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
|
package com.jogamp.opencl.demos.hellojocl;
import com.jogamp.opencl.CLBuffer;
import com.jogamp.opencl.CLCommandQueue;
import com.jogamp.opencl.CLContext;
import com.jogamp.opencl.CLDevice;
import com.jogamp.opencl.CLKernel;
import com.jogamp.opencl.CLProgram;
import java.io.IOException;
import java.nio.FloatBuffer;
import java.util.Random;
import static java.lang.System.*;
import static com.jogamp.opencl.CLMemory.Mem.*;
import static java.lang.Math.*;
/**
* Hello Java OpenCL example. Adds all elements of buffer A to buffer B
* and stores the result in buffer C.<p>
* Sample was inspired by the Nvidia VectorAdd example written in C/C++
* which is bundled in the Nvidia OpenCL SDK.
* @author Michael Bien
*/
public class HelloJOCL {
public static void main(String[] args) throws IOException {
// set up (uses default CLPlatform and creates context for all devices)
CLContext context = CLContext.create();
out.println("created "+context);
// always make sure to release the context under all circumstances
// not needed for this particular sample but recommented
try{
// select fastest device
CLDevice device = context.getMaxFlopsDevice();
out.println("using "+device);
// create command queue on device.
CLCommandQueue queue = device.createCommandQueue();
int elementCount = 1444477; // Length of arrays to process
int localWorkSize = min(device.getMaxWorkGroupSize(), 256); // Local work size dimensions
int globalWorkSize = roundUp(localWorkSize, elementCount); // rounded up to the nearest multiple of the localWorkSize
// load sources, create and build program
CLProgram program = context.createProgram(HelloJOCL.class.getResourceAsStream("VectorAdd.cl")).build();
// A, B are input buffers, C is for the result
CLBuffer<FloatBuffer> clBufferA = context.createFloatBuffer(globalWorkSize, READ_ONLY);
CLBuffer<FloatBuffer> clBufferB = context.createFloatBuffer(globalWorkSize, READ_ONLY);
CLBuffer<FloatBuffer> clBufferC = context.createFloatBuffer(globalWorkSize, WRITE_ONLY);
out.println("used device memory: "
+ (clBufferA.getCLSize()+clBufferB.getCLSize()+clBufferC.getCLSize())/1000000 +"MB");
// fill input buffers with random numbers
// (just to have test data; seed is fixed -> results will not change between runs).
fillBuffer(clBufferA.getBuffer(), 12345);
fillBuffer(clBufferB.getBuffer(), 67890);
// get a reference to the kernel function with the name 'VectorAdd'
// and map the buffers to its input parameters.
CLKernel kernel = program.createCLKernel("VectorAdd");
kernel.putArgs(clBufferA, clBufferB, clBufferC).putArg(elementCount);
// asynchronous write of data to GPU device,
// followed by blocking read to get the computed results back.
long time = nanoTime();
queue.putWriteBuffer(clBufferA, false)
.putWriteBuffer(clBufferB, false)
.put1DRangeKernel(kernel, 0, globalWorkSize, localWorkSize)
.putReadBuffer(clBufferC, true);
time = nanoTime() - time;
// print first few elements of the resulting buffer to the console.
out.println("a+b=c results snapshot: ");
for(int i = 0; i < 10; i++)
out.print(clBufferC.getBuffer().get() + ", ");
out.println("...; " + clBufferC.getBuffer().remaining() + " more");
out.println("computation took: "+(time/1000000)+"ms");
}finally{
// cleanup all resources associated with this context.
context.release();
}
}
private static void fillBuffer(FloatBuffer buffer, int seed) {
Random rnd = new Random(seed);
while(buffer.remaining() != 0)
buffer.put(rnd.nextFloat()*100);
buffer.rewind();
}
private static int roundUp(int groupSize, int globalSize) {
int r = globalSize % groupSize;
if (r == 0) {
return globalSize;
} else {
return globalSize + groupSize - r;
}
}
}
|
