| /* |
| * Copyright (c) 2017 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. |
| */ |
| layout(local_size_x = LOCAL_SIZE_X, local_size_y = LOCAL_SIZE_Y, local_size_z = LOCAL_SIZE_Z) in; |
| |
| #include "helpers_cs.h" |
| |
| #if defined(DATA_TYPE_FP16) |
| precision mediump float; |
| #endif /*DATA_TYPE_FP16*/ |
| |
| /** This kernel concatenates the input tensor into the output tensor along the third dimension |
| * |
| * @note The data type must be passed at compile time using "#define DATA_TYPE_NAME". e.g. "#define DATA_TYPE_FP32" |
| * |
| * @param[in] src_ptr Pointer to the source tensor. Supported data types: F16/F32 |
| * @param[in] src_attrs The attributes of the source tensor |
| * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src_ptr |
| * @param[in] dst_attrs The attributes of the destination tensor |
| */ |
| SHADER_PARAMS_DECLARATION |
| { |
| Tensor3DAttributes src_attrs; |
| Tensor3DAttributes dst_attrs; |
| }; |
| |
| #ifdef DATA_TYPE_FP32 |
| TENSOR_DECLARATION(1, srcBuffer, float, src_ptr, src_shift, 2, readonly); |
| TENSOR_DECLARATION(2, dstBuffer, float, dst_ptr, dst_shift, 2, writeonly); |
| |
| void main(void) |
| { |
| Tensor3DIterator src_iter = CONVERT_TO_TENSOR3D_ITERATOR(src_attrs, src_shift); |
| Tensor3DIterator dst_iter = CONVERT_TO_TENSOR3D_ITERATOR(dst_attrs, dst_shift); |
| |
| float tmp = LOAD(src_ptr, TENSOR3D_OFFSET(src_iter, -OFFSETS_X, -OFFSETS_Y, 0)); |
| STORE(dst_ptr, TENSOR_OFFSET_ADVANCE_IN_BYTES(dst_iter, OFFSETS_Z), tmp); |
| } |
| |
| #elif defined(DATA_TYPE_FP16) |
| TENSOR_DECLARATION(1, srcBuffer, uvec2, src_ptr, src_shift, 3, readonly); |
| TENSOR_DECLARATION(2, dstBuffer, uvec2, dst_ptr, dst_shift, 3, writeonly); |
| |
| void main(void) |
| { |
| Tensor3DIterator src_iter = CONVERT_TO_TENSOR3D_ITERATOR(src_attrs, src_shift); |
| Tensor3DIterator dst_iter = CONVERT_TO_TENSOR3D_ITERATOR(dst_attrs, dst_shift); |
| |
| uvec2 tmp = LOAD(src_ptr, TENSOR3D_OFFSET(src_iter, -OFFSETS_X, -OFFSETS_Y, 0)); |
| STORE(dst_ptr, TENSOR_OFFSET_ADVANCE_IN_BYTES(dst_iter, OFFSETS_Z), tmp); |
| } |
| #endif /*DATA_TYPE_FP16*/ |