i m trying to write opencl program for sorting.........i m having code which i have posted below.......can anyone tell me why it is showing wrong output.....
Host code:
#include <stdio.h>
#include <stdlib.h>
#include <iostream>
#include<time.h>
#ifdef __APPLE__
#include <OpenCL/opencl.h>
#else
#include <CL/cl.h>
#endif
#define MAX_SOURCE_SIZE (0x100000)
double timeDifference = 0;
struct timespec start, stop;
long int size=256;
//#define LIST_SIZE 1024
using namespace std;
float * copy(float c[],long int list_size)
{
int i;
/* for(i=0;i<list_size;i++)
{
printf(" %f",c);
}*/
// int *A = (int*)malloc(sizeof(int)*(list_size));
float *B = (float*)malloc(sizeof(float)*(list_size));
// int *C = (int*)malloc(sizeof(int)*(list_size/2));
// Load the kernel source code into the array source_str
FILE *fp;
char *source_str;
size_t source_size;
cout<<"\n"<<"array in opencl program"<<"\n";
for(i=0;i<list_size-200;i++)
{
printf(" %f",c);
}
fp = fopen("sorting_array_kernel1.cl", "r");
if (!fp) {
fprintf(stderr, "Failed to load kernel.\n");
exit(1);
}
source_str = (char*)malloc(MAX_SOURCE_SIZE);
source_size = fread( source_str, 1, MAX_SOURCE_SIZE, fp);
fclose( fp );
// Get platform and device information
cl_platform_id platform_id = NULL;
cl_device_id device_id = NULL;
cl_uint ret_num_devices;
cl_uint ret_num_platforms;
cl_int ret = clGetPlatformIDs(1, &platform_id, &ret_num_platforms);
ret = clGetDeviceIDs( platform_id, CL_DEVICE_TYPE_GPU, 1,
&device_id, &ret_num_devices);
// Create an OpenCL context
cl_context context = clCreateContext( NULL, 1, &device_id, NULL, NULL, &ret);
// Create a command queue
cl_command_queue command_queue = clCreateCommandQueue(context, device_id, 0, &ret);
// Create memory buffers on the device for each vector
cl_mem a_mem_obj = clCreateBuffer(context, CL_MEM_READ_WRITE,
(list_size) * sizeof(float), NULL, &ret);
cl_mem b_mem_obj = clCreateBuffer(context, CL_MEM_READ_WRITE,
(list_size) * sizeof(float), NULL, &ret);
// cl_mem c_mem_obj = clCreateBuffer(context, CL_MEM_WRITE_ONLY,
// (list_size) * sizeof(int), NULL, &ret);
// Copy the lists A and B to their respective memory buffers
ret = clEnqueueWriteBuffer(command_queue, a_mem_obj, CL_TRUE, 0,
(list_size) * sizeof(float), c, 0, NULL, NULL);
//ret = clEnqueueWriteBuffer(command_queue, b_mem_obj, CL_TRUE, 0,
// (list_size) * sizeof(int), B, 0, NULL, NULL);
// Create a program from the kernel source
cl_program program = clCreateProgramWithSource(context, 1,
(const char **)&source_str, (const size_t *)&source_size, &ret);
// Build the program
ret = clBuildProgram(program, 1, &device_id, NULL, NULL, NULL);
// Create the OpenCL kernel
cl_kernel kernel = clCreateKernel(program, "vector_add", &ret);
// Set the arguments of the kernel
ret = clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *)&a_mem_obj);
ret = clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *)&b_mem_obj);
// ret = clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *)&c_mem_obj);
clock_gettime(CLOCK_REALTIME, &start);
// Execute the OpenCL kernel on the list
size_t global_item_size = (list_size); // Process the entire lists
size_t local_item_size = 256; // Divide work items into groups of 512
ret = clEnqueueNDRangeKernel(command_queue, kernel, 1, NULL,
&global_item_size, &local_item_size, 0, NULL, NULL);
// Read the memory buffer C on the device to the local variable C
ret = clEnqueueReadBuffer(command_queue, b_mem_obj, CL_TRUE, 0,
(list_size) * sizeof(float), B, 0, NULL, NULL);
cout<<"\n"<<"array in opencl program"<<"\n";
// Display the result to the screen
for(i = 0; i <list_size-200; i++)
printf(" %f",B);
clock_gettime(CLOCK_REALTIME, &stop);
timeDifference += (double) (stop.tv_sec - start.tv_sec)
+ (double) (stop.tv_nsec - start.tv_nsec) / 1000000000;
//printf("\nsum of array %d\n",sum);
//getchar();
// Clean up
ret = clFlush(command_queue);
ret = clFinish(command_queue);
ret = clReleaseKernel(kernel);
ret = clReleaseProgram(program);
ret = clReleaseMemObject(a_mem_obj);
ret = clReleaseMemObject(b_mem_obj);
// ret = clReleaseMemObject(c_mem_obj);
ret = clReleaseCommandQueue(command_queue);
ret = clReleaseContext(context);
// free(A);
// free(B);
return B;
}
int main()
{
int i;
float *c = (float*)malloc(sizeof(float)*(size));float *f;
for(i=0;i<size;i++)
{
c=256-i;
}
for(i=0;i<size-200;i++)
{
printf(" %f",c);
}
cout<<"array before sorting.................."<<"/n";
f=copy(c,size);
cout<<"\n";
for(i=0;i<size-200;i++)
{
printf(" %f",f);
}
cout << "parallel Total Required Time:" << timeDifference << endl;
return 0;
}
Kernel code:
__kernel void ParallelSelection(__global const data_t * in,__global data_t * out)
{
int i = get_global_id(0); // current thread
int n = get_global_size(0); // input size
data_t iData = in;
uint iKey = keyValue(iData);
// Compute position of in in output
int pos = 0;
for (int j=0;j<n;j++)
{
uint jKey = keyValue(in); // broadcasted
bool smaller = (jKey < iKey) || (jKey == iKey && j < i); // in < in ?
pos += (smaller)?1:0;
}
out[pos] = iData;
}
will be a great help........if anyone reply soon.....