From 4b90865ab985d571f70c60583cdfb8c7a65f1670 Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Thu, 18 Oct 2018 10:21:02 +0100 Subject: COMPMID-1413 - Improve the performance of GEMMLowp with 8 bit dot product on OpenCL COMPMID-1424 - Add dot product support for CLDepthwise QASYMM8 3x3 NHWC non-unit stride With this patch we are able to improve the performance of MobileNet v1-qasymm8 by 37 % Tried to use the dot product instruction in CLDepthwise QASYMM8 3x3 NHWC non-unit stride but I have not seen any benefit (maybe because we have few arithemtic operation and we do not have more load instructions). However Depthwise convolution has been improved by 30% Change-Id: Id768a99c2e53a04276707e427af5d0ec93419ada Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/155082 Tested-by: bsgcomp Reviewed-by: Georgios Pinitas --- src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp') diff --git a/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp b/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp index eb561faf77..19cc649c96 100644 --- a/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp +++ b/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp @@ -246,13 +246,12 @@ void CLDepthwiseConvolutionLayer3x3NCHWKernel::configure(const ICLTensor *input, int output_shift = 0; quantization::calculate_quantized_multiplier_less_than_one(multiplier, &output_multiplier, &output_shift); + build_opts.add_option("-DREAL_MULTIPLIER=" + support::cpp11::to_string(multiplier)); build_opts.add_option("-DCONV_STRIDE_Y=" + support::cpp11::to_string(_conv_stride_y)); build_opts.add_option("-DINPUT_OFFSET=" + support::cpp11::to_string(-_input->info()->quantization_info().offset)); build_opts.add_option("-DWEIGHTS_OFFSET=" + support::cpp11::to_string(-_weights->info()->quantization_info().offset)); build_opts.add_option("-DOUTPUT_OFFSET=" + support::cpp11::to_string(_output->info()->quantization_info().offset)); build_opts.add_option("-DK_OFFSET=" + support::cpp11::to_string(9 * input->info()->quantization_info().offset * weights->info()->quantization_info().offset)); - build_opts.add_option("-DOUTPUT_MULTIPLIER=" + support::cpp11::to_string(output_multiplier)); - build_opts.add_option("-DOUTPUT_SHIFT=" + support::cpp11::to_string(output_shift)); if(act_info.enabled()) { -- cgit v1.2.1