Table 6 Performance comparison among SW implementations using the large set
From: SWIFOLD: Smith-Waterman implementation on FPGA with OpenCL for long DNA sequences
Implementation | SWIFOLD | SWAPHI-LS | SW# | CUDAlign | SW# | CUDAlign |
|---|---|---|---|---|---|---|
Accelerator | Intel Arria 10 GX | Intel Xeon Phi 3120P | NVIDIA GTX980 | NVIDIA GTX1080 | ||
Matrix size (cells) | Performance (GCUPS) | |||||
1.6T | 132.41 | 31.03 | 91.54 | 122.14 | 193.56 | 224.15 |
1.9T | 132.41 | 27.86 | 84.93 | 110.77 | 180.34 | 231.91 |
3.7T | 132.42 | 33.66 | 89.02 | 119.47 | 191.59 | 232.54 |
4.4T | 132.43 | 30.41 | 95.61 | 132.22 | 138.22 | 250.78 |