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/CLKernelLibrary.cpp | 3 +++ 1 file changed, 3 insertions(+) (limited to 'src/core/CL/CLKernelLibrary.cpp') diff --git a/src/core/CL/CLKernelLibrary.cpp b/src/core/CL/CLKernelLibrary.cpp index 880963de7b..b9b3ce970b 100644 --- a/src/core/CL/CLKernelLibrary.cpp +++ b/src/core/CL/CLKernelLibrary.cpp @@ -259,6 +259,7 @@ const std::map CLKernelLibrary::_kernel_program_map = { "gemm_lc_vm_f32", "gemm.cl" }, { "gemm_transpose1xW", "gemm.cl" }, { "gemmlowp_matrix_a_reduction", "gemmlowp.cl" }, + { "gemmlowp_matrix_a_reduction_dot8", "gemmlowp.cl" }, { "gemmlowp_matrix_b_reduction", "gemmlowp.cl" }, { "gemmlowp_mm_bifrost", "gemmlowp.cl" }, { "gemmlowp_mm_bifrost_dot8", "gemmlowp.cl" }, @@ -267,6 +268,8 @@ const std::map CLKernelLibrary::_kernel_program_map = { "gemmlowp_mm_interleaved_transposed_bifrost_dot8", "gemmlowp.cl" }, { "gemmlowp_mm_interleaved_transposed_midgard", "gemmlowp.cl" }, { "gemmlowp_offset_contribution", "gemmlowp.cl" }, + { "gemmlowp_offset_contribution_quantize_down", "gemmlowp.cl" }, + { "gemmlowp_offset_contribution_quantize_down_fixedpoint", "gemmlowp.cl" }, { "gemmlowp_output_stage_quantize_down", "gemmlowp.cl" }, { "gemmlowp_output_stage_quantize_down_fixedpoint", "gemmlowp.cl" }, { "gemmlowp_output_stage_quantize_down_float", "gemmlowp.cl" }, -- cgit v1.2.1