commit | 8baca90f290b6b9f621749aa5778f40014cd309b | [log] [tgz] |
---|---|---|
author | David Mansell <David.Mansell@arm.com> | Tue Aug 22 13:27:03 2023 +0100 |
committer | Ramy Elgammal <ramy.elgammal@arm.com> | Tue Aug 22 16:21:26 2023 +0100 |
tree | e2d25f4f54f8f771653a81872253c8dbacf68e06 | |
parent | 1a4ae04ed1918352864909c955da93b435f0ef9b [diff] |
CPU: Depthwise: Generate correct size for input indirection array. Signed-off-by: David Mansell <David.Mansell@arm.com> Change-Id: I359ed0703f4036e017b34b622f76b630cefac973 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10183 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/arm_conv/depthwise/depthwise_depthfirst_generic.hpp b/src/core/NEON/kernels/arm_conv/depthwise/depthwise_depthfirst_generic.hpp index ca5026b..e2d0556 100644 --- a/src/core/NEON/kernels/arm_conv/depthwise/depthwise_depthfirst_generic.hpp +++ b/src/core/NEON/kernels/arm_conv/depthwise/depthwise_depthfirst_generic.hpp
@@ -186,7 +186,7 @@ static size_t get_element_size(const WorkspaceArgs<IDepthfirstStrategy, OutputStage> &args) { const auto kernel_points = args.depthwise_args.kernel_rows * args.depthwise_args.kernel_cols; - return sizeof(T **) * args.strategy->get_input_rows() * args.strategy->get_input_cols() * kernel_points; + return sizeof(T **) * args.strategy->get_output_rows() * args.strategy->get_output_cols() * kernel_points; } template <class WorkspaceType, class OutputStage>