| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 344466 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 354351 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 355332 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 355843 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 419376 | neon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 525759 | neon | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 650768 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 665609 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 815670 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 828917 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 838725 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 887213 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 1301825 | smaller | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 1303956 | smaller | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 1340776 | smaller | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 1344073 | smaller | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 1520214 | smaller | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 1625530 | smaller | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 2186654 | bitslice | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 2259472 | bitslice | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 2269609 | bitslice | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 2295909 | bitslice | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 2356738 | bitslice | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 2582170 | bitslice | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 4894585 | 8bit | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 5048428 | 8bit | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 5260952 | 8bit | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 5408082 | 8bit | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 6019407 | 8bit | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 6285133 | 8bit | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |