| Time | Implementation | Compiler | Benchmark date | SUPERCOP version |
| 42378 | faster | gcc -funroll-loops -march=loongson2f -mabi=n32 -O2 | 20161214 | 20161026 |
| 44152 | faster | gcc -march=loongson2f -mabi=n32 -O2 | 20161214 | 20161026 |
| 44828 | faster | gcc -march=loongson2f -mabi=n32 -O3 | 20161214 | 20161026 |
| 46916 | faster | gcc -funroll-loops -march=loongson2f -mabi=n32 -O3 | 20161214 | 20161026 |
| 53074 | ref | gcc -funroll-loops -march=loongson2f -mabi=n32 -O3 | 20161214 | 20161026 |
| 53328 | ref | gcc -march=loongson2f -mabi=n32 -O3 | 20161214 | 20161026 |
| 55024 | faster | gcc -funroll-loops -march=loongson2f -mabi=n32 -Os | 20161214 | 20161026 |
| 55306 | faster | gcc -march=loongson2f -mabi=n32 -Os | 20161214 | 20161026 |
| 74118 | ref | gcc -funroll-loops -march=loongson2f -mabi=n32 -O2 | 20161214 | 20161026 |
| 139038 | ref | gcc -funroll-loops -march=loongson2f -mabi=n32 -Os | 20161214 | 20161026 |
| 139860 | ref | gcc -march=loongson2f -mabi=n32 -Os | 20161214 | 20161026 |
| 161488 | ref | gcc -march=loongson2f -mabi=n32 -O2 | 20161214 | 20161026 |