Table 11 Speedups—parallel/sequential in the same platform - II
From: Solving the maximum subsequence sum and related problems using BSP/CGM model and multi-GPU CUDA
n | CS-2 OMP 8T | CS-2 CUDA | CS-1 OMP 12T | CS-1 CUDA |
|---|---|---|---|---|
4GPUs | ||||
220 | 3.348 | 11.893 | 4.292 | 6.344 |
221 | 3.621 | 14.610 | 4.249 | 7.017 |
222 | 3.650 | 16.508 | 4.7322 | 14.030 |
223 | 3.587 | 17.289 | 6.302 | 35.305 |
224 | 3.657 | 17.707 | 6.738 | 66.345 |
225 | 3.658 | 17.817 | 7.117 | 89.454 |
226 | 3.749 | – | 6.679 | 133.460 |
227 | 3.651 | – | 6.104 | 150.070 |
228 | 9.288 | – | 8.014 | 183.489 |
229 | – | – | 5.995 | 208.092 |