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
|
/* tests that non-kernel functions which call work-item functions like
* get_global_id() can be compiled
Copyright (c) 2012 Pekka Jääskeläinen / Tampere University of Technology
Copyright (c) 2022 Michal Babej / Intel Finland Oy
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.
*/
// Enable OpenCL C++ exceptions
#define CL_HPP_ENABLE_EXCEPTIONS
#include <CL/opencl.hpp>
#include <cstdio>
#include <cstdlib>
#include <iostream>
#include <random>
#include "pocl_opencl.h"
#define WORK_ITEMS 128
#define BUFFER_SIZE 128
#define STRINGIFY(X, Y) X #Y
#define BUILD_OPTION(NUM) STRINGIFY("-DBUFFER_SIZE=", NUM)
static char
kernelSourceCode[] = R"raw(
void test5(__global float *b) {
size_t gid = get_global_id(0);
float f = sin(b[gid]);
printf("calling printf in test5: %u | %f\n", (unsigned)gid, f);
}
__kernel void test1 (__global const float *a) {
size_t gid = get_global_id(0);
printf("calling printf in test1: %u | %f\n", (unsigned)gid, a[gid]);
test5(a);
}
)raw";
int
main(void)
{
float A[BUFFER_SIZE];
std::random_device RandomDevice;
std::mt19937 Mersenne{RandomDevice()};
std::uniform_real_distribution<float> UniDist{100.0f, 200.0f};
std::vector<cl::Platform> platformList;
bool ok = false;
try {
cl::Platform::get(&platformList);
cl_context_properties cprops[] = {
CL_CONTEXT_PLATFORM, (cl_context_properties)(platformList[0])(), 0};
cl::Context context(CL_DEVICE_TYPE_CPU|CL_DEVICE_TYPE_GPU, cprops);
std::vector<cl::Device> devices = context.getInfo<CL_CONTEXT_DEVICES>();
cl::Program::Sources sources({kernelSourceCode});
cl::Program program(context, sources);
for (int i = 0; i < BUFFER_SIZE; ++i)
A[i] = UniDist(Mersenne);
program.build(devices, BUILD_OPTION(BUFFER_SIZE));
cl::Buffer aBuffer = cl::Buffer(
context,
CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR,
BUFFER_SIZE * sizeof(float),
(void *) &A[0]);
cl::Kernel test1(program, "test1");
test1.setArg(0, aBuffer);
cl::CommandQueue queue(context, devices[0], 0);
queue.enqueueNDRangeKernel(
test1,
cl::NullRange,
cl::NDRange(WORK_ITEMS),
cl::NullRange);
queue.finish();
ok = true;
}
catch (cl::Error &err) {
std::cerr << "ERROR: " << err.what() << "(" << err.err() << ")"
<< std::endl;
return EXIT_FAILURE;
}
platformList[0].unloadCompiler();
if (ok) {
std::cout << "OK" << std::endl;
return EXIT_SUCCESS;
} else {
std::cout << "FAIL\n";
return EXIT_FAILURE;
}
}
|
