| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 23927 | sphlib | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 23989 | sphlib | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 24638 | sphlib | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 24665 | sphlib | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 27799 | sphlib | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 28865 | sphlib | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 38596 | sphlib-small | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 39222 | sphlib-small | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 42960 | sphlib-small | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 43061 | sphlib-small | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 43104 | sphlib-small | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 43531 | sphlib-small | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 43553 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 44678 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 46172 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 50401 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 51511 | ref | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 51786 | ref | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |