View Full Version : program error

10-04-2012, 06:54 AM
//program of vector addition between two array on gpu----------------

#include "stdafx.h"
#include <stdio.h>
#include <stdlib.h>
#include "CL/cl.h"

// OpenCL source code
const char* OpenCLSource[] = {
"__kernel void VectorAdd(__global int* c, __global int* a,__global int* b)",
" // Index of the elements to add \n",
" unsigned int n = get_global_id(0);",
" // Sum the níth element of vectors a and b and store in c \n",
" c[n] = a[n] + b[n];",
// Some interesting data for the vectors
int InitialData1[20] = {37,50,54,50,56,0,43,43,74,71,32,36,16,43,56,100,5 0,25,15,17};
int InitialData2[20] = {35,51,54,58,55,32,36,69,27,39,35,40,16,44,55,14,5 8,75,18,15};
// Number of elements in the vectors to be added
#define SIZE 2048
// Main function
// ************************************************** *******************
int main(void)
// Two integer source vectors in Host memory
int HostVector1[SIZE], HostVector2[SIZE];
// Initialize with some interesting repeating data
for(int c = 0; c < SIZE; c++)
HostVector1[c] = InitialData1[c%20];
HostVector2[c] = InitialData2[c%20];
// Create a context to run OpenCL on our CUDA-enabled NVIDIA GPU
cl_context GPUContext = clCreateContextFromType(0, CL_DEVICE_TYPE_GPU,
// Get the list of GPU devices associated with this context
size_t ParmDataBytes;
clGetContextInfo(GPUContext, CL_CONTEXT_DEVICES, 0, NULL, &ParmDataBytes);
cl_device_id* GPUDevices = (cl_device_id*)malloc(ParmDataBytes);
clGetContextInfo(GPUContext, CL_CONTEXT_DEVICES, ParmDataBytes, GPUDevices, NULL);

// Create a command-queue on the first GPU device
cl_command_queue GPUCommandQueue = clCreateCommandQueue(GPUContext,
GPUDevices[0], 0, NULL);
// Allocate GPU memory for source vectors AND initialize from CPU memory
cl_mem GPUVector1 = clCreateBuffer(GPUContext, CL_MEM_READ_ONLY |
CL_MEM_COPY_HOST_PTR, sizeof(int) * SIZE, HostVector1, NULL);
cl_mem GPUVector2 = clCreateBuffer(GPUContext, CL_MEM_READ_ONLY |
CL_MEM_COPY_HOST_PTR, sizeof(int) * SIZE, HostVector2, NULL);
// Allocate output memory on GPU
cl_mem GPUOutputVector = clCreateBuffer(GPUContext, CL_MEM_WRITE_ONLY,
sizeof(int) * SIZE, NULL, NULL);
// Create OpenCL program with source code
cl_program OpenCLProgram = clCreateProgramWithSource(GPUContext, 7,
OpenCLSource, NULL, NULL);
// Build the program (OpenCL JIT compilation)
clBuildProgram(OpenCLProgram, 0, NULL, NULL, NULL, NULL);
// Create a handle to the compiled OpenCL function (Kernel)
cl_kernel OpenCLVectorAdd = clCreateKernel(OpenCLProgram, "VectorAdd", NULL);
// In the next step we associate the GPU memory with the Kernel arguments
clSetKernelArg(OpenCLVectorAdd, 0, sizeof(cl_mem),(void*)&GPUOutputVector);
clSetKernelArg(OpenCLVectorAdd, 1, sizeof(cl_mem), (void*)&GPUVector1);
clSetKernelArg(OpenCLVectorAdd, 2, sizeof(cl_mem), (void*)&GPUVector2);
// Launch the Kernel on the GPU
size_t WorkSize[1] = {SIZE}; // one dimensional Range
clEnqueueNDRangeKernel(GPUCommandQueue, OpenCLVectorAdd, 1, NULL,
WorkSize, NULL, 0, NULL, NULL);
// Copy the output in GPU memory back to CPU memory
int HostOutputVector[SIZE];
clEnqueueReadBuffer(GPUCommandQueue, GPUOutputVector, CL_TRUE, 0,
SIZE * sizeof(int), HostOutputVector, 0, NULL, NULL);
// Cleanup
// Print out the results
for (int Rows = 0; Rows < (SIZE/20); Rows++, printf("\n")){
for(int c = 0; c <20; c++){
printf("%c",(char)HostOutputVector[Rows * 20 + c]);
return 0;}

10-04-2012, 06:56 AM
this program giving the error CXX0076
on line---------->

cl_command_queue GPUCommandQueue = clCreateCommandQueue(GPUContext,
GPUDevices[0], 0, NULL);

how it can be solved?

10-05-2012, 12:38 AM
Hm the error is not very helpful.

// Includes
#include <stdio.h>
#include <stdlib.h>
#include <stdbool.h>
#include <CL/cl.h>

const char* programSource =
"__kernel \n"
"void vecadd( __global int *A, \n"
" __global int *B, \n"
" __global int *C) \n"
"{ \n"
" int idx = get_global_id(0); \n"
" C[idx] = A[idx] + B[idx]; \n"
"} \n";

int main()
// This code executes on the OpenCL host

// Host Data
int *A = NULL; // Input Array
int *B = NULL; // Input Array
int *C = NULL; // Output Array

// Elements in each array
const int elements = 20;

// compute size of the data
size_t datasize = sizeof(int)*elements;

// Allocate space for input/output data
A = (int*)malloc(datasize);
B = (int*)malloc(datasize);
C = (int*)malloc(datasize);

//initialize the input data
int i;
for (i = 0; i < elements; i++)
A[i] = i;
B[i] = i;

// Use this to check the output of each API call
cl_int status;

cl_uint numPlatforms = 0;
cl_platform_id *platforms = NULL;
cl_uint numDevices = 0;
cl_device_id *devices = 0;
cl_context context = NULL;
cl_command_queue cmdQueue;
cl_kernel kernel = NULL;
cl_program program = NULL;

// Uses to recieve the number of platforms
status = clGetPlatformIDs(0,NULL, &numPlatforms);

// Allocate enough space for each platform
platforms = (cl_platform_id*)malloc(numPlatforms*sizeof(cl_pla tform_id));

// Fill in platforms
status = clGetPlatformIDs(numPlatforms, platforms, NULL);

// Retrieve the number of devices present
status = clGetDeviceIDs(platforms[0], CL_DEVICE_TYPE_ALL, 0, NULL, &numDevices);

// Allocate enough space for each device
devices = (cl_device_id*)malloc(numDevices*sizeof(cl_device_ id));

// Fill in devices
status = clGetDeviceIDs(platforms[0], CL_DEVICE_TYPE_ALL, numDevices, devices, NULL);

// Create a context and associate it with the devices
context = clCreateContext(NULL,numDevices, devices, NULL, NULL, &status);

// Create a command queue and associate it with the device you want to execute on
cmdQueue = clCreateCommandQueue(context,devices[0], 0, &status);

cl_mem bufferA; // Input array on the device
cl_mem bufferB; // Input array on the device
cl_mem bufferC; // Output array on the device

// Create buffer objects that will contain the data from the arrays
bufferA = clCreateBuffer(context, CL_MEM_READ_ONLY, datasize, NULL, &status);
bufferB = clCreateBuffer(context, CL_MEM_READ_ONLY, datasize, NULL, &status);
bufferC = clCreateBuffer(context, CL_MEM_WRITE_ONLY, datasize, NULL, &status);

// Write input arrays to the device buffers
status = clEnqueueWriteBuffer(cmdQueue, bufferA, CL_FALSE, 0, datasize, A, 0, NULL, NULL);
status = clEnqueueWriteBuffer(cmdQueue, bufferB, CL_FALSE, 0, datasize, A, 0, NULL, NULL);

// Create a program
program = clCreateProgramWithSource(context, 1, (const char**)&programSource, NULL, &status);

//Build the program for the devices
status = clBuildProgram(program, numDevices, devices, NULL, NULL, NULL);

// Create kernel from the vector addition function
kernel = clCreateKernel(program, "vecadd", &status);

// Associate the input and output buffers with the kernel
status = clSetKernelArg(kernel, 0, sizeof(cl_mem), &bufferA);
status |= clSetKernelArg(kernel, 1, sizeof(cl_mem), &bufferB);
status |= clSetKernelArg(kernel, 2, sizeof(cl_mem), &bufferC);

// Define an index space (global work size) of work items for execution
// A workgroup size (local work size) is not required but can be used
size_t globalWorkSize[1];

// There are 'elements' work-items
globalWorkSize[0] = elements;

// Execute the kernel
status = clEnqueueNDRangeKernel(cmdQueue, kernel, 1 , NULL, globalWorkSize, NULL, 0, NULL, NULL);

clEnqueueReadBuffer(cmdQueue, bufferC, CL_TRUE, 0, datasize, C, 0 , NULL, NULL);

// Verify the output
bool result = true;

for (i = 0; i < elements; i++)
if(C[i] != i+i)
result = false;

printf("Output is correct\n");
printf("Output is incorrect\n");

int c;
// Print out the results
for (c = 0; c < 20; c++)
printf("%d ", C[c]);

// Free OpenCl resources

// Free host resources

return (0);

Here's my implementation. Runs fine. You can check for the differences. Sorry but i don't have time to do so now. Try to use the build-in OpenCL error code to localize the problem. (I also didn't do this in this implementation)

10-05-2012, 03:47 AM
this error is giving for GPUDevices[0] now i m not getting that what is the problem regarding gpudevices?
if any suggestion

10-05-2012, 04:00 AM
this error is giving for GPUDevices[0] now i m not getting that what is the problem regarding gpudevices?
if any suggestion

OpenCL has its own error codes. Try to use them to figure out whats going wrong.
And compare both sourcecodes to find differences.