| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 120954 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 123593 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 125208 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 126260 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 139657 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 139930 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 141704 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 141736 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 141758 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 142039 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 142067 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 143469 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |