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 /tests/datasets/LargeGEMMLowpDataset.h | |
| 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 'tests/datasets/LargeGEMMLowpDataset.h')
| -rw-r--r-- | tests/datasets/LargeGEMMLowpDataset.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/tests/datasets/LargeGEMMLowpDataset.h b/tests/datasets/LargeGEMMLowpDataset.h index cc1feb49a2..87f879e70a 100644 --- a/tests/datasets/LargeGEMMLowpDataset.h +++ b/tests/datasets/LargeGEMMLowpDataset.h @@ -42,7 +42,9 @@ class LargeGEMMLowpDataset final : public GEMMLowpDataset public: LargeGEMMLowpDataset() { + add_config(TensorShape(923U, 2U), TensorShape(871U, 923U), TensorShape(871U, 2U), 0, 0); add_config(TensorShape(923U, 429U), TensorShape(871U, 923U), TensorShape(871U, 429U), 0, 0); + add_config(TensorShape(873U, 7U), TensorShape(784U, 873U), TensorShape(784U, 7U), -1, 3); add_config(TensorShape(873U, 513U), TensorShape(784U, 873U), TensorShape(784U, 513U), 0, 4); add_config(TensorShape(697U, 872U), TensorShape(563U, 697U), TensorShape(563U, 872U), -2, 0); add_config(TensorShape(1021U, 973U), TensorShape(783U, 1021U), TensorShape(783U, 973U), 5, 13); |