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 --- ...QuantizeDownInt32ToUint8ScaleByFixedPointKernel.h | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h') diff --git a/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h b/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h index 1206206fdc..72373b50eb 100644 --- a/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h @@ -67,25 +67,22 @@ public: * @param[in] min (Optional) Min value used to saturate down the output result before converting back to QASYMM8 * @param[in] max (Optional) Max value used to saturate up the output result before converting back to QASYMM8, * Along with @p min, this value can be used to implement "rectified linear unit" activation functions - * @param[in] output_3d_depth (Optional) Depth of output in 3D (Defaults to 1) */ void configure(const ICLTensor *input, const ICLTensor *bias, ICLTensor *output, int result_fixedpoint_multiplier, int result_shift, int result_offset_after_shift, - int min = 0, int max = 0, unsigned int output_3d_depth = 1); + int min = 0, int max = 0); /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel * - * @param[in] input Input tensor. Data type supported: S32 - * @param[in] bias Biases tensor. Only shared biases supported and it can be a nullptr if the biases addition is not required. - * Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p input. - * @param[in] output Output tensor. Data type supported: Data type supported: QASYMM8 - * @param[in] min (Optional) Min value used to saturate down the output result before converting back to QASYMM8 - * @param[in] max (Optional) Max value used to saturate up the output result before converting back to QASYMM8, + * @param[in] input Input tensor. Data type supported: S32 + * @param[in] bias Biases tensor. Only shared biases supported and it can be a nullptr if the biases addition is not required. + * Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p input. + * @param[in] output Output tensor. Data type supported: Data type supported: QASYMM8 + * @param[in] min (Optional) Min value used to saturate down the output result before converting back to QASYMM8 + * @param[in] max (Optional) Max value used to saturate up the output result before converting back to QASYMM8, * Along with @p min, this value can be used to implement "rectified linear unit" activation functions - * @param[in] output_3d_depth (Optional) Depth of output in 3D (Defaults to 1) * * @return a status */ - static Status validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, - int min = 0, int max = 0, unsigned int output_3d_depth = 1); + static Status validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, int min = 0, int max = 0); // Inherited methods overridden: void run(const Window &window, cl::CommandQueue &queue) override; @@ -94,7 +91,6 @@ private: const ICLTensor *_input; const ICLTensor *_bias; ICLTensor *_output; - bool _reinterpret_as_3d; }; } // namespace arm_compute #endif /* __ARM_COMPUTE_CLGEMMLOWPQUANTIZEDOWNINT32TOUINT8SCALEBYFIXEDPOINTKERNEL_H__ */ -- cgit v1.2.1