| Compiler | Implementations |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | ref |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | ref |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | ref |
| gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | ref |
| gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | ref |
| gcc -mcpu=native -mfpu=neon-vfpv4 -Os | ref |
| Compiler | Implementations |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | neon |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | neon |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | neon |
| gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | neon |
| gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | neon |
| gcc -mcpu=native -mfpu=neon-vfpv4 -Os | neon |
| Compiler | Implementations |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2 | xmm |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3 | xmm |
| gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os | xmm |
| gcc -mcpu=native -mfpu=neon-vfpv4 -O2 | xmm |
| gcc -mcpu=native -mfpu=neon-vfpv4 -O3 | xmm |
| gcc -mcpu=native -mfpu=neon-vfpv4 -Os | xmm |