/
main.c
275 lines (244 loc) · 9.53 KB
/
main.c
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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
//
// File: hello.c
//
// Abstract: A simple "Hello World" compute example showing basic usage of OpenCL which
// calculates the mathematical square (X[i] = pow(X[i],2)) for a buffer of
// floating point values.
//
//
// Version: <1.0>
//
// Disclaimer: IMPORTANT: This Apple software is supplied to you by Apple Inc. ("Apple")
// in consideration of your agreement to the following terms, and your use,
// installation, modification or redistribution of this Apple software
// constitutes acceptance of these terms. If you do not agree with these
// terms, please do not use, install, modify or redistribute this Apple
// software.
//
// In consideration of your agreement to abide by the following terms, and
// subject to these terms, Apple grants you a personal, non - exclusive
// license, under Apple's copyrights in this original Apple software ( the
// "Apple Software" ), to use, reproduce, modify and redistribute the Apple
// Software, with or without modifications, in source and / or binary forms;
// provided that if you redistribute the Apple Software in its entirety and
// without modifications, you must retain this notice and the following text
// and disclaimers in all such redistributions of the Apple Software. Neither
// the name, trademarks, service marks or logos of Apple Inc. may be used to
// endorse or promote products derived from the Apple Software without specific
// prior written permission from Apple. Except as expressly stated in this
// notice, no other rights or licenses, express or implied, are granted by
// Apple herein, including but not limited to any patent rights that may be
// infringed by your derivative works or by other works in which the Apple
// Software may be incorporated.
//
// The Apple Software is provided by Apple on an "AS IS" basis. APPLE MAKES NO
// WARRANTIES, EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION THE IMPLIED
// WARRANTIES OF NON - INFRINGEMENT, MERCHANTABILITY AND FITNESS FOR A
// PARTICULAR PURPOSE, REGARDING THE APPLE SOFTWARE OR ITS USE AND OPERATION
// ALONE OR IN COMBINATION WITH YOUR PRODUCTS.
//
// IN NO EVENT SHALL APPLE BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL OR
// CONSEQUENTIAL DAMAGES ( INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
// SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
// INTERRUPTION ) ARISING IN ANY WAY OUT OF THE USE, REPRODUCTION, MODIFICATION
// AND / OR DISTRIBUTION OF THE APPLE SOFTWARE, HOWEVER CAUSED AND WHETHER
// UNDER THEORY OF CONTRACT, TORT ( INCLUDING NEGLIGENCE ), STRICT LIABILITY OR
// OTHERWISE, EVEN IF APPLE HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Copyright ( C ) 2008 Apple Inc. All Rights Reserved.
//
////////////////////////////////////////////////////////////////////////////////
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <CL/opencl.h>
#include "cl_util.h"
#include "common.h"
int main(int argc, char** argv)
{
int err; // error code returned from api calls
float *cpu_xyz; //calculate the results on the CPU
float *gpu_xyz; //calculate the results on the GPU
unsigned int correct; // number of correct results returned
char* kernel_source; //kernel source code
cl_platform_id platform_id; // compute platform id
cl_device_id device_id; // compute device id
cl_context context; // compute context
cl_command_queue commands; // compute command queue
cl_program program; // compute program
cl_kernel kernel; // compute kernel code
//stuff were going to query
cl_int preferred_workgroup_size;
cl_int max_workgroup_size;
cl_mem cl_output; // device memory used for the output array
int i, j, k;
if(!cl_load("main.cl", &kernel_source))
{
printf("Your file didn't load.");
return 1;
}
int theta, phi, r;
for(i=0; i<V_THETA_MAX; i++)
{
theta = i*V_THETA_INC;
for(j=0; j<V_PHI_MAX; j++)
{
phi = j*V_PHI_INC;
for(k=0; k<V_R_MAX; k++)
{
r = k*V_R_INC;
}
}
}
//get the platform information. This corresponds to vendor implementations of opencl
cl_uint platforms;
err = clGetPlatformIDs(1, &platform_id, &platforms);
if(err != CL_SUCCESS)
{
printf("Error: Failed to query platform ids!\n");
return EXIT_FAILURE;
}
// Connect to a compute device. A GPU in this case.
//
cl_uint num_devices;
err = clGetDeviceIDs(platform_id, CL_DEVICE_TYPE_GPU, 1, &device_id, &num_devices);
if (err != CL_SUCCESS)
{
printf("Error: Failed to create a device group!\n");
return EXIT_FAILURE;
}
// Create a compute context. A handle to the combination of platform and device.
//
context = clCreateContext(0, 1, &device_id, NULL, NULL, &err);
if (!context)
{
printf("Error: Failed to create a compute context!\n");
return EXIT_FAILURE;
}
// Create a command queue. We will use this to send work to the CPU.
//
commands = clCreateCommandQueue(context, device_id, 0, &err);
if (!commands)
{
printf("Error: Failed to create a command commands!\n");
return EXIT_FAILURE;
}
// create a program, given the loaded source code.
//
program = clCreateProgramWithSource(context, 1, (const char **) &kernel_source, NULL, &err);
if (!program)
{
printf("Error: Failed to create compute program!\n");
return EXIT_FAILURE;
}
// Compile the program executable
//
err = clBuildProgram(program, 0, NULL, NULL, NULL, NULL);
if (err != CL_SUCCESS)
{
size_t len;
char buffer[2048];
printf("Error: Failed to build program executable!\n");
clGetProgramBuildInfo(program, device_id, CL_PROGRAM_BUILD_LOG, sizeof(buffer), buffer, &len);
printf("%s\n", buffer);
exit(1);
}
// create (select) a kernel function from the compiled program
//
kernel = clCreateKernel(program, "square", &err);
if (!kernel || err != CL_SUCCESS)
{
printf("Error: Failed to create compute kernel!\n");
exit(1);
}
// Get the preferred workgroup size multiple
//
err = clGetKernelWorkGroupInfo(kernel, device_id, CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE, sizeof(preferred_workgroup_size), &preferred_workgroup_size, NULL);
if (err != CL_SUCCESS)
{
printf("Error: Failed to retrieve kernel work group info! %d\n", err);
exit(1);
}
// Get the preferred workgroup size
//
err = clGetKernelWorkGroupInfo(kernel, device_id, CL_DEVICE_MAX_WORK_GROUP_SIZE, sizeof(max_workgroup_size), &max_workgroup_size, NULL);
if (err != CL_SUCCESS)
{
printf("Error: Failed to retrieve kernel work group info! %d\n", err);
exit(1);
}
// Create the output array in device memory for our calculation
//
output = clCreateBuffer(context, CL_MEM_WRITE_ONLY, sizeof(float) * count, NULL, NULL);
if (!input || !output)
{
printf("Error: Failed to allocate device memory!\n");
exit(1);
}
// Write our data set into the input array in device memory
//
err = clEnqueueWriteBuffer(commands, input, CL_TRUE, 0, sizeof(float) * count, data, 0, NULL, NULL);
if (err != CL_SUCCESS)
{
printf("Error: Failed to write to source array!\n");
exit(1);
}
// Set the arguments to our compute kernel
//
err = 0;
err = clSetKernelArg(kernel, 0, sizeof(cl_mem), &input);
err |= clSetKernelArg(kernel, 1, sizeof(cl_mem), &output);
err |= clSetKernelArg(kernel, 2, sizeof(unsigned int), &count);
if (err != CL_SUCCESS)
{
printf("Error: Failed to set kernel arguments! %d\n", err);
exit(1);
}
// Execute the kernel over the entire range of our 1d input data set
// using the maximum number of work group items for this device
//
// global = count;
global = local;
err = clEnqueueNDRangeKernel(commands, kernel, 1, NULL, &global, &local, 0, NULL, NULL);
if (err)
{
printf("Error: Failed to execute kernel!\n");
return EXIT_FAILURE;
}
// Wait for the command commands to get serviced before reading back results
//
clFinish(commands);
// Read back the results from the device to verify the output
//
err = clEnqueueReadBuffer( commands, output, CL_TRUE, 0, sizeof(float) * count, results, 0, NULL, NULL );
if (err != CL_SUCCESS)
{
printf("Error: Failed to read output array! %d\n", err);
exit(1);
}
// Validate our results
//
correct = 0;
for(i = 0; i < count; i++)
{
if((results[i]) == data[i] * data[i])
correct++;
}
// Print a brief summary detailing the results
//
printf("Computed '%d/%d' correct values!\n", correct, count);
// Shutdown and cleanup
//
clReleaseMemObject(input);
clReleaseMemObject(output);
clReleaseProgram(program);
clReleaseKernel(kernel);
clReleaseCommandQueue(commands);
clReleaseContext(context);
return 0;
}