diff options
Diffstat (limited to 'compute/ARMComputeEx/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCoreEx.h')
| -rw-r--r-- | compute/ARMComputeEx/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCoreEx.h | 170 |
1 files changed, 0 insertions, 170 deletions
diff --git a/compute/ARMComputeEx/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCoreEx.h b/compute/ARMComputeEx/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCoreEx.h deleted file mode 100644 index d844513c9..000000000 --- a/compute/ARMComputeEx/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCoreEx.h +++ /dev/null @@ -1,170 +0,0 @@ -/* - * Copyright (c) 2019 Samsung Electronics Co., Ltd. All Rights Reserved - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -/* - * Copyright (c) 2017-2019 ARM Limited. - * - * SPDX-License-Identifier: MIT - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in all - * copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#ifndef __ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYCOREEX_H__ -#define __ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYCOREEX_H__ - -#include "arm_compute/core/NEON/INEKernel.h" -#include "arm_compute/core/NEON/kernels/NEGEMMLowpOffsetContributionKernel.h" -#include "arm_compute/core/NEON/kernels/NEGEMMLowpOffsetContributionOutputStageKernel.h" -#include "arm_compute/core/NEON/kernels/NEGEMMLowpReductionKernel.h" -#include "arm_compute/runtime/IFunction.h" -#include "arm_compute/runtime/IMemoryManager.h" -#include "arm_compute/runtime/MemoryGroup.h" -// #include "arm_compute/runtime/NEON/functions/NEActivationLayer.h" -#include "arm_compute/runtime/NEON/functions/NEGEMMAssemblyDispatch.h" -#include "arm_compute/runtime/Tensor.h" - -#include <memory> - -namespace arm_compute -{ -class ITensor; - -/** Basic function to execute GEMMLowpMatrixMultiplyCore on NEON. This function calls the following - * NEON kernels if the DOT product instruction is not available: - * - * -# @ref NEGEMMInterleave4x4Kernel - * -# @ref NEGEMMTranspose1xWKernel - * -# @ref NEGEMMLowpMatrixMultiplyKernel - * -# @ref NEGEMMLowpOffsetContributionKernel - * -# @ref NEActivationLayer - * - * otherwise if the DOT product instruction is available: - * - * -# @ref NEGEMMLowpOffsetContributionKernel - * -*/ -class NEGEMMLowpMatrixMultiplyCoreEx : public IFunction -{ -public: - /** Constructor */ - NEGEMMLowpMatrixMultiplyCoreEx(std::shared_ptr<IMemoryManager> memory_manager = nullptr); - /** Prevent instances of this class from being copied (As this class contains pointers) */ - NEGEMMLowpMatrixMultiplyCoreEx(const NEGEMMLowpMatrixMultiplyCoreEx &) = delete; - /** Default move constructor */ - NEGEMMLowpMatrixMultiplyCoreEx(NEGEMMLowpMatrixMultiplyCoreEx &&) = default; - /** Prevent instances of this class from being copied (As this class contains pointers) */ - NEGEMMLowpMatrixMultiplyCoreEx &operator=(const NEGEMMLowpMatrixMultiplyCoreEx &) = delete; - /** Default move assignment operator */ - NEGEMMLowpMatrixMultiplyCoreEx &operator=(NEGEMMLowpMatrixMultiplyCoreEx &&) = default; - /** Initialise the kernel's inputs, output - * - * @note GEMM_LOWP: low precision GEMM kernel - * This kernel performs the following computations: - * - * -# Convert a values from QASYMM8 to int32 and add a_offset to each of them. - * -# Convert b values from QASYMM8 to int32 add b_offset to each of them. - * -# Compute the matrix product of the resulting a * b in int32. - * - * @note The @p output type is S32 if @p gemm_info.type == GEMMLowpOutputStageType::NONE. It is - * QASYMM8/QASYMM8_SIGNED otherwise - * - * @param[in] a First input tensor (Matrix A). Data type supported: - * QASYMM8/QASYMM8_SIGNED. - * @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/QASYMM8/QASYMM8_SIGNED - * @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, 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 - * NEGEMMLowpMatrixMultiplyCoreEx - * - * @note The @p output type is S32 if @p gemm_info.type == GEMMLowpOutputStageType::NONE. It is - * QASYMM8/QASYMM8_SIGNED otherwise - * - * @param[in] a First input tensor info (Matrix A). Data type supported: - * QASYMM8/QASYMM8_SIGNED. - * @param[in] b Second input tensor info (Matrix B). Data type supported: same as @p a - * @param[in] c Third input tensor info (Matrix C). It can be a nullptr. Data type - * supported: S32 - * @param[in] output Output tensor info. Data type supported: Data type supported: - * S32/QASYMM8/QASYMM8_SIGNED - * @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 *c, - const ITensorInfo *output, const GEMMInfo &gemm_info = GEMMInfo()); - - // Inherited methods overridden - void run() override; - void prepare() override; - -private: - MemoryGroup _memory_group; - NEGEMMAssemblyDispatch _asm_glue; - std::unique_ptr<INEKernel> _mm_kernel; - std::unique_ptr<INEKernel> _mtx_a_reshape_kernel; - std::unique_ptr<INEKernel> _mtx_b_reshape_kernel; - NEGEMMLowpMatrixAReductionKernel _mtx_a_reduction_kernel; - NEGEMMLowpMatrixBReductionKernel _mtx_b_reduction_kernel; - NEGEMMLowpOffsetContributionKernel _offset_contribution_kernel; - NEGEMMLowpOffsetContributionOutputStageKernel _offset_contribution_output_stage_kernel; - - Tensor _vector_sum_col; - Tensor _vector_sum_row; - Tensor _tmp_a; - Tensor _tmp_b; - Tensor _mm_result_s32; - Tensor _signed_a; - Tensor _signed_output; - const ITensor *_original_b; - int32_t _a_offset; - int32_t _b_offset; - - bool _run_vector_matrix_multiplication; - bool _assembly_path; - bool _fused_assembly_path; - bool _reshape_b_only_on_first_run; - bool _is_prepared; - bool _fuse_output_stage; - bool _flip_signedness; -}; -} // namespace arm_compute -#endif /*__ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYCOREEX_H__ */ |