Browse thread
[Benchmark] NBody
[
Home
]
[ Index:
by date
|
by threads
]
[ Message by date: previous | next ] [ Message in thread: previous | next ] [ Thread: previous | next ]
[ Message by date: previous | next ] [ Message in thread: previous | next ] [ Thread: previous | next ]
| Date: | -- (:) |
| From: | Oliver Bandel <oliver@f...> |
| Subject: | Re: [Caml-list] [Benchmark] NBody |
On Mon, Feb 07, 2005 at 09:04:39PM +0100, sejourne_kevin wrote: > Martin Jambon a écrit : > >On Mon, 7 Feb 2005, Christophe TROESTLER wrote: > > > > > >>Hi, > >> > >>For fun I have implemented an nbody simulation following > >>http://shootout.alioth.debian.org/benchmark.php?test=nbody&lang=all&sort=cpu > >>(code is attached). I've compiled it with > >> > >> ocamlopt -o nbody.com -inline 3 -unsafe -ccopt -O2 nbody.ml > > > > > >-inline 100 gives better results for me (around -25%) > >This should be enough to beat Java :-p if you get the same improvement on > >your side. > Same for me, but "-ccopt -O2" don't change anything. If using gcc, you have to use -O3 to enable inlining. If using only -O2, inlining is not enabled automatically by the gcc. Ciao, Oliver