commit | 8deee9bd9b9137c256c23b86be11dbf0466f3aa8 | [log] [tgz] |
---|---|---|
author | Michael Tyler <michael.tyler@arm.com> | Fri Jun 30 11:26:05 2023 +0100 |
committer | michael.tyler <michael.tyler@arm.com> | Tue Jul 04 14:34:58 2023 +0000 |
tree | ac80b3bdd992552b65e306b77f061484da0591ca | |
parent | 19844f605f5e5b71d05164711dee13f8652adafe [diff] [blame] |
Depthwise channel pre-multiplication Resolves: COMPMID-6337 Change-Id: Ie9097b3f56e8071426c621386a5988bd7f7e8ef2 Signed-off-by: Michael Tyler <michael.tyler@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9852 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/core/NEON/kernels/assembly/depthwise_common.hpp b/src/core/NEON/kernels/assembly/depthwise_common.hpp index fea6326..a5db793 100644 --- a/src/core/NEON/kernels/assembly/depthwise_common.hpp +++ b/src/core/NEON/kernels/assembly/depthwise_common.hpp
@@ -85,7 +85,7 @@ size_t ld_weight_row = 0) = 0; // Determine the amount of working space required - virtual size_t get_working_size(unsigned int n_threads, unsigned int n_input_channels) const = 0; + virtual size_t get_working_size(unsigned int n_threads) const = 0; // Execute the convolution over the specified area of memory. virtual void execute(