Handling Big Data Scalability in Biological Domain Using Parallel and Distributed Processing: A Case of Three Biological Semantic Similarity Measures

Table 8

Average time obtained using a distributed system (2, 3, and 4 slaves) with Enhanced Resnik and input data divided equally.

Sample Size	Original Resnik Average Time (ns)	Threaded Resnik Average Time (ns) (Input Data Divided Equally)			% Threaded Resnik Average Time (Input Data Divided Equally) vs. Original Resnik Average Time
		2 Slaves	3 Slaves	4 Slaves	2 Slaves	3 Slaves	4 Slaves
10	56515	3.80E+08	1.48E+05	1.07E+10	672287.86	161.88	18932926.63
100	26184.94949	7.14E+04	2.90E+05	6.70E+08	172.68	1007.51	2558621.76
1000	27907.82082	3.36E+04	2.65E+04	6.46E+07	20.40	-5.04	231376.33
10000	16287.9895	1.92E+04	1.61E+04	6.45E+06	17.88	-1.15	39499.73
100000	11844.26883	7.20E+03	1.15E+04	6.56E+05	-39.21	-2.91	5438.54
1000000	8273.153824	4.31E+03	7.10E+03	7.15E+04	-47.90	-14.18	764.24
Average	24502.19708	6.34E+07	8.32E+04	1.91E+09	112068.62	191.02	3628104.54