4

1000

42.60

42.61

42.61

8

1000

45.14

45.14

45.14

16

1000

42.83

42.84

42.84

32

1000

46.46

46.46

46.46

64

1000

44.62

44.63

44.62

128

1000

58.27

58.29

58.28

256

1000

61.13

61.15

61.15

512

1000

70.58

70.60

70.60

1024

1000

81.64

81.66

81.65

2048

1000

113.24

113.29

113.27

4096

1000

158.73

158.80

158.78

8192

1000

296.67

296.83

296.78

16384

1000

534.17

534.48

534.39

32768

1000

925.54

926.11

925.76

65536

640

1643.30

1644.20

1643.76

131072

320

1211.07

1211.61

1211.35

262144

160

2377.06

2379.35

2378.28

524288

80

9937.20

9945.09

9941.42

1048576

40

14141.08

14171.55

14157.80

2097152

20

23278.50

23407.60

23348.72

4194304

10

41601.71

42125.80

41887.28

Stream

This is sample output of a Stream test on a cluster of 349 nodes.

Running Memory Benchmark

 

 

 

node1: -------------------------------------------------------------

 

 

 

node1: This system uses 8 bytes per DOUBLE PRECISION word.

 

node1: -------------------------------------------------------------

 

 

 

node1: Array size = 44739242, Offset = 0

 

 

node1: Total memory required = 1024.0 MB.

 

 

node1: Each test is run 25 times, but only

 

 

node1: the *best* time for each is used.

 

 

node1: Function

Rate (MB/s)

Avg time

Min time

Max time

node1: Copy:

2679.4987

0.2566

0.2671

0.2675

node1: Scale:

2606.1366

0.2640

0.2747

0.2776

node1: Add:

3090.3320

0.3339

0.3475

0.3507

node1: Triad:

3086.9809

0.3342

0.3478

0.3488

node1: -------------------------------------------------------------

 

 

 

node1: Solution Validates

 

 

 

node1: -------------------------------------------------------------

 

 

 

node9: -------------------------------------------------------------

 

 

 

node9: This system uses 8 bytes per DOUBLE PRECISION word.

 

node9: -------------------------------------------------------------

 

 

 

node9: Array size = 44739242, Offset = 0

 

 

node9: Total memory required = 1024.0 MB.

 

 

node9: Each test is run 25 times, but only

 

 

node9: the *best* time for each is used.

 

 

node9: Function

Rate (MB/s)

Avg time

Min time

Max time

node9: Copy:

2672.2059

0.2582

0.2679

0.2714

node9: Scale:

2605.7793

0.2648

0.2747

0.2781

node9: Add:

3095.3829

0.3345

0.3469

0.3518

node9: Triad:

3093.9731

0.3348

0.3470

0.3522

node9: -------------------------------------------------------------

 

 

 

node9: Solution Validates

 

 

 

node9: -------------------------------------------------------------

 

 

 

node24: -------------------------------------------------------------

 

 

 

node24: This system uses 8 bytes per DOUBLE PRECISION word.

 

node24: -------------------------------------------------------------

 

 

 

node24: Array size = 44739242, Offset = 0

 

 

node24: Total memory required = 1024.0 MB.

 

 

node24: Each test is run 25 times, but only

 

 

node24: the *best* time for each is used.

 

 

node24: Function

Rate (MB/s)

Avg time

Min time

Max time

node24: Copy:

2662.2282

0.2587

0.2689

0.2725

node24: Scale:

2599.2867

0.2649

0.2754

0.2786

node24: Add:

3081.9215

0.3353

0.3484

0.3533

Stream 65