| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 125211 | opt32 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 128393 | opt32 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 129177 | opt32 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 135636 | arm | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 137178 | arm | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 137800 | arm | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161216 | 20161026 |
| 151554 | arm | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 162960 | arm | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 166617 | arm | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 175506 | opt32 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161216 | 20161026 |
| 180309 | opt32 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |
| 181534 | opt32 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161216 | 20161026 |