batching them a minor change

preprocessing/p2preprocessing.cpp

@@ -136,19 +136,19 @@ int main(int argc, char* argv[])
 
 
 
-	__m128i ** output0 = (__m128i ** ) malloc(sizeof(__m128i *) * n_threads);
-	int8_t  ** flags0  = (int8_t ** ) malloc(sizeof(uint8_t *) * n_threads);
+	__m128i ** output0 = (__m128i ** ) malloc(sizeof(__m128i *) * thread_per_batch);
+	int8_t  ** flags0  = (int8_t ** ) malloc(sizeof(uint8_t *) * thread_per_batch);
 	 
-	for(size_t j = 0; j < n_threads; ++j)
+	for(size_t j = 0; j < thread_per_batch; ++j)
 	{
 		output0[j] = (__m128i *)std::aligned_alloc(sizeof(node_t), db_nitems * sizeof(__m128i));
 		flags0[j]  = (int8_t *)std::aligned_alloc(sizeof(node_t), db_nitems * sizeof(uint8_t));
 	}
   
-	__m128i ** output1 = (__m128i ** ) malloc(sizeof(__m128i *) * n_threads);
-	int8_t  ** flags1  = (int8_t ** ) malloc(sizeof(uint8_t *) * n_threads);
+	__m128i ** output1 = (__m128i ** ) malloc(sizeof(__m128i *) * thread_per_batch);
+	int8_t  ** flags1  = (int8_t ** ) malloc(sizeof(uint8_t *) * thread_per_batch);
 	 
-	for(size_t j = 0; j < n_threads; ++j)
+	for(size_t j = 0; j < thread_per_batch; ++j)
 	{
 		output1[j] = (__m128i *)std::aligned_alloc(sizeof(node_t), db_nitems * sizeof(__m128i));
 		flags1[j]  = (int8_t *)std::aligned_alloc(sizeof(node_t), db_nitems * sizeof(uint8_t));