| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 2331755 | ref10 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161226 | 20161026 |
| 2423421 | ref10 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161226 | 20161026 |
| 2439682 | ref10 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161226 | 20161026 |
| 2453683 | ref10 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161226 | 20161026 |
| 2459363 | ref10 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161226 | 20161026 |
| 2510361 | ref10 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161226 | 20161026 |
| 24219340 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161226 | 20161026 |
| 24263073 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161226 | 20161026 |
| 31076561 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161226 | 20161026 |
| 48115599 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161226 | 20161026 |
| 50294907 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161226 | 20161026 |
| 50327223 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161226 | 20161026 |