| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 815033 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 817899 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 846654 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 886155 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 936901 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 997886 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 2890698 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 2928835 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 4673558 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 6137942 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 7637843 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 7968292 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |