Re: gcj jit, timing comparison

[Bryce McKinlay <mckinlay at redhat dot com>]

On 1-Jun-06, at 11:12 AM, Thomas Johnsson wrote:

> I'm toying with gcj jit, ie running gcj as a jit:er for gij --  
> great stuff!
> For embedded caffeinemark it is called like this:
>
>    $GIJ -Dgnu.gcj.jit.compiler=$GCJ -Dgnu.gcj.jit.cachedir=$ 
> {CACHEDIR} -Dgnu.gcj.jit.options=$OPT CaffeineMarkEmbeddedApp
> (OPT=-O2)
>
> I've run this both for gcj/gij 4.0.2 and 4.1.0, and statically  
> compiled gcj, with the following numbers:
>
> gij/gcj 'jit' 4.0.2:  39000-39300
> gij/gcj 'jit' 4.1.0:  44700-44900 gcj -O2 static 4.1.0: 56700-57200
>
> Ie, there's an improvement by about 14%  4.0.2->4.1.0, presumably  
> due to better code from gcc/gcj. (?)
>
> And now to my question: where does the difference 'jit' vs static  
> come from?


The BC-ABI (-findirect-dispatch) is used by the gcj-jit and carries  
some overhead, as does shared library (-fPIC) code. Possibly, the way  
that gcj-jit loads a large number of small shared libraries  
introduces overheads as well - a large number of GC static roots, etc.

Bryce