| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 115380 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 124386 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 137876 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 139308 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 140764 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 140847 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 141818 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 142274 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 157505 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 167512 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 169533 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 171319 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |