So now i use the AMD stream on my laptop and the compilation works fine and i can start the program but i got the following error and i dont know how i can solve the problem:
Id of the platform: 1
OpenCL demo application started!
clCreateContext
clCreateCommandQueue
clCreateProgramWithSource
Error: Failed to build program executable!
/tmp/OCLSIKDpf.cl(2): warning: explicit type is missing (“int” assumed)
__kernel square(
^
/tmp/OCLSIKDpf.cl(2): error: kernel must return void
__kernel square(
^
1 error detected in the compilation of “/tmp/OCLSIKDpf.cl”.
Best regards
Harald
//
// 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.
//
////////////////////////////////////////////////////////////////////////////////
#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>
////////////////////////////////////////////////////////////////////////////////
// Use a static data size for simplicity
//
#define DATA_SIZE (1024)
////////////////////////////////////////////////////////////////////////////////
// Simple compute kernel which computes the square of an input array
//
const char *KernelSource = "\n" \
"__kernel square( \n" \
" __global float* input, \n" \
" __global float* output, \n" \
" const unsigned int count) \n" \
"{ \n" \
" int i = get_global_id(0); \n" \
" if(i < count) \n" \
" output[i] = input[i] * input[i]; \n" \
"} \n" \
"\n";
////////////////////////////////////////////////////////////////////////////////
int main(int argc, char** argv)
{
int err; // error code returned from api calls
float data[DATA_SIZE]; // original data set given to device
float results[DATA_SIZE]; // results returned from device
unsigned int correct; // number of correct results returned
size_t global; // global domain size for our calculation
size_t local; // local domain size for our calculation
cl_platform_id platform_id;
cl_uint num_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
cl_mem input; // device memory used for the input array
cl_mem output; // device memory used for the output array
// Fill our data set with random float values
//
int i = 0;
unsigned int count = DATA_SIZE;
for(i = 0; i < count; i++)
data[i] = rand() / (float)RAND_MAX;
// Connect to a compute device
//
int gpu = 1;
err = clGetPlatformIDs(1, &platform_id, &num_id);
if(err != CL_SUCCESS)
{
printf("Failed to get the ID of the platform (%i)\n", num_id);
return EXIT_FAILURE;
}
printf("Id of the platform: %i\n",num_id);
err = clGetDeviceIDs(platform_id, CL_DEVICE_TYPE_ALL, 1, &device_id, NULL); // gpu ? CL_DEVICE_TYPE_GPU : CL_DEVICE_TYPE_CPU
if (err != CL_SUCCESS)
{
if(err == CL_INVALID_PLATFORM)
printf("CL_INVALID_PLATFORM\n");
if(err == CL_INVALID_DEVICE_TYPE)
printf("CL_INVALID_DEVICE_TYPE\n");
if(err == CL_INVALID_VALUE)
printf("CL_INVALID_VALUE\n");
if(err == CL_DEVICE_NOT_FOUND)
printf("CL_DEVICE_NOT_FOUND\n");
printf("Error: Failed to create a device group!\n");
return EXIT_FAILURE;
}
printf("\nOpenCL demo application started!\n");
// Create a compute context
//
context = clCreateContext(0, 1, &device_id, NULL, NULL, &err);
if (!context)
{
printf("Error: Failed to create a compute context!\n");
return EXIT_FAILURE;
}
printf("clCreateContext\n");
// Create a command commands
//
commands = clCreateCommandQueue(context, device_id, 0, &err);
if (!commands)
{
printf("Error: Failed to create a command commands!\n");
return EXIT_FAILURE;
}
printf("clCreateCommandQueue\n");
// Create the compute program from the source buffer
//
program = clCreateProgramWithSource(context, 1, (const char **) & KernelSource, NULL, &err);
if (!program)
{
printf("Error: Failed to create compute program!\n");
return EXIT_FAILURE;
}
printf("clCreateProgramWithSource\n");
// Build 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);
}
printf("clBuildProgram\n");
// Create the compute kernel in the program we wish to run
//
kernel = clCreateKernel(program, "square", &err);
if (!kernel || err != CL_SUCCESS)
{
printf("Error: Failed to create compute kernel!\n");
exit(1);
}
printf("clCreateKernel\n");
// Create the input and output arrays in device memory for our calculation
//
input = clCreateBuffer(context, CL_MEM_READ_ONLY, sizeof(float) * count, NULL, NULL);
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);
}
printf("clCreateBuffer\n");
// 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);
}
printf("clEnqueueWriteBuffer\n");
// 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);
}
// Get the maximum work group size for executing the kernel on the device
//
err = clGetKernelWorkGroupInfo(kernel, device_id, CL_KERNEL_WORK_GROUP_SIZE, sizeof(local), &local, NULL);
if (err != CL_SUCCESS)
{
printf("Error: Failed to retrieve kernel work group info! %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;
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;
}