Rework DepthwiseConvolution heuristic on OpenCL
Resolves COMPMID-5632
Change-Id: I2bdbe69a610ca2510fbd74d5d412842679299762
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8365
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: Jakub Sujak <jakub.sujak@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h b/src/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h
index eeed115..5352f68 100644
--- a/src/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h
+++ b/src/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2019-2021 Arm Limited.
+ * Copyright (c) 2019-2022 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -103,7 +103,8 @@
unsigned int _depth_multiplier{ 0 };
const ICLTensor *_output_multipliers{};
const ICLTensor *_output_shifts{};
- bool _export_to_cl_image { true };
+ bool _export_input_to_cl_image{ false };
+ bool _export_weights_to_cl_image{ true };
bool _is_quantized{ false };
};
} // namespace arm_compute