forked from NVIDIA/cutlass
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbatched_strided_sgemm_128x128x8.cu
135 lines (112 loc) · 6.72 KB
/
batched_strided_sgemm_128x128x8.cu
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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
/***************************************************************************************************
* Copyright (c) 2017-2019, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification, are permitted
* provided that the following conditions are met:
* * Redistributions of source code must retain the above copyright notice, this list of
* conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright notice, this list of
* conditions and the following disclaimer in the documentation and/or other materials
* provided with the distribution.
* * Neither the name of the NVIDIA CORPORATION nor the names of its contributors may be used
* to endorse or promote products derived from this software without specific prior written
* permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
* FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
* OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
* STRICT LIABILITY, OR TOR (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
**************************************************************************************************/
#include "cutlass_unit_test.h"
#include "cutlass/gemm/gemm.h"
#include "cutlass/gemm/sgemm_traits.h"
#include "tools/test/unit/gemm/gemm_testbed.h"
#include "tools/test/unit/gemm/run_gemm.h"
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_256x384x64x3_nn) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kColumnMajor,
cutlass::MatrixLayout::kColumnMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(256/*m*/, 384/*n*/, 64/*k*/, 3 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_128x384x192x2_nn) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kColumnMajor,
cutlass::MatrixLayout::kColumnMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(128/*m*/, 384/*n*/, 192/*k*/, 2 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_127x384x192x2_nn) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kColumnMajor,
cutlass::MatrixLayout::kColumnMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(127/*m*/, 384/*n*/, 192/*k*/, 2 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_127x388x190x2_nn) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kColumnMajor,
cutlass::MatrixLayout::kColumnMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(127/*m*/, 388/*n*/, 190/*k*/, 2 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_256x384x64x3_nt) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kColumnMajor,
cutlass::MatrixLayout::kRowMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(256/*m*/, 384/*n*/, 64/*k*/, 3 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_128x384x192x2_nt) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kColumnMajor,
cutlass::MatrixLayout::kRowMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(128/*m*/, 384/*n*/, 192/*k*/, 2 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_256x384x64x3_tn) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kRowMajor,
cutlass::MatrixLayout::kColumnMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(256/*m*/, 384/*n*/, 64/*k*/, 3 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_128x384x192x2_tn) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kRowMajor,
cutlass::MatrixLayout::kColumnMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(128/*m*/, 384/*n*/, 192/*k*/, 2 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_256x384x64x3_tt) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kRowMajor,
cutlass::MatrixLayout::kRowMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(256/*m*/, 384/*n*/, 64/*k*/, 3 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
TEST(Sgemm_strided_batched_128x128x8, sgemm_128x384x192x2_tt) {
typedef cutlass::gemm::SgemmTraits<cutlass::MatrixLayout::kRowMajor,
cutlass::MatrixLayout::kRowMajor, cutlass::Shape<8, 128, 128> >
SgemmTraits;
//think about using run_gemm directly
run_batched_strided_gemm<SgemmTraits>(128/*m*/, 384/*n*/, 192/*k*/, 2 /*batch_size*/);
}
////////////////////////////////////////////////////////////////////////////////////////////////////