[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Chicken-users] [ANN] fannkuch chicken benchmark!
From: |
Elf |
Subject: |
[Chicken-users] [ANN] fannkuch chicken benchmark! |
Date: |
Tue, 4 Mar 2008 08:12:27 -0800 (PST) |
attached is new code for the fannkuch benchmark. it has been tested
on openbsd (as thats the only machine i have access to with any memory or
cpu).
Old program:
run1:
real 1m7.544s
user 1m6.602s
sys 0m0.492s
run2:
real 1m8.324s
user 1m7.250s
sys 0m0.563s
New program:
run1:
real 0m25.048s
user 0m24.500s
sys 0m0.422s
run2:
real 0m24.835s
user 0m24.227s
sys 0m0.406s
run3:
real 0m24.824s
user 0m24.391s
sys 0m0.328s
run4:
real 0m24.999s
user 0m24.469s
sys 0m0.320s
C benchmark (for comparison):
run1:
real 0m11.717s
user 0m11.656s
sys 0m0.000s
run2:
real 0m11.814s
user 0m11.602s
sys 0m0.008s
run3:
real 0m11.719s
user 0m11.688s
sys 0m0.008s
Note: Only the first two runs are consecutive; all following runs are staggered
randomly along with running other programs in order to try to incur max
inefficiency.
At the moment, it's looking like we're at twice the speed of C in this
benchmark. Other people, please test it on linux boxen, and post some
figures... if they all look good, with your permission, i'd like to submit
this to the shootout.
-elf
fannkuch_chicken.scm
Description: Text document
- [Chicken-users] [ANN] fannkuch chicken benchmark!,
Elf <=