Table 3.
Runtime Performance of svmPRAT on the Disorder Dataset (in seconds).
| w = f = 11 | w = f = 13 | w = f = 15 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| #KER | NO | YES | SP | #KER | NO | YES | SP | #KER | NO | YES | SP | |
 |
1.93e+10 | 83993 | 45025 | 1.86 | 1.92e+10 | 95098 | 53377 | 1.78 | 1.91e+10 | 106565 | 54994 | 1.93 |
 |
1.91e+10 | 79623 | 36933 | 2.15 | 1.88e+10 | 90715 | 39237 | 2.31 | 1.87e+10 | 91809 | 39368 | 2.33 |
 |
2.01e+10 | 99501 | 56894 | 1.75 | 2.05e+10 | 112863 | 65035 | 1.73 | 2.04e+10 | 125563 | 69919 | 1.75 |
The runtime performance of svmPRAT was benchmarked for learning a classification model on a 64-bit Intel Xeon CPU 2.33 GHz processor. #KER denotes the number of kernel evaluations for training the SVM model. NO denotes runtime in seconds when the CBLAS library was not used, YES denotes the runtime in seconds when the CBLAS library was used, and SP denotes the speedup achieved using the CBLAS library.