From 8155c0253c00aa9e26651361460c66feb39829a6 Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Fri, 16 Apr 2021 15:08:59 +0100 Subject: Rework OpenCL Depthwise Convolution - Remove dedicated kernels for NCHW. Now we only use NHWC with permute - Remove specialized kernels for 3x3 NHWC - Simplify CLDepthwiseConvolutionLayer.cpp to call just the native implementation for both floating-point and quantized data types - Develop two parametric opencl kernels for depthwise convolution layer NHWC (floating-point and quantized) - Add support to export the weights to cl_image - Extend test for depthwise convolution on opencl Resolves COMPMID-4417 Change-Id: Ibe533f79c2860f9cac8e921895d5a8f947753a5c Signed-off-by: Gian Marco Iodice Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5893 Reviewed-by: Giorgio Arena Tested-by: Arm Jenkins Comments-Addressed: Arm Jenkins --- arm_compute/core/CL/CLHelpers.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arm_compute/core/CL/CLHelpers.h') diff --git a/arm_compute/core/CL/CLHelpers.h b/arm_compute/core/CL/CLHelpers.h index a9ac6a5933..180211c558 100644 --- a/arm_compute/core/CL/CLHelpers.h +++ b/arm_compute/core/CL/CLHelpers.h @@ -236,5 +236,13 @@ bool get_wbsm_support_info(const cl::Device &device); */ void set_wbsm(cl::Kernel &kernel, cl_int wbsm_hint); +/* Helper function to check if we can export the weights to cl_image + * + * @param[in] tensor Weights tensor + * + * @return true if we can export the weights to cl_image + */ +bool export_weights_to_cl_image(const ITensorInfo *tensor); + } // namespace arm_compute #endif /* ARM_COMPUTE_CLHELPERS_H */ -- cgit v1.2.1