COMPMID-3639: (3RDPARTY_UPDATE) Move CL kernels to src
Change-Id: I10d27db788e5086adae1841e3e2441cd9b76ef84
Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4310
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.h b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.h
new file mode 100644
index 0000000..125f0c6
--- /dev/null
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.h
@@ -0,0 +1,108 @@
+/*
+ * Copyright (c) 2019-2020 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_CLGEMMLOWPMATRIXMULTIPLYNATIVEKERNEL_H
+#define ARM_COMPUTE_CLGEMMLOWPMATRIXMULTIPLYNATIVEKERNEL_H
+
+#include "src/core/CL/ICLKernel.h"
+
+namespace arm_compute
+{
+class ICLTensor;
+
+/** OpenCL kernel to multiply matrices with QASYMM8/QASYMM8_SIGNED data type */
+class CLGEMMLowpMatrixMultiplyNativeKernel : public ICLKernel
+{
+public:
+ /** Default Constructor */
+ CLGEMMLowpMatrixMultiplyNativeKernel();
+ /** Prevent instances of this class from being copied (As this class contains pointers) */
+ CLGEMMLowpMatrixMultiplyNativeKernel(const CLGEMMLowpMatrixMultiplyNativeKernel &) = delete;
+ /** Prevent instances of this class from being copied (As this class contains pointers) */
+ CLGEMMLowpMatrixMultiplyNativeKernel &operator=(const CLGEMMLowpMatrixMultiplyNativeKernel &) = delete;
+ /** Allow instances of this class to be moved */
+ CLGEMMLowpMatrixMultiplyNativeKernel(CLGEMMLowpMatrixMultiplyNativeKernel &&) = default;
+ /** Allow instances of this class to be moved */
+ CLGEMMLowpMatrixMultiplyNativeKernel &operator=(CLGEMMLowpMatrixMultiplyNativeKernel &&) = default;
+ /** Initialise the kernel's input and output.
+ *
+ * @param[in] input0 Input tensor containing the LHS matrix. Data type supported: QASYMM8/QASYMM8_SIGNED
+ * @param[in] input1 Input tensor containing the RHS matrix. Data type supported: same as @p input0
+ * @param[out] output Output tensor to store the result of matrix multiplication. Data type supported: S32
+ * @param[in] lhs_info LHS matrix information used to retrieve the number of rows to be processed by each thread
+ * lhs_info.m0: 2,3,4,5,6,7,8
+ * lhs_info.k0: 2,3,4,8,16
+ * @param[in] rhs_info RHS matrix information used to retrieve the number of columns to be processed by each thread
+ * rhs_info.n0: 2,3,4,8,16
+ * rhs_info.k0: same as lhs_info.k0
+ * @param[in] gemm_info GEMM information used to retrieve the original dimensions of the input matrices
+ */
+ void configure(const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output, const GEMMLHSMatrixInfo &lhs_info, const GEMMRHSMatrixInfo &rhs_info, const GEMMReshapeInfo &gemm_info);
+ /** Initialise the kernel's input and output.
+ *
+ * @param[in] compile_context The compile context to be used.
+ * @param[in] input0 Input tensor containing the LHS matrix. Data type supported: QASYMM8/QASYMM8_SIGNED
+ * @param[in] input1 Input tensor containing the RHS matrix. Data type supported: same as @p input0
+ * @param[out] output Output tensor to store the result of matrix multiplication. Data type supported: S32
+ * @param[in] lhs_info LHS matrix information used to retrieve the number of rows to be processed by each thread
+ * lhs_info.m0: 2,3,4,5,6,7,8
+ * lhs_info.k0: 2,3,4,8,16
+ * @param[in] rhs_info RHS matrix information used to retrieve the number of columns to be processed by each thread
+ * rhs_info.n0: 2,3,4,8,16
+ * rhs_info.k0: same as lhs_info.k0
+ * @param[in] gemm_info GEMM information used to retrieve the original dimensions of the input matrices
+ */
+ void configure(const CLCompileContext &compile_context, const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output, const GEMMLHSMatrixInfo &lhs_info, const GEMMRHSMatrixInfo &rhs_info,
+ const GEMMReshapeInfo &gemm_info);
+ /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMLowpMatrixMultiplyNativeKernel
+ *
+ * @param[in] input0 Input tensor info for the LHS matrix. Data type supported: QASYMM8/QASYMM8_SIGNED
+ * @param[in] input1 Input tensor info for the RHS matrix. Data type supported: same as @p input0
+ * @param[in] output Output tensor info. Data type supported: S32
+ * @param[in] lhs_info LHS matrix information used to retrieve the number of rows to be processed by each thread
+ * lhs_info.m0: 2,3,4,5,6,7,8
+ * lhs_info.k0: 2,3,4,8,16
+ * @param[in] rhs_info RHS matrix information used to retrieve the number of columns to be processed by each thread
+ * rhs_info.n0: 2,3,4,8,16
+ * rhs_info.k0: same as lhs_info.k0
+ * @param[in] gemm_info GEMM information used to retrieve the original dimensions of the input matrices
+ *
+ * @return a status
+ */
+ static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output, const GEMMLHSMatrixInfo &lhs_info, const GEMMRHSMatrixInfo &rhs_info,
+ const GEMMReshapeInfo &gemm_info);
+
+ // Inherited methods overridden:
+ void run(const Window &window, cl::CommandQueue &queue) override;
+
+private:
+ const ICLTensor *_input0;
+ const ICLTensor *_input1;
+ ICLTensor *_output;
+ bool _slide_matrix_b;
+ bool _reinterpret_input_as_3d;
+ bool _reinterpret_output_as_3d;
+ bool _use_dummy_work_items;
+};
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMLOWPMATRIXMULTIPLYNATIVEKERNEL_H*/