GP in your browser
GP scripts library
Tests & benchmarks
PARI library benchmarks: floating point arithmetic
This page refers to the stable version 2.5.5 of the PARI/GP system [ bench source code ], with native kernel and GMP kernel respectively. PARI and GMP-4.3.2 were linked dynamically to the bench program. This benchmark was adapted from the MPFR bench, with a minor change: we precompute log(2) and π.
The following tables give the cpu time in milliseconds spent by the PARI kernels for different operations, at different (decimal) digitsizes.
64-bit machine: pari.math.u-bordeaux.fr
Xeon E5540 @ 2.53Ghz, running Linux 2.6.32-5-amd64. Libraries were compiled with gcc 4.4.5 and native flags.
32-bit machine: pari.math.u-bordeaux.fr
Xeon E5540 @ 2.53Ghz, running Linux 2.6.32-5-amd64. Libraries were compiled with gcc 4.4.5 -m32 and native flags.
Last Modified: 2016-03-22 20:34:27
Copyleft © 2003-2016 the PARI group.