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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
|
/*
* 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.
*/
#pragma once
#include "arm_gemm.hpp"
namespace arm_gemm
{
template <typename To, typename Tr>
class GemmBatched : public GemmCommon<To, Tr>
{
private:
UniqueGemmCommon<To, Tr> _subgemm = nullptr;
public:
GemmBatched(const CPUInfo &ci, const unsigned int M, const unsigned int N, const unsigned int K,
const unsigned int nbatches, const unsigned int nmulti, const bool trA, const bool trB,
const To alpha, const To beta, const int maxthreads, const bool pretransposed_hint)
{
/* Just create a subgemm with batches->M */
_subgemm = gemm<To, Tr>(ci, nbatches, N, K, 1, nmulti, trA, trB, alpha, beta, maxthreads, pretransposed_hint);
}
void set_arrays(const To *A, const int lda, const int A_batch_stride, const int A_multi_stride,
const To *B, const int ldb, const int B_multi_stride,
Tr *C, const int ldc, const int C_batch_stride, const int C_multi_stride) override
{
/* A and C's batch stride becomes their new row stride. New batch stride is 0 as nbatches for subgemm is always 1. */
_subgemm->set_arrays(A, A_batch_stride, 0, A_multi_stride,
B, ldb, B_multi_stride,
C, C_batch_stride, 0, C_multi_stride);
}
unsigned int get_window_size() const override
{
return _subgemm->get_window_size();
}
void set_nthreads(int nthreads) override
{
_subgemm->set_nthreads(nthreads);
}
void execute(unsigned int start, unsigned int end, int threadid) override
{
_subgemm->execute(start, end, threadid);
}
size_t get_working_size() const override
{
return _subgemm->get_working_size();
}
void set_working_space(void *space) override
{
_subgemm->set_working_space(space);
}
bool B_is_pretransposed() const override
{
return _subgemm->B_is_pretransposed();
}
bool B_pretranspose_required() const override
{
return _subgemm->B_pretranspose_required();
}
size_t get_B_pretransposed_array_size() const override
{
return _subgemm->get_B_pretransposed_array_size();
}
void pretranspose_B_array(void *buffer, const To *B, const int ldb, const int B_multi_stride) override
{
_subgemm->pretranspose_B_array(buffer, B, ldb, B_multi_stride);
}
void set_pretransposed_B_data(void *buffer) override
{
_subgemm->set_pretransposed_B_data(buffer);
}
};
} // namespace arm_gemm
|
