| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 186396 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161211 | 20161026 |
| 200969 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161211 | 20161026 |
| 210581 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161211 | 20161026 |
| 217236 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161211 | 20161026 |
| 220317 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161211 | 20161026 |
| 220561 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161211 | 20161026 |
| 227574 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161211 | 20161026 |
| 235710 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161211 | 20161026 |
| 247073 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161211 | 20161026 |
| 259009 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161211 | 20161026 |
| 274342 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161211 | 20161026 |
| 281062 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161211 | 20161026 |