English version
Accueil     À propos     Téléchargement     Ressources     Contactez-nous    

Ce site est rarement mis à jour. Pour les informations les plus récentes, rendez-vous sur le nouveau site OCaml à l'adresse ocaml.org.

Browse thread
Odd performance result with HLVM
[ Home ] [ Index: by date | by threads ]
[ Search: ]

[ Message by date: previous | next ] [ Message in thread: previous | next ] [ Thread: previous | next ]
Date: 2009-02-28 (20:18)
From: Kuba Ober <ober.14@o...>
Subject: Re: [Caml-list] Odd performance result with HLVM
> I am developing a high-level virtual machine built upon LLVM and  
> written in
> OCaml that uses JIT compilation to execute OCaml-like code at break- 
> neck
> speeds.
> I just stumbled upon a weird performance result: compiling my VM  
> with ocamlc
> and ocamlopt produces very different benchmark results for the  
> performance of
> the generated code (which should be identical). For example, my  
> float-based
> Fibonacci function becomes 70% slower if I use ocamlopt and some other
> float-based functions also see big performance drops.
> What is ocamlopt doing that might explain this? I assume it is  
> fiddling with
> the floating point state somehow...

You didn't let us in on how it really works. You said "high-level  
virtual machine
built upon LLVM and written in OCaml". LLVM means too many things to be
able to decipher what you mean, and your statement is too general.

I'm assuming, but that's forced, so don't shoot if I make an asinus  
out of myself ;)

So, it's a VM and it runs native jit-ted code like say .net would. So  
presumably you
have some OCaml code that then invokes jit and some native functions  
to dispatch
to jit-ted code? Do you interpret any bytecode, or always compile? Do  
you even
have to have any OCaml code running in the process where the jit-ted  
code runs in?

I presume you use the LLVM infrastructure to do the jit-ting, but  
without knowing
exactly what code runs in the process space of the application, it's  
hard to tell
what's going on.

There's no floating point state to change that would slow things up  
that much.
At least I have never seen anything like that. Maybe the FP exceptions  
are being
fired somehow? You can always set a breakpoint in exception handler(s).

Cheers, Kuba