From ff1fe3e32e25069fed750cdfe3046b7d8d5a2628 Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Sat, 2 Jan 2021 09:58:51 +0000 Subject: Remove padding from direct convolution - OpenCL - Refactor direct convolution for NHWC - Remove old kernels for NHWC - Change the heuristic in CLConvolutionLayer.cpp. The new direct convolution implementation is faster than FFT Resolves COMPMID-3908 Change-Id: Iee15ce7b04e21847b6eaae5c6d3c1b18180e7efc Signed-off-by: Gian Marco Iodice Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4876 Tested-by: Arm Jenkins Reviewed-by: Georgios Pinitas --- src/core/CL/cl_kernels/gemmlowp.cl | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'src/core/CL/cl_kernels/gemmlowp.cl') diff --git a/src/core/CL/cl_kernels/gemmlowp.cl b/src/core/CL/cl_kernels/gemmlowp.cl index 50dda7ef3c..ad92511c22 100644 --- a/src/core/CL/cl_kernels/gemmlowp.cl +++ b/src/core/CL/cl_kernels/gemmlowp.cl @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2020 Arm Limited. + * Copyright (c) 2017-2021 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -37,7 +37,6 @@ #if defined(ARM_COMPUTE_OPENCL_DOT8_ENABLED) && defined(cl_arm_integer_dot_product_int8) -/** Specialized macros to perform the dot product instruction between two vectors of size N [1,16]. These macros use the dot8 instruction */ #define ARM_DOT1(a, b, c) \ ({ \ ARM_DOT((VEC_DATA_TYPE(DATA_TYPE, 4))(a, (VEC_DATA_TYPE(DATA_TYPE, 3))0), (VEC_DATA_TYPE(DATA_TYPE, 4))(b, (VEC_DATA_TYPE(DATA_TYPE, 3))0), c); \ -- cgit v1.2.1