| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 422025 | simple | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 447012 | unrolled | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 452619 | simple | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 454352 | simple | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 461493 | unrolled | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 468424 | unrolled | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 480603 | unrolled | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 501095 | unrolled | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 525101 | unrolled | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 1231326 | spec | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 1284870 | spec | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 1512409 | spec | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161210 | 20161026 |
| 2089626 | spec | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 2201050 | spec | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 2242079 | spec | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 2253909 | simple | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161210 | 20161026 |
| 2369906 | simple | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |
| 2494491 | simple | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161210 | 20161026 |