Parallelization 11

Speedup: 3.754 (27.790s / 7.410s) on 8 cores | Distortion: 0.000000 (bound 0.003) | Total Run Time: 318.643s

Transformation

Loop Parallelization Privatization Scheduling Synchronization Replication
barnes.C:1383 (94.3%) p static
barnes.C:499 (2.38%) velsq, m, p static barnes.C:504 (addval => addvalRepl) barnes.C:510,524,527,530 (vecAdd => vecAddRepl) barnes.C:517,521 (matAdd => matAddRepl)

Metrics

Run Run Time (s) Speedup Distortion
1 7.491 3.710 0.000000
2 7.381 3.765 0.000000
3 7.431 3.740 0.000000
4 7.331 3.791 0.000000
5 7.341 3.786 0.000000
6 7.311 3.801 0.000000
7 7.351 3.781 0.000000
8 7.331 3.791 0.000000
9 7.561 3.676 0.000000
10 7.331 3.791 0.000000
11 7.361 3.776 0.000000
12 7.331 3.791 0.000000
13 7.591 3.661 0.000000
14 7.301 3.807 0.000000
15 7.311 3.801 0.000000
16 7.311 3.801 0.000000
17 7.571 3.671 0.000000
18 7.321 3.796 0.000000
19 7.381 3.765 0.000000
20 7.331 3.791 0.000000
21 7.341 3.786 0.000000
22 7.321 3.796 0.000000
23 7.311 3.801 0.000000
24 7.311 3.801 0.000000
25 7.521 3.695 0.000000
26 7.311 3.801 0.000000
27 7.411 3.750 0.000000
28 7.431 3.740 0.000000
29 7.321 3.796 0.000000
30 7.311 3.801 0.000000
31 7.541 3.685 0.000000
32 7.321 3.796 0.000000
33 7.501 3.705 0.000000
34 8.941 3.108 0.000000
35 7.341 3.786 0.000000
36 7.311 3.801 0.000000
37 7.321 3.796 0.000000
38 7.311 3.801 0.000000
39 7.301 3.807 0.000000
40 7.301 3.807 0.000000
41 7.611 3.652 0.000000
42 7.301 3.807 0.000000
43 7.301 3.807 0.000000
Avg. 7.410 3.754 0.000000
Back