| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 116345 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 125117 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 138666 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 139428 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 140913 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 141223 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 141979 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 142459 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 159436 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 169674 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 171930 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 173696 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |