AMD64 Multi-Precision Arithmetic
Eric Bainville - Dec 2006These pages relate my experiments on 64-bit multi-precision arithmetic running on Athlon 64 processors. See the introduction for further details.
Here are the best timings I could get so far:
| Function | glibc | gmp | this page | Z ← 0 | 0.50 | - | 0.50 | Z ← op Z (not neg) | - | - | 1.13 | Z ← X | 1.50 | - | 1.50 | Z ← Z op X (+ - and or xor) | - | 2.00 | 1.50 | Z ← Z op not X (and or xor) | - | - | 1.50 | Z ← Z * k | - | 3.00 | 3.00 | Z ← Z * k op X (+ -) | - | 3.13 | 3.13 | Z ← Z << k | - | 2.50 | 2.25 | Z ← Z / k | - | 22.00 | 17.00 |
glibc refers to glibc 4.2, and gmp to gmp 4.2.1 with P. Gaudry's patch.
![]() Multi-Precision Arithmetic | ![]() Top of Page | ![]() AMD64 Multi-Precision : Memory Zero |




