blob: 1988ba4e927eb5d8eedc094e723c8b7b973f855e [file] [log] [blame]
Georgios Pinitasd8e765b2017-08-02 13:44:33 +01001/*
Michele Di Giorgiod9eaf612020-07-08 11:12:57 +01002 * Copyright (c) 2017 Arm Limited.
Georgios Pinitasd8e765b2017-08-02 13:44:33 +01003 *
4 * SPDX-License-Identifier: MIT
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a copy
7 * of this software and associated documentation files (the "Software"), to
8 * deal in the Software without restriction, including without limitation the
9 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
10 * sell copies of the Software, and to permit persons to whom the Software is
11 * furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice shall be included in all
14 * copies or substantial portions of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22 * SOFTWARE.
23 */
24#include "helpers.h"
25
26/** Perform a floor operation on an input tensor.
27 *
28 * @attention Data type can be passed using the -DDATA_TYPE compile flag, e.g. -DDATA_TYPE=float
29 * @attention Vector size should be given as a preprocessor argument using -DVEC_SIZE=size. e.g. -DVEC_SIZE=16
30 * @note Can only take floating point data types.
31 *
32 * @param[in] input_ptr Pointer to the source image. Supported data types: F16/F32
33 * @param[in] input_stride_x Stride of the source image in X dimension (in bytes)
34 * @param[in] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)
35 * @param[in] input_stride_y Stride of the source image in Y dimension (in bytes)
36 * @param[in] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)
37 * @param[in] input_stride_z Stride of the source tensor in Z dimension (in bytes)
38 * @param[in] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)
39 * @param[in] input_offset_first_element_in_bytes The offset of the first element in the source image
40 * @param[out] output_ptr Pointer to the destination image. Supported data types: same as @p input_ptr
41 * @param[in] output_stride_x Stride of the destination image in X dimension (in bytes)
42 * @param[in] output_step_x output_stride_x * number of elements along X processed per workitem(in bytes)
43 * @param[in] output_stride_y Stride of the destination image in Y dimension (in bytes)
44 * @param[in] output_step_y output_stride_y * number of elements along Y processed per workitem(in bytes)
45 * @param[in] output_stride_z Stride of the source tensor in Z dimension (in bytes)
46 * @param[in] output_step_z output_stride_z * number of elements along Z processed per workitem(in bytes)
47 * @param[in] output_offset_first_element_in_bytes The offset of the first element in the destination image
48 */
49__kernel void floor_layer(
50 TENSOR3D_DECLARATION(input),
51 TENSOR3D_DECLARATION(output))
52{
53 Tensor3D input = CONVERT_TO_TENSOR3D_STRUCT(input);
54 Tensor3D output = CONVERT_TO_TENSOR3D_STRUCT(output);
55
56 VSTORE(VEC_SIZE)
57 (floor(VLOAD(VEC_SIZE)(0, (__global DATA_TYPE *)input.ptr)), 0, (__global DATA_TYPE *)output.ptr);
58}