| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 873364 | optimized_nonSSE | gcc -funroll-loops -mcpu=marvell-pj4 -O3 | 20161216 | 20161026 |
| 885553 | optimized_nonSSE | gcc -funroll-loops -mcpu=marvell-pj4 -O2 | 20161216 | 20161026 |
| 1264142 | optimized_nonSSE | gcc -mcpu=marvell-pj4 -O3 | 20161216 | 20161026 |
| 1297534 | ref | gcc -funroll-loops -mcpu=marvell-pj4 -O3 | 20161216 | 20161026 |
| 1336543 | ref | gcc -mcpu=marvell-pj4 -O3 | 20161216 | 20161026 |
| 1410498 | optimized_nonSSE | gcc -mcpu=marvell-pj4 -O2 | 20161216 | 20161026 |
| 1449112 | ref | gcc -funroll-loops -mcpu=marvell-pj4 -O2 | 20161216 | 20161026 |
| 1538097 | ref | gcc -mcpu=marvell-pj4 -O2 | 20161216 | 20161026 |
| 1584014 | optimized_nonSSE | gcc -mcpu=marvell-pj4 -Os | 20161216 | 20161026 |
| 1679846 | optimized_nonSSE | gcc -funroll-loops -mcpu=marvell-pj4 -Os | 20161216 | 20161026 |
| 2220014 | ref | gcc -funroll-loops -mcpu=marvell-pj4 -Os | 20161216 | 20161026 |
| 2233034 | ref | gcc -mcpu=marvell-pj4 -Os | 20161216 | 20161026 |