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: | Christophe TROESTLER <Christophe.Troestler@u...> |
| Subject: | Re: [Caml-list] [Benchmark] NBody |
Hi, Sorry for the late reply, I am catching up with email. On Tue, 8 Feb 2005, Xavier Leroy <Xavier.Leroy@inria.fr> wrote: > > Your OCaml code is about as good as you can write. All the unboxing > optimizations are triggered. Ah, thanks for telling, I was wondering about that. > You don't say which Java implementation you used (there are several). Sorry; Sun JDK 1.5.0. > (Besides, being 1.3 times slower than gcc on numerical code is > within the design envelope for OCaml. My performance goals have > always been "never more than twice as slow as C".) Yes. I am not complaining, just trying to understand (and, to say the whole truth, I was also a bit "sad" that Java was beating my favorite language :). > On a "normal" (register-based) float architecture like PowerPC or > x86_64, the OCaml-generated code is essentially identical to the > gcc-generated one. Oh, good, so going to 64 bits will bring us that too! > The C translation is attached for your amusement. Thanks for your very detailed and informative answer! Best regards, ChriS