JOCL Tutorial - Revision history

Xranby: /* Online JogAmp JOGL tutorials and papers */

2013-07-16T19:41:16Z

Online JogAmp JOGL tutorials and papers

← Older revision		Revision as of 21:41, 16 July 2013
Line 1:		Line 1:
	== Online JogAmp JOGL tutorials and papers ==		== Online JogAmp JOGL tutorials and papers ==

	* http://e-archivo.uc3m.es/bitstream/10016/17183/5/finalversionPFC_Raquel_Medina.pdf - paper: Evaluating different Java bindings for #OpenCL. #Jogamp vs #Jocl vs #Javacl		* http://e-archivo.uc3m.es/bitstream/10016/17183/5/finalversionPFC_Raquel_Medina.pdf - paper: Evaluating different Java bindings for #OpenCL. #Jogamp.jocl vs #Jocl vs #Javacl
	** This paper show JogAmp JOCL IDE setup and usage.		** This paper show JogAmp JOCL IDE setup and usage.

Xranby at 19:40, 16 July 2013

2013-07-16T19:40:50Z

← Older revision		Revision as of 21:40, 16 July 2013
Line 1:		Line 1:
	Hello JOCL host program:		== Online JogAmp JOGL tutorials and papers ==

			* http://e-archivo.uc3m.es/bitstream/10016/17183/5/finalversionPFC_Raquel_Medina.pdf - paper: Evaluating different Java bindings for #OpenCL. #Jogamp vs #Jocl vs #Javacl
			** This paper show JogAmp JOCL IDE setup and usage.

			== Hello JOCL host program: ==
	<pre>		<pre>
	package com.jogamp.opencl.demos.hellojocl;		package com.jogamp.opencl.demos.hellojocl;

Mbien at 21:53, 18 February 2011

2011-02-18T21:53:32Z

← Older revision		Revision as of 23:53, 18 February 2011
Line 109:		Line 109:

	}		}
			</pre>


			Hello JOCL Kernel:

			<pre>
			// OpenCL Kernel Function for element by element vector addition
			kernel void VectorAdd(global const float* a, global const float* b, global float* c, int numElements) {

			// get index into global data array
			int iGID = get_global_id(0);

			// bound check, equivalent to the limit on a 'for' loop
			if (iGID >= numElements) {
			return;
			}

			// add the vector elements
			c[iGID] = a[iGID] + b[iGID];
			}
	</pre>		</pre>

Mbien: updated sourcecode

2011-02-12T20:11:04Z

updated sourcecode

Show changes

Mbien: moved hello world from faq to tutorial

2010-04-25T14:36:02Z

moved hello world from faq to tutorial

New page

Hello JOCL host program:
<pre>
import com.jogamp.opencl.*;
import java.io.IOException;
import java.nio.FloatBuffer;
import java.util.Random;

import static java.lang.System.*;
import static com.jogamp.opencl.CLMemory.Mem.*;

/**
* Hello Java OpenCL example. Adds all elements of buffer A to buffer B
* and stores the result in buffer C.<br/>
* 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 {

int elementCount = 11444777; // Length of arrays to process
int localWorkSize = 256; // Local work size
int globalWorkSize = roundUp(localWorkSize, elementCount); // rounded up to the nearest multiple of the localWorkSize

// set up
CLContext context = CLContext.create();
CLProgram program = context.createProgram(HelloJOCL.class.getResourceAsStream("VectorAdd.cl")).build();

CLBuffer<FloatBuffer> clBufferA = context.createFloatBuffer(globalWorkSize, READ_ONLY);
CLBuffer<FloatBuffer> clBufferB = context.createFloatBuffer(globalWorkSize, READ_ONLY);
CLBuffer<FloatBuffer> clBufferC = context.createFloatBuffer(globalWorkSize, WRITE_ONLY);

// fill read buffers with random numbers.
fillBuffer(clBufferA.getBuffer(), 12345);
fillBuffer(clBufferB.getBuffer(), 67890);

// get a reference to the kernel functon with the name 'VectorAdd'
// and map the buffers to its input parameters.
CLKernel kernel = program.createCLKernel("VectorAdd");
kernel.putArgs(clBufferA, clBufferB, clBufferC).putArg(elementCount);

// create command queue on fastest device.
CLCommandQueue queue = context.getMaxFlopsDevice().createCommandQueue();

// asynchronous write of data to GPU device,
// blocking read later 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;

// cleanup all resources associated with this context.
context.release();

// 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");
}

/* utilities */
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;
}
}
</pre>
Hello JOCL Kernel:
<pre>
// OpenCL Kernel Function for element by element vector addition
kernel void VectorAdd(global const float* a, global const float* b, global float* c, int numElements) {

// get index into global data array
int iGID = get_global_id(0);

// bound check, equivalent to the limit on a 'for' loop
if (iGID >= numElements) {
return;
}

// add the vector elements
c[iGID] = a[iGID] + b[iGID];
}
</pre>