diff options
author | Gian Marco <gianmarco.iodice@arm.com> | 2017-11-21 10:57:50 +0000 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:41:17 +0000 |
commit | 05288a2b871ef99f544771621c3bba409b2f70df (patch) | |
tree | 21e3d2a9927ef31f6d5bcdd5523c4c8e933047a6 /src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp | |
parent | c82799003fbfdc5bb9526ff944e41eaae23e3f03 (diff) | |
download | ComputeLibrary-05288a2b871ef99f544771621c3bba409b2f70df.tar.gz |
COMPMID-697 - Rework GEMMLowp interface on OpenCL
Reworked the interface of GemmLowp in order to make easy the integration
in Android NN
- Added support for different output stage
- Added validation for both matrix multiplication and output stage
- Added bounded relu support in the output stage
- Added in32_t bias support
- Added optimized path for vector by matrix case
This rework is required for:
- Convolution quantized
- Fully connected quantized
Change-Id: I512283d406099cf8c614dd89d0a97ed411143afc
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110625
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp')
-rw-r--r-- | src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp | 10 |
1 files changed, 8 insertions, 2 deletions
diff --git a/src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp b/src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp index 92c911c370..da5ac22fdc 100644 --- a/src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp +++ b/src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp @@ -133,7 +133,10 @@ void NEGEMMLowpMatrixMultiplyCore::configure(const ITensor *a, const ITensor *b, if(_a_offset != 0) { TensorShape shape_vector_sum_col = b->info()->tensor_shape(); - shape_vector_sum_col.remove_dimension(1); + if(b->info()->num_dimensions() > 1) + { + shape_vector_sum_col.remove_dimension(1); + } TensorInfo info_vector_sum_col(shape_vector_sum_col, 1, DataType::S32); _vector_sum_col.allocator()->init(info_vector_sum_col); _memory_group.manage(&_vector_sum_col); @@ -147,7 +150,10 @@ void NEGEMMLowpMatrixMultiplyCore::configure(const ITensor *a, const ITensor *b, { TensorShape shape_vector_sum_row = a->info()->tensor_shape(); shape_vector_sum_row.set(Window::DimX, a->info()->dimension(1)); - shape_vector_sum_row.remove_dimension(1); + if(a->info()->num_dimensions() > 1) + { + shape_vector_sum_row.remove_dimension(1); + } TensorInfo info_vector_sum_row(shape_vector_sum_row, 1, DataType::S32); _vector_sum_row.allocator()->init(info_vector_sum_row); _memory_group.manage(&_vector_sum_row); |