CUDA memory troubles

nvcc text.cu -cubin

__global__ void string_search(char** texts, int* lengths, char* symbol, int* matches, int symbolLength)
{
    int localMatches = 0;
    int blockId = blockIdx.x + blockIdx.y * gridDim.x;
    int threadId = threadIdx.x + threadIdx.y * blockDim.x;
    int blockThreads = blockDim.x * blockDim.y;

    __shared__ int localMatchCounts[32];

    bool breaking = false;
    for(int i = 0; i < (lengths[blockId] - (symbolLength - 1)); i += blockThreads)
    {
    	if(texts[blockId][i] == symbol[0])
    	{
    		for(int j = 1; j < symbolLength; j++)
    		{
    			if(texts[blockId][i + j] != symbol[j])
    			{
    				breaking = true;
    				break;
    			}
    		}
    		if (breaking) continue;
    		localMatches++;
    	}
    }

    localMatchCounts[threadId] = localMatches;

    __syncthreads();

    if(threadId == 0)
    {
        int sum = 0;
        for(int i = 0; i < 32; i++)
        {
            sum += localMatchCounts[i];
        }
        matches[blockId] = sum;
    }
}

localMatchCounts[threadId] = localMatches;

localMatchCounts[threadId] = 5;