| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 807 | armneon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 807 | armneon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 810 | armneon | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 810 | armneon | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 822 | armneon2 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 822 | armneon2 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 822 | armneon2 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 822 | armneon2 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 825 | armneon | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 825 | armneon2 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 826 | armneon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 828 | armneon2 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 915 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 915 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 915 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 915 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 1062 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 1114 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |