| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 34180 | opt_v4 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 34914 | opt_v4 | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 34993 | opt_v4 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 35056 | opt_v4 | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 37381 | opt | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 39052 | opt | gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | 20161214 | 20161026 |
| 39121 | opt_v4 | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 39270 | opt_v4 | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 42975 | opt | gcc -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 43033 | opt | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | 20161214 | 20161026 |
| 49757 | opt | gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |
| 51004 | opt | gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | 20161214 | 20161026 |