diff options
| author | Siddhartha Menon <siddhartha.menon@arm.com> | 2024-08-02 10:32:12 +0000 |
|---|---|---|
| committer | Siddhartha Menon <siddhartha.menon@arm.com> | 2024-08-02 14:47:57 +0000 |
| commit | b8151190072256b97e696249298086797618f832 (patch) | |
| tree | ccc2877bcc2a0d7beae33d4791e2c55a3ab7cebb /arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h | |
| parent | 0fd04bfc8662b99556c73a8473eb215bd6775ed7 (diff) | |
| download | ComputeLibrary-release_candidate.tar.gz | |
call prepare() in run() to match NE conv interfaceHEADrelease_candidatemain
NEGEMMConv2d and NEWinogradConvolutionLayer call prepare() as part of
their run() method. This behaviour is assumed by other external
libraries. This patch matches this behaviour for the Cpu-convolution
wrappers.
Change-Id: Icebfb622a27fccf572c48b11d7016ce8c7575fec
Signed-off-by: Siddhartha Menon <siddhartha.menon@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/12028
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h')
0 files changed, 0 insertions, 0 deletions