diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-03-19 10:49:03 +0000 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-03-19 11:53:59 +0000 |
| commit | 02acf014b2840a3b644bfb783b8396e79cafd3a3 (patch) | |
| tree | bc610105f2dd98ecf0522848c0e115b1ed08fe6a /src/runtime/NEON | |
| parent | 146138378c1587b7297d245b7177641315f6180b (diff) | |
| download | ComputeLibrary-02acf014b2840a3b644bfb783b8396e79cafd3a3.tar.gz | |
COMPMID-2065: Fix validation issue in NEGEMMLowpMMCore
Sets correctly the quantization info in the auxilary tensors.
Change-Id: I35355d0aa2ab9716df3a91cbbf4609365fb109e4
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/872
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/NEON')
| -rw-r--r-- | src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp b/src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp index 85e49fd265..0247a39421 100644 --- a/src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp +++ b/src/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.cpp @@ -104,9 +104,9 @@ void NEGEMMLowpMatrixMultiplyCore::configure(const ITensor *a, const ITensor *b, matrix_b = &_tmp_b; // The interleaved output matrix will have the following shape: [ a_height * 4, ceil(a_width / 4.0f) ] - TensorInfo a_info(compute_interleaved_shape(*a->info()), 1, a->info()->data_type()); + TensorInfo a_info(compute_interleaved_shape(*a->info()), 1, a->info()->data_type(), a->info()->quantization_info()); // The transpose1xW output matrix will have the following shape: [ b_height * 16, ceil(b_width / 16.0f) ] - TensorInfo b_info(compute_transpose1xW_shape(*b->info()), 1, b->info()->data_type()); + TensorInfo b_info(compute_transpose1xW_shape(*b->info()), 1, b->info()->data_type(), b->info()->quantization_info()); _tmp_a.allocator()->init(a_info); _tmp_b.allocator()->init(b_info); _memory_group.manage(&_tmp_a); |