OV - K-Means scalability clang-O3-ffast-math 100000000

Software Topology

▼Scalability - run_1_thread

Number processes: 1 Number nodes: 1 Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_WAIT_POLICY: activeOMP_NUM_THREADS: 1OMP_PLACES: cores

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node skylake+	1	1	338.12
►Process 680206+		1	338.12
○Thread 680206			338.12	340.88	99.19	0.00	0.00	248.06

▶Scalability - run_2_threads

Number processes: 1 Number nodes: 1 Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_PLACES: coresOMP_NUM_THREADS: 2OMP_WAIT_POLICY: active

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node skylake+	1	2	245.97
►Process 680309+		2	245.97
○Thread 680309			245.97	293.77	83.73	0.00	0.00	199.53
○Thread 680371			201.45	201.45	100.00	92.32	0.00	199.53

▶Scalability - run_4_threads

Number processes: 1 Number nodes: 1 Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_PLACES: coresOMP_NUM_THREADS: 4OMP_WAIT_POLICY: active

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node skylake+	1	4	129.85
►Process 680398+		4	129.85
○Thread 680398			129.85	199.97	64.93	0.00	0.00	106.60
○Thread 680462			107.58	107.58	100.00	92.39	0.00	106.60
○Thread 680463			107.58	107.58	100.00	92.39	0.00	106.59
○Thread 680464			107.57	107.57	100.00	92.39	0.00	106.59

▶Scalability - run_8_threads

Number processes: 1 Number nodes: 1 Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_PLACES: coresOMP_NUM_THREADS: 8OMP_WAIT_POLICY: active

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node skylake+	1	8	62.71
►Process 680487+		8	62.71
○Thread 680487			62.71	143.84	43.59	0.00	0.00	51.09
○Thread 680550			51.59	51.59	100.00	92.25	0.00	51.10
○Thread 680551			51.59	51.59	100.00	92.25	0.00	51.10
○Thread 680552			51.59	51.59	100.00	92.25	0.00	51.10
○Thread 680553			51.59	51.59	100.00	92.25	0.00	51.10
○Thread 680554			51.59	51.59	100.00	92.25	0.00	51.10
○Thread 680555			51.59	51.59	100.00	92.25	0.00	51.09
○Thread 680556			51.59	51.59	100.00	92.25	0.00	51.09

▶Scalability - run_16_threads

Number processes: 1 Number nodes: 1 Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_PLACES: coresOMP_NUM_THREADS: 16OMP_WAIT_POLICY: active

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node skylake+	1	16	31.04
►Process 680574+		16	31.04
○Thread 680574			31.04	117.82	26.35	0.00	0.00	25.29
○Thread 680636			25.56	25.56	100.00	92.26	0.00	25.31
○Thread 680637			25.56	25.56	100.00	92.26	0.00	25.29
○Thread 680638			25.56	25.56	100.00	92.26	0.00	25.29
○Thread 680639			25.56	25.56	100.00	92.26	0.00	25.29
○Thread 680640			25.56	25.56	100.00	92.26	0.00	25.29
○Thread 680641			25.55	25.55	100.00	92.26	0.00	25.29
○Thread 680642			25.55	25.55	100.00	92.27	0.00	25.29
○Thread 680643			25.55	25.55	100.00	92.27	0.00	25.29
○Thread 680644			25.55	25.55	100.00	92.27	0.00	25.29
○Thread 680645			25.55	25.55	100.00	92.27	0.00	25.29
○Thread 680646			25.55	25.55	100.00	92.27	0.00	25.29
○Thread 680647			25.55	25.55	100.00	92.27	0.00	25.29
○Thread 680648			25.55	25.55	100.00	92.27	0.00	25.29
○Thread 680649			25.55	25.55	100.00	92.27	0.00	25.29
○Thread 680650			25.54	25.54	100.00	92.27	0.00	25.29

▶Scalability - run_26_threads

Number processes: 1 Number nodes: 1 Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_PLACES: coresOMP_NUM_THREADS: 26OMP_WAIT_POLICY: active

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node skylake+	1	26	18.86
►Process 680667+		26	18.86
○Thread 680667			18.86	108.03	17.46	0.00	0.00	15.56
○Thread 680732			15.75	15.75	100.00	92.28	0.00	15.59
○Thread 680733			15.75	15.75	100.00	92.28	0.00	15.56
○Thread 680734			15.75	15.75	100.00	92.28	0.00	15.57
○Thread 680735			15.75	15.75	100.00	92.28	0.00	15.56
○Thread 680736			15.74	15.74	100.00	92.29	0.00	15.57
○Thread 680737			15.74	15.74	100.00	92.29	0.00	15.56
○Thread 680738			15.74	15.74	100.00	92.29	0.00	15.56
○Thread 680739			15.74	15.74	100.00	92.29	0.00	15.56
○Thread 680740			15.74	15.74	100.00	92.29	0.00	15.57
○Thread 680741			15.74	15.74	100.00	92.29	0.00	15.56
○Thread 680742			15.74	15.74	100.00	92.29	0.00	15.56
○Thread 680743			15.74	15.74	100.00	92.29	0.00	15.57
○Thread 680744			15.74	15.74	100.00	92.29	0.00	15.56
○Thread 680745			15.73	15.73	100.00	92.30	0.00	15.56
○Thread 680746			15.73	15.73	100.00	92.30	0.00	15.57
○Thread 680747			15.73	15.73	100.00	92.30	0.00	15.56
○Thread 680748			15.73	15.73	100.00	92.30	0.00	15.56
○Thread 680749			15.73	15.73	100.00	92.30	0.00	15.57
○Thread 680750			15.73	15.73	100.00	92.30	0.00	15.56
○Thread 680751			15.73	15.73	100.00	92.30	0.00	15.56
○Thread 680752			15.73	15.73	100.00	92.30	0.00	15.56
○Thread 680753			15.73	15.73	100.00	92.30	0.00	15.57
○Thread 680754			15.72	15.72	100.00	92.31	0.00	15.57
○Thread 680755			15.72	15.72	100.00	92.31	0.00	15.57
○Thread 680756			15.72	15.72	100.00	92.31	0.00	15.56