JOCL Char not returning all chars

Question

package parallelencode;

import org.jocl.*;
import static org.jocl.CL.*;

public class ParallelEncode {
    /**
     * The source code of the OpenCL program to execute
     */
    private static String programSource =
        "__kernel void "+
        "sampleKernel(__global const float *a,"+
        "             __global const float *b,"+
        "             __global uchar16 *c,"+
        "             __global char *d)"+
        "{"+
        "    int gid = get_global_id(0);"+
        "    c[gid] = 'q';"+
        "    "+
        "    d[gid] = 'm';"+
        "}";


    /**
     * The entry point of this sample
     * 
     * @param args Not used
     */
    public static void main(String args[])
    {
        // Create input- and output data 
        int n = 17;
        float srcArrayA[] = new float[n];
        float srcArrayB[] = new float[n];
        char dstArray[] = new char[n];
        char charArray[] = new char[n];
        for (int i=0; i<n; i++)
        {
            srcArrayA[i] = i;
            srcArrayB[i] = i;
        }
        Pointer srcA = Pointer.to(srcArrayA);
        Pointer srcB = Pointer.to(srcArrayB); 
        Pointer dst = Pointer.to(dstArray);
        Pointer cArr = Pointer.to(charArray);

        // The platform, device type and device number
        // that will be used
        final int platformIndex = 0;
        final long deviceType = CL_DEVICE_TYPE_ALL;
        final int deviceIndex = 0;

        // Enable exceptions and subsequently omit error checks in this sample
        CL.setExceptionsEnabled(true);

        // Obtain the number of platforms
        int numPlatformsArray[] = new int[1];
        clGetPlatformIDs(0, null, numPlatformsArray);
        int numPlatforms = numPlatformsArray[0];

        // Obtain a platform ID
        cl_platform_id platforms[] = new cl_platform_id[numPlatforms];
        clGetPlatformIDs(platforms.length, platforms, null);
        cl_platform_id platform = platforms[platformIndex];

        // Initialize the context properties
        cl_context_properties contextProperties = new cl_context_properties();
        contextProperties.addProperty(CL_CONTEXT_PLATFORM, platform);

        // Obtain the number of devices for the platform
        int numDevicesArray[] = new int[1];
        clGetDeviceIDs(platform, deviceType, 0, null, numDevicesArray);
        int numDevices = numDevicesArray[0];

        // Obtain a device ID 
        cl_device_id devices[] = new cl_device_id[numDevices];
        clGetDeviceIDs(platform, deviceType, numDevices, devices, null);
        cl_device_id device = devices[deviceIndex];

        // Create a context for the selected device
        cl_context context = clCreateContext(
            contextProperties, 1, new cl_device_id[]{device}, 
            null, null, null);

        // Create a command-queue for the selected device
        cl_command_queue commandQueue = 
            clCreateCommandQueue(context, device, 0, null);

        // Allocate the memory objects for the input- and output data
        cl_mem memObjects[] = new cl_mem[4];
        memObjects[0] = clCreateBuffer(context, 
            CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR,
            Sizeof.cl_float * n, srcA, null);
        memObjects[1] = clCreateBuffer(context, 
            CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR,
            Sizeof.cl_float * n, srcB, null);
        memObjects[2] = clCreateBuffer(context, 
            CL_MEM_READ_WRITE, 
            Sizeof.cl_char * n, null, null);
        memObjects[3] = clCreateBuffer(context, CL_MEM_READ_WRITE, Sizeof.cl_char * n, null, null);

        //char *h_rp = (char*)malloc(length);
        //cl_mem d_rp = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR, length, h_rp, &err);
        //err = clSetKernelArg(ckKernel, 0, sizeof(cl_mem), &d_rp)

        // Create the program from the source code
        cl_program program = clCreateProgramWithSource(context,
            1, new String[]{ programSource }, null, null);

        // Build the program
        clBuildProgram(program, 0, null, null, null, null);

        // Create the kernel
        cl_kernel kernel = clCreateKernel(program, "sampleKernel", null);

        // Set the arguments for the kernel
        clSetKernelArg(kernel, 0, Sizeof.cl_mem, Pointer.to(memObjects[0]));
        clSetKernelArg(kernel, 1, Sizeof.cl_mem, Pointer.to(memObjects[1]));
        clSetKernelArg(kernel, 2, Sizeof.cl_mem, Pointer.to(memObjects[2]));
        clSetKernelArg(kernel, 3, Sizeof.cl_mem, Pointer.to(memObjects[3]));

        // Set the work-item dimensions
        long global_work_size[] = new long[]{n};
        long local_work_size[] = new long[]{1};

        // Execute the kernel
        clEnqueueNDRangeKernel(commandQueue, kernel, 1, null,
            global_work_size, local_work_size, 0, null, null);

        // Read the output data
        clEnqueueReadBuffer(commandQueue, memObjects[2], CL_TRUE, 0,
            n * Sizeof.cl_char, dst, 0, null, null);

        clEnqueueReadBuffer(commandQueue, memObjects[3], CL_TRUE, 0,
                n * Sizeof.cl_char, cArr, 0, null, null);

        // Release kernel, program, and memory objects
        clReleaseMemObject(memObjects[0]);
        clReleaseMemObject(memObjects[1]);
        clReleaseMemObject(memObjects[2]);
        clReleaseMemObject(memObjects[3]);
        clReleaseKernel(kernel);
        clReleaseProgram(program);
        clReleaseCommandQueue(commandQueue);
        clReleaseContext(context);

        System.out.println(java.util.Arrays.toString(dstArray));
        System.out.println(java.util.Arrays.toString(charArray));
    }
}

Result:

[?, ?, ?, ?, ?, ?, ?, ?, q,  ,  ,  ,  ,  ,  ,  ,  ]
[?, ?, ?, ?, ?, ?, ?, ?, m,  ,  ,  ,  ,  ,  ,  ,  ]

Why does it not produce a q for every one in the array, and what are the question marks? I tried changing some things, like the int gid = get_global_id(0); to int gid = get_global_id(1); and the end result was something like [q, , , ...] and [m, , , ...]. Can someone explain this, and how to pass multiple chars as input to an OpenCL kernel?

Answer 1

 int n = 17;

this is okay except for buffer copies.

clEnqueueReadBuffer(commandQueue, memObjects[3], CL_TRUE, 0,
            n * Sizeof.cl_char, cArr, 0, null, null);

this reads 8 and a half char values or 17 bytes. A mismatch between java char (being 2 bytes) and device-side char (1 byte).

Thats why you see correct q at 17th byte or 9th element.

Similar error is made with java bool arrays too.

Also uchar16 means 16 bytes.

    clEnqueueReadBuffer(commandQueue, memObjects[2], CL_TRUE, 0,
        n * Sizeof.cl_char, dst, 0, null, null);

this needs multiplication by 16 unless each element works on all 16 elements. If you have meant 17 elements each 16-bytes, then n*16 should be there and host-side(java) should give array of bytes.

Answer 2

The most important point was already mentioned in the answer by huseyin tugrul buyukisik:

A java char consists of two bytes (16 bits). In C and OpenCL, a char is one byte (8 bits).

It's not entirely clear what your program is supposed to do in the end, but as huseyin also said: I'm pretty sure that you intended to use a char2 instead of char16 (assuming that this will be some UTF16-related program - and otherwise, the host code would not make sense). Also, you seem to have mixed the input- and output arrays somehow.

---

Note:

If you now change this to use uchar2, you may also encounter a limitation of OpenCL: According to the restrictions that are mentioned on the Khronos Website :

Built-in types that are less than 32-bits in size i.e. char, uchar, char2, uchar2, short, ushort, and half have the following restriction:

Writes to a pointer (or arrays) of type char, uchar, char2, uchar2, short, ushort, and half ... are not supported.

---

If you describe more clearly what the program is supposed to do (and drop me a note here, as a comment), I'll try to add a small example that demonstrates how this could be approached.