| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 1778074 | arm | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161225 | 20161026 |
| 1803984 | arm | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161225 | 20161026 |
| 1808224 | arm | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161225 | 20161026 |
| 1818688 | arm | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161225 | 20161026 |
| 1841959 | arm | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161225 | 20161026 |
| 1842208 | arm | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161225 | 20161026 |
| 2644589 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161225 | 20161026 |
| 2666775 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161225 | 20161026 |
| 2698705 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161225 | 20161026 |
| 2775901 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161225 | 20161026 |
| 2845678 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161225 | 20161026 |
| 2850993 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161225 | 20161026 |