OpenCL - Kernel crashes on the second run

OpenCL - Kernel crashes on the second run

I am trying to run a code which works the first time but crashes the
second time that it runs. The function which causes the crash is part of
the class Octree_GPU and is this:
int Octree_GPU::runCreateNodeKernel(int length)
{
cl_uint nodeLength;
if(nodeNumsArray[length-1] == 0)
nodeLength = nodeAddArray[length-1];
else
nodeLength = nodeAddArray[length-1]+8;
nodeArray = (cl_uint*)malloc(sizeof(cl_uint)*nodeLength);
nodePointsArray = (cl_int*)malloc(sizeof(cl_uint)*nodeLength);
startIndexArray = (cl_int*)malloc(sizeof(cl_int)*nodeLength);
d_nodeAdd = clCreateBuffer(context, CL_MEM_READ_WRITE,
sizeof(cl_uint)*length, NULL, &err);
d_nodeArray = clCreateBuffer(context,CL_MEM_READ_WRITE,
sizeof(cl_uint)*temp_length, NULL, &err);
d_numPoints = clCreateBuffer(context, CL_MEM_READ_WRITE,
sizeof(cl_uint)*length, NULL, &err);
d_pointIndex = clCreateBuffer(context,
CL_MEM_READ_WRITE,sizeof(cl_uint)*length,NULL, &err);
d_nodePointsArray = clCreateBuffer(context, CL_MEM_READ_WRITE,
sizeof(cl_int)*temp_length, NULL, &err);
d_nodeIndexArray = clCreateBuffer(context,CL_MEM_READ_WRITE,
sizeof(cl_int)*temp_length, NULL, &err);
err |= clEnqueueWriteBuffer(commands, d_nodeAdd, CL_TRUE, 0,
sizeof(cl_uint)*length, nodeAddArray, 0, NULL,NULL);
err |= clEnqueueWriteBuffer(commands, d_numPoints,CL_TRUE, 0,
sizeof(cl_uint)*length,numPointsArray,0,NULL,NULL);
err |= clEnqueueWriteBuffer(commands, d_pointIndex, CL_TRUE, 0,
sizeof(cl_uint)*length,pointStartIndexArray,0, NULL, NULL);
clFinish(commands);
err = clSetKernelArg(createNodeKernel, 0, sizeof(cl_mem), &d_odata);
err |= clSetKernelArg(createNodeKernel, 1, sizeof(cl_mem),
&d_nodeNums);
err |= clSetKernelArg(createNodeKernel, 2, sizeof(cl_mem), &d_nodeAdd);
err |= clSetKernelArg(createNodeKernel, 3, sizeof(cl_mem),
&d_numPoints);
err |= clSetKernelArg(createNodeKernel, 4, sizeof(cl_mem),
&d_pointIndex);
err |= clSetKernelArg(createNodeKernel, 5, sizeof(cl_mem),
&d_nodeArray);
err |= clSetKernelArg(createNodeKernel, 6, sizeof(cl_mem),
&d_nodePointsArray);
err |= clSetKernelArg(createNodeKernel, 7, sizeof(cl_mem),
&d_nodeIndexArray);
clFinish(commands);
if(err != CL_SUCCESS) {
printf("Cannot set Kernel Arg \n");
exit(1);
}
size_t global_size[1] = {limit-1};
err = clEnqueueNDRangeKernel(commands, createNodeKernel, 1, NULL,
global_size, NULL, 0, NULL, NULL);
if(err != CL_SUCCESS) {
printf(" Kernel does not work \n");
exit(1);
}
clFinish(commands);
err = clEnqueueReadBuffer(commands, d_nodeArray, CL_TRUE, 0,
sizeof(cl_uint)*temp_length, nodeArray, 0, NULL, NULL);
err|= clEnqueueReadBuffer(commands, d_nodePointsArray, CL_TRUE, 0,
sizeof(cl_int)*nodeLength, nodePointsArray, 0, NULL, NULL);
err|= clEnqueueReadBuffer(commands, d_nodeIndexArray, CL_TRUE, 0,
sizeof(cl_int)*nodeLength, startIndexArray, 0, NULL, NULL);
clFinish(commands);
clReleaseMemObject(d_nodeAdd);
clReleaseMemObject(d_numPoints);
clReleaseMemObject(d_nodeArray);
clReleaseMemObject(d_nodePointsArray);
clFinish(commands);
return 0;
}
Please note that d_odata and d_nodeNums have been declared in the previous
functions. The kernel code is given below for the same:
__kernel void createNode(__global int* uniqueCode, __global int*
nodeNums,__global int* nodeAdd, __global int* numPoints, __global int*
pointIndex,__global int* nodeArray, __global int* nodePoints,__global int*
nodeIndex)
{
int ig = get_global_id(0);
int add;
int num = uniqueCode[ig];
int pt = numPoints[ig];
int ind = pointIndex[ig];
int temp,j;
if(nodeNums[ig] == 8)
{
for(int i=0;i<8;i++)
{
temp = ((int)num/10)*10+i;
add = nodeAdd[ig] + i;
nodeArray[add] = temp;
nodePoints[add] = select(0, pt, temp==num);
nodeIndex[add] = select(-1, ind, temp==num);
barrier(CLK_LOCAL_MEM_FENCE);
}
}
else
{
j = num % 10;
nodeAdd[ig] = nodeAdd[ig-1];
add = nodeAdd[ig]+j;
nodePoints[add] = pt;
nodeIndex[add] = ind;
barrier(CLK_LOCAL_MEM_FENCE);
}
}
I have tried to find out why but have not succeeded. I might be
overlooking something really simple. Thank you for your help.