From 932491f44d51940d82514417a82e43cb11b06bd4 Mon Sep 17 00:00:00 2001 From: Georgios Pinitas Date: Fri, 21 Sep 2018 16:33:15 +0100 Subject: COMPMID-1519: Add support for 3D input/output in CLGEMMLowpOutputStage Change-Id: I637add70310d2da4d82b236a6352af9d33be17a1 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149706 Reviewed-by: Isabella Gottardi Reviewed-by: Michele DiGiorgio Tested-by: bsgcomp --- ...antizeDownInt32ToUint8ScaleByFixedPointKernel.h | 26 +++++++++++++--------- 1 file changed, 15 insertions(+), 11 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 49e19e3c63..1206206fdc 100644 --- a/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017 ARM Limited. + * Copyright (c) 2017-2018 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -67,21 +67,25 @@ 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); + 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); /** 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, - * Along with @p min, this value can be used to implement "rectified linear unit" activation functions + * @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); + static Status validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, + int min = 0, int max = 0, unsigned int output_3d_depth = 1); // Inherited methods overridden: void run(const Window &window, cl::CommandQueue &queue) override; @@ -90,7 +94,7 @@ 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