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 --- arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h') diff --git a/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h b/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h index 3db76f423c..682475c824 100644 --- a/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h +++ b/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h @@ -75,22 +75,24 @@ public: * * @param[in] a First input tensor (Matrix A). Data type supported: QASYMM8. * @param[in] b Second input tensor (Matrix B). Data type supported: same as @p a + * @param[in] c Third input tensor (Matrix C). It can be a nullptr. Data type supported: S32 * @param[out] output Output tensor. Data type supported: Data type supported: S32 * @param[in] gemm_info (Optional) Specifies if the matrix A and/or matrix B have been reshaped and * if the reshape of matrix B should be executed only for the first run */ - void configure(const ITensor *a, const ITensor *b, ITensor *output, const GEMMInfo &gemm_info = GEMMInfo()); + void configure(const ITensor *a, const ITensor *b, const ITensor *c, ITensor *output, const GEMMInfo &gemm_info = GEMMInfo()); /** Static function to check if given info will lead to a valid configuration of @ref NEGEMMLowpMatrixMultiplyCore * * @param[in] a First input tensor (Matrix A). Data type supported: QASYMM8. * @param[in] b Second input tensor (Matrix B). Data type supported: same as @p a + * @param[in] c Third input tensor (Matrix C). It can be a nullptr. Data type supported: S32 * @param[in] output Output tensor. Data type supported: Data type supported: S32 * @param[in] gemm_info (Optional) Specifies if the matrix A and/or matrix B have been reshaped and * if the reshape of matrix B should be executed only for the first run * * @return a status */ - static Status validate(const ITensorInfo *a, const ITensorInfo *b, const ITensorInfo *output, const GEMMInfo &gemm_info = GEMMInfo()); + static Status validate(const ITensorInfo *a, const ITensorInfo *b, const ITensorInfo *c, const ITensorInfo *output, const GEMMInfo &gemm_info = GEMMInfo()); // Inherited methods overridden void run() override; -- cgit v1.2.1