dot product of two vectors using reduction

#include <stdio.h>
#include <stdlib.h>

#ifdef APPLE
#include <OpenCL/opencl.h>
#else
#include <CL/cl.h>
#endif

#define MAX_SOURCE_SIZE (0x100000)

int main(void) {
// Create the two input vectors
int i;

int LIST_SIZE = 8;//declaring the size 
int *A = (int*)malloc(sizeof(int)*LIST_SIZE); // Allocating the memory for set A
int *B = (int*)malloc(sizeof(int)*LIST_SIZE); // Allocating the memory for set A

printf("getting the first set

");
for(i = 0; i < LIST_SIZE; i++)
{
A[i] = i;B[i] = i*2;
printf("A[%d]=%d B[%d]=%d
",i,A[i],i,B[i]);

 }



	
// Load the kernel source code into the array source_str
FILE *fp;
char *source_str;
size_t source_size;

fp = fopen("new_kernel.cl", "r");
if (!fp) {
    fprintf(stderr, "Failed to load kernel.

");
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_ALL, 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_ONLY, LIST_SIZE * sizeof(int), NULL, &ret);
cl_mem b_mem_obj = clCreateBuffer(context, CL_MEM_READ_ONLY, LIST_SIZE * sizeof(int), NULL, &ret);
cl_mem c_mem_obj = clCreateBuffer(context, CL_MEM_READ_WRITE,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(int), A, 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, "new", &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);
ret = clSetKernelArg(kernel, 3, sizeof(cl_int), NULL);//local prods array
ret = clSetKernelArg(kernel, 4, sizeof(cl_int), (void *)&LIST_SIZE);


// Execute the OpenCL kernel on the list
size_t global_item_size = LIST_SIZE; // Process the entire lists
size_t local_item_size = 2; // Process in groups of 64
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
 int *C = (int*)malloc(sizeof(int)*LIST_SIZE);
ret = clEnqueueReadBuffer(command_queue, c_mem_obj, CL_TRUE, 0,
        LIST_SIZE * sizeof(int), C, 0, NULL, NULL);

// Display the result to the screen

int val=0;
	
for(i = 0; i &lt; 2; i++)
   {
 val=val+C[i];
   }
printf("value is %d

",val);
// Clean up
ret = clFlush(command_queue);
ret = clFinish(command_queue);
ret = clReleaseKernel(kernel);
ret = clReleaseProgram(program);
ret = clReleaseMemObject(a_mem_obj);
ret = clReleaseMemObject(a_mem_obj);
ret = clReleaseMemObject(c_mem_obj);
ret = clReleaseCommandQueue(command_queue);
ret = clReleaseContext(context);
free(A);
free(B);
freeĀ©;
return 0;
}

kernel function:

_kernel void new(__global int* A, __global int C, __local int cache, int LIST_SIZE){
int tid = get_global_id(0);
int cacheIndex = get_local_id(0);
int blockDim.x = get_local_size(0);
int blockIdx.x = get_group_id(0);
int gridDim.x = get_num_groups(0);

int temp=0;
while(tid&lt;N)
{
	temp+=a[tid] * b[tid];
    tid+= blockDim.x * gridDim.x;
}

cache[cacheIndex] = temp;
barrier(CLK_LOCAL_MEM_FENCE);
int i= blockDim.x/2;
while(i!=0)
{
if(cacheIndex < i)
cache[cacheIndex] += cache[cacheIndex + i];
barrier(CLK_GLOBAL_MEM_FENCE);
i/=2;
}
if(cacheIndex == 0)
C[blockIdx.x] = cache[0];

}

Error:etting the first set
A[0]=0 B[0]=0
A[1]=1 B[1]=2
A[2]=2 B[2]=4
A[3]=3 B[3]=6
A[4]=4 B[4]=8
A[5]=5 B[5]=10
A[6]=6 B[6]=12
A[7]=7 B[7]=14
value is 902153097
Segmentation fault (core dumped)

can you tell me the error

clSetKernelArg(kernel, 3, sizeof(cl_int), NULL) declares the local buffer with a size of sizeof(cl_int) (4 bytes), which is not enough to store more than one integerā€¦