| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 2643084 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 2650559 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 2946413 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 3005608 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 4070815 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 4175229 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161218 | 20161026 |
| 4404911 | table | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 4408568 | table | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 7160345 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 10446490 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161218 | 20161026 |
| 12765127 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |
| 13193750 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161218 | 20161026 |