/google/gemmlowp/blob/master/doc/low-precision.md
Change-Id: Ie2c775f45234f68ca53dba644b3a912b997fd890
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95504
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/NEGEMMInterleave4x4Kernel.cpp')
| -rw-r--r-- | src/core/NEON/kernels/NEGEMMInterleave4x4Kernel.cpp | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/src/core/NEON/kernels/NEGEMMInterleave4x4Kernel.cpp b/src/core/NEON/kernels/NEGEMMInterleave4x4Kernel.cpp index ae5d456141..a29b661a00 100644 --- a/src/core/NEON/kernels/NEGEMMInterleave4x4Kernel.cpp +++ b/src/core/NEON/kernels/NEGEMMInterleave4x4Kernel.cpp @@ -132,7 +132,8 @@ NEGEMMInterleave4x4Kernel::NEGEMMInterleave4x4Kernel() void NEGEMMInterleave4x4Kernel::configure(const ITensor *input, ITensor *output) { - ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(input, 1, DataType::QS8, DataType::QS16, DataType::U8, DataType::S8, DataType::U16, DataType::S16, DataType::U32, DataType::S32, DataType::F16, + ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(input, 1, DataType::QASYMM8, DataType::QS8, DataType::QS16, DataType::U8, DataType::S8, DataType::U16, DataType::S16, DataType::U32, DataType::S32, + DataType::F16, DataType::F32); ARM_COMPUTE_ERROR_ON_NULLPTR(output); |