(ms) | (μs) |
| Execution Time (ms) | ||||
Sequential | OpenMP-HSW | OpenMP-KNL | OpenACC-GPU | CUDA-GPU | |||
10 | 100 | 2560 | 40.786 | 2.573 | 2.209 | 2.233 | 1.875 |
5 | 50 | 5120 | 72.57 | 4.553 | 4.425 | 3.04 | 2.728 |
2 | 20 | 12,800 | 159.665 | 8.621 | 11.052 | 6.144 | 5.043 |
1 | 10 | 25,600 | 289.96 | 15.972 | 22.02 | 13.395 | 9.714 |