| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 137467 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 139220 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 140429 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 140903 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 142240 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 142713 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161222 | 20161026 |
| 157400 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 159892 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 163649 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 167515 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161222 | 20161026 |
| 169497 | ref64 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |
| 171417 | ref64 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161222 | 20161026 |