| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 1279 | armneon | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 1283 | armneon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 1284 | armneon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 1284 | armneon | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 1289 | armneon2 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 1290 | armneon2 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 1291 | armneon2 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 1292 | armneon2 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 1294 | armneon2 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 1294 | armneon2 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 1299 | armneon | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 1299 | armneon | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 1423 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 1423 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 1441 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 1441 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 1526 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 1594 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |