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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
|
/***************************************************************************************************
* Copyright (c) 2017 - 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: BSD-3-Clause
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* 2. 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.
*
* 3. Neither the name of the copyright holder 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 THE COPYRIGHT HOLDER OR CONTRIBUTORS 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 TORT (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 <cuda_runtime_api.h>
#include "cutlass_unit_test.h"
/////////////////////////////////////////////////////////////////////////////////////////////////
/// Gets a CUDA device
cudaDeviceProp GetCudaDevice() {
cudaError_t err;
int cudaDeviceId;
err = cudaGetDevice(&cudaDeviceId);
if (cudaSuccess != err) {
std::cerr << "*** Error: Could not detect active GPU device ID"
<< " [" << cudaGetErrorString(err) << "]" << std::endl;
exit(1);
}
cudaDeviceProp deviceProperties;
err = cudaGetDeviceProperties(&deviceProperties, cudaDeviceId);
return deviceProperties;
}
/// Prints device properties
std::ostream &operator<<(std::ostream &out, cudaDeviceProp const &deviceProperties) {
int deviceMajorMinor = deviceProperties.major * 10 + deviceProperties.minor;
if (deviceMajorMinor) {
int32_t clock_MHz = deviceProperties.clockRate / 1000;
out << "GPU(compute_"
<< deviceMajorMinor << ", "
<< deviceProperties.multiProcessorCount << " SMs @ " << clock_MHz << " MHz)";
}
else {
out << "No CUDA device.";
}
return out;
}
/////////////////////////////////////////////////////////////////////////////////////////////////
/// Sets flags for Unit test
void FilterArchitecture() {
// Default flags can be overwritten by --gtest_filter from commandline
int const kMaxDevice = 999;
cudaError_t err;
int cudaDeviceId;
err = cudaGetDevice(&cudaDeviceId);
if (cudaSuccess != err) {
std::cerr << "*** Error: Could not detect active GPU device ID"
<< " [" << cudaGetErrorString(err) << "]" << std::endl;
exit(1);
}
cudaDeviceProp deviceProperties;
err = cudaGetDeviceProperties(&deviceProperties, cudaDeviceId);
if (cudaSuccess != err) {
std::cerr << "*** Error: Could not get device properties for GPU " << cudaDeviceId << " ["
<< cudaGetErrorString(err) << "]" << std::endl;
exit(1);
}
int deviceMajorMinor = deviceProperties.major * 10 + deviceProperties.minor;
// Defines text filters for each GEMM kernel based on minimum supported compute capability
struct {
/// Unit test filter string
char const *filter;
/// Minimum compute capability for the kernels in the named test
int min_compute_capability;
/// Maximum compute capability for which the kernels are enabled
int max_compute_capability;
}
test_filters[] = {
{ "SM50*", 50, kMaxDevice},
{ "SM60*", 60, kMaxDevice},
{ "SM61*", 61, kMaxDevice},
{ "SM70*", 70, 75},
{ "SM75*", 75, kMaxDevice},
{ "SM80*", 80, kMaxDevice},
{ "SM90*", 90, 90 },
{ 0, 0, false }
};
// Set negative test filters
std::stringstream ss;
ss << "-";
for (int i = 0, j = 0; test_filters[i].filter; ++i) {
if (deviceMajorMinor < test_filters[i].min_compute_capability ||
deviceMajorMinor > test_filters[i].max_compute_capability) {
ss << (j++ ? ":" : "") << test_filters[i].filter;
}
}
::testing::GTEST_FLAG(filter) = ss.str();
}
/////////////////////////////////////////////////////////////////////////////////////////////////
int CutlassUnitTestProblemCount() {
if(const char* problem_count = std::getenv("CUTLASS_UNIT_TEST_PROBLEM_COUNT")) {
return std::stoi(problem_count);
}
return 0;
}
/////////////////////////////////////////////////////////////////////////////////////////////////
|
