How to read-modify-write threads in blocks differents

Accelerated Computing CUDA CUDA Programming and Performance
1 
typedef struct {
     char ItemId[MAX_STR_SIZE];
    cuda_int indexArrayMap;
    cuda_int suporte;
} Elo;

int new_canditatos_cont_suporte_size = 0;
        for (int i = 0; i < index_elo_put; ++i) {
            int index = 0;
            bool newFlag = true;
            while (newFlag) {
                if (0 == compare(new_canditatos_cont_suporte[index].ItemId, "")) {
                	new_canditatos_cont_suporte_size++;
                	my_strcpy(new_canditatos_cont_suporte[index].ItemId,new_canditatos[i]->ItemId);
                	new_canditatos_cont_suporte[index].indexArrayMap = new_canditatos[i]->indexArrayMap;
                	new_canditatos_cont_suporte[index].suporte = new_canditatos[i]->suporte;
                    newFlag = false;
                } else if (0 == compare(new_canditatos_cont_suporte[index].ItemId, new_canditatos[i]->ItemId)) {
                	new_canditatos_cont_suporte[index].suporte += new_canditatos[i]->suporte;
                    newFlag = false;
                } else {
                    index++;
                }
            }
        }

The threads access the first position of the new support canditates and add their values ​​at the same time. I would like a barrier something of the genre.