Re: GCJ slower than JDK?

[Fernando Lozano <fernando at lozano dot eti dot br>]

Hi Per,

>> I wrote a small test program which tries to find wether a list of 
>> files contains two or more files with the same contents. It first 
>> groups all files with the same size, then it gets a checksum for all 
>> files with the same size and if the checksum matches they are grouped 
>> as real duplicates.
>
> In other words a very file-intensive benchmark, which tells us nothing
> about gcj vs jdk speed.

Using the same files on the same machine, only one user, stand-alone (no 
network), repeated many times so the file system cache and paging file 
would not interfere with the results? I think it show clearly that 
something on the GCJ app is much slower than the JDK one, and I'd like 
to find what. But I was afraid GCJ had not yet matured to the point such 
comparisions would be worthless.

It's hard to find real-world apps (or real-word toys like mine ;) to 
compare both, because libgcj does not have AWT, Swing, JDBC and other 
APIs most apps use.

I did not expected so great a difference, because the app is simple, and 
most of its execution time is spent on the CRC check (I guess, maybe I 
should profile the program). Should I expect system calls (getting the 
file size) and the classes Vector or Hashtable to be the reason? Reading 
my source would help?


[]s, Fernando Lozano