| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 289706 | opt | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 290281 | opt | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 291309 | opt | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 291640 | opt | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 294543 | opt | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 295546 | opt | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 421841 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 426975 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161217 | 20161026 |
| 460253 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |
| 502335 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 503397 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161217 | 20161026 |
| 535239 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161217 | 20161026 |