diff options
author | Gunes Bayir <gunes.bayir@arm.com> | 2022-12-26 16:24:04 +0000 |
---|---|---|
committer | Gunes Bayir <gunes.bayir@arm.com> | 2022-12-29 17:27:33 +0000 |
commit | b7e8626717b2ef81b0d03284c8f6ffdbe9cd2245 (patch) | |
tree | 8fb8197a4f69fb5024a5330e031d3d5c0b26bdad /src/core/CL/kernels | |
parent | a5cb79f18685292bf5b63a0c484a58945320823d (diff) | |
download | ComputeLibrary-b7e8626717b2ef81b0d03284c8f6ffdbe9cd2245.tar.gz |
Optimize CL Scale/Resize Quantized by removing (de)quant. code
This patch removes the quant/dequant code in CLScale and the Resize operator in dynamic fusion. We don't support different quantization information for input and output and in this case the quantization and dequantization is not necessary. The very same optimization was delivered for cpu.
It also moves the SCALE_X and SCALE_Y arguments to look-up table from build options in the template writer of Resize.
Change-Id: Icd043c8671220c8feea935dd4b24a5b17c6c4ea4
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8888
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL/kernels')
0 files changed, 0 insertions, 0 deletions