GMP-Chudnovsky, multipthread version
sam.rawlins at gmail.com
Tue Aug 10 00:52:14 CEST 2010
On Sun, Aug 8, 2010 at 9:15 AM, Torbjorn Granlund <tg at gmplib.org> wrote:
> Pavel Boldin <boldin.pavel at gmail.com> writes:
> If I understand question correctly: speedups up to <cpu count> times.
> So, exactly linear speedup in the number of CPUs? That's very good.
In any case, I think this might be interesting news in light of the new
record for digits of Pi (5 Trillion):
<http://www.numberworld.org/misc_runs/pi-5t/details.html>The record holder
used y-cruncher. y-cruncher writes a comparison to "Parallel GMP-Chudnovsky"
(http://www.numberworld.org/y-cruncher/#FAQ) authored by "David Carver +
Hanhong Xue + GMP team":
- This is a paralleled version of GMP-Chudnovsky using OpenMP. It
appeared back in October 2008 and was improved a month later. It runs much
faster on AMD processors than Intel processors. But because of its use of
GMP, the true speed of this program cannot be achieved in Windows due to the
lack of assembly support.
- On AMD K10 (in linux), the x64 version appears to beat y-cruncher (in
- All computations below a million digits.
- All single-threaded computations.
- Dual-thread computations below a few million digits.
- For larger computations with 4 or more cores, y-cruncher is still
- Although Parallel GMP-Chudnovsky is multi-threaded, it does not scale
as well as y-cruncher. So even though it beats y-cruncher in clock-for-clock
linear speed, it is slower when there are more than 2 cores.
So yours is definitely an update from the October 2008 version?
> gmp-discuss mailing list
> gmp-discuss at gmplib.org
More information about the gmp-discuss