diff options
author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2021-10-01 17:48:02 +0100 |
---|---|---|
committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2021-10-06 10:40:49 +0000 |
commit | 8b8405aec8af17b04205b60094680751abfdc94a (patch) | |
tree | ae8f7e68271acf4791cab04c6deaf9a9ddcb3b38 /src/core/NEON/kernels/arm_conv/depthwise/depthwise_fp32.cpp | |
parent | 8229e5a8b5e38fcfa53cab5752f12e8f17a65e6c (diff) | |
download | ComputeLibrary-8b8405aec8af17b04205b60094680751abfdc94a.tar.gz |
Optimize CpuScale NHWC F32/F16
- Rework CpuScaleKernel F32/F16 NHWC - bilinear
- Rework CpuScaleKernel F32/F16 NHWC - nearest
- Add test to validate the vector computation path
Resolves COMPMID-4801, COMPMID-4802
Change-Id: Ie6e4f262a8cce509edd7b8f564c940758625c58a
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6361
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_conv/depthwise/depthwise_fp32.cpp')
0 files changed, 0 insertions, 0 deletions