| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 569090 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 571399 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 573511 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 587905 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 611538 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 652666 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 2158565 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 2198812 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 3324687 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 4293855 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 5315539 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 5638721 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |