| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 5384162 | simple | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 5440895 | unrolled | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 5477899 | unrolled | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 5580261 | unrolled | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 5600113 | simple | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 5743557 | unrolled | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 5786893 | simple | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 6069463 | unrolled | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 6588291 | unrolled | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 6797556 | spec | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 7101823 | spec | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 7291615 | spec | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 19096656 | spec | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 20609262 | spec | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 20942959 | spec | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 31536757 | simple | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 34067430 | simple | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 34822015 | simple | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |