| unoptimized mode at 8192x4096 |
| matrix1d |
2.53 |
134217744 |
5.3 |
27.63 |
| matrix2d |
0.82 |
134316044 |
8.13 |
33.59 |
| matrix2das1d |
1.25 |
134250524 |
4.29 |
27.3 |
| matrix2das1d_shimpl |
1.25 |
134250524 |
4.33 |
27.17 |
| matrix1d_static |
0.8 |
134217728 |
1.26 |
24 |
| matrix2d_static |
0.8 |
134217728 |
1.69 |
24.11 |
| matrix2das1d_static |
0 |
134250496 |
1.54 |
24.34 |
| matrix2das1d_shimpl_static |
0 |
134250496 |
1.57 |
24.4 |
| optimized mode at 8192x4096 |
| matrix1d |
0.96 |
134217744 |
0.74 |
23.28 |
| matrix2d |
0.81 |
134316044 |
0.5 |
26.34 |
| matrix2das1d |
0.82 |
134250524 |
0.5 |
23.59 |
| matrix2das1d_shimpl |
0.81 |
134250524 |
0.49 |
23.63 |
| matrix1d_static |
0.79 |
134217728 |
0.5 |
22.86 |
| matrix2d_static |
0.8 |
134217728 |
0.5 |
22.88 |
| matrix2das1d_static |
0 |
134250496 |
1 |
23.55 |
| matrix2das1d_shimpl_static |
0 |
134250496 |
1.02 |
23.49 |