1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
|
/*
* Copyright (c) 2017-2018 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.
*/
#include "GEMM.h"
#include "arm_compute/core/Types.h"
namespace arm_compute
{
namespace test
{
namespace validation
{
namespace reference
{
template <typename T>
SimpleTensor<T> gemm_transpose_1xW(const SimpleTensor<T> &in)
{
const int W = 16 / sizeof(T);
const TensorShape shape_out(static_cast<size_t>(in.shape().y() * W), static_cast<size_t>(std::ceil(in.shape().x() / static_cast<float>(W))));
SimpleTensor<T> out(shape_out, in.data_type());
const int32_t in_height = in.shape().y();
const int32_t in_width = in.shape().x();
const int32_t out_width = out.shape().x();
const T *in_base_addr = reinterpret_cast<const T *>(in.data());
T *out_base_addr = reinterpret_cast<T *>(out.data());
int x = 0;
for(; x < in_width; x += W)
{
for(int y = 0; y < in_height; y++)
{
const T *in_addr = (in_base_addr + x + y * in_width);
T *out_addr = (out_base_addr + y * W + (x / W) * out_width);
for(int k = 0; k < W; ++k)
{
// If the input width is not multiple of W, we fill the reference with 0s
if((x + k) >= in_width)
{
out_addr[k] = T(0);
}
else
{
out_addr[k] = in_addr[k];
}
}
}
}
return out;
}
} // namespace reference
} // namespace validation
} // namespace test
} // namespace arm_compute
|
