| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 86576 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 87758 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 89631 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 93379 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 93397 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 94112 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 94267 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 94646 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 94646 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 94709 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 97337 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 99035 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |