| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 897337 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 917023 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 989063 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 1030940 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 1041601 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 1183104 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 3001624 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 3134835 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 5297306 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 6552336 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 10481641 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 10521973 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |