gcc4.2 compiler

[kees de jong <omekeesje at wanadoo dot nl>]

Dear gcc-developers,
I downloaded, compiled and installed Your experimental
snapshot compiler gcc4.2-20060805 with some minor
troubles on my dual processor Athlon64 computer with Debian-linux (kernel 2.6.15, smp)
I wanted to use this compiler because it supports openmp.
To test the performance I used a matrix-multiply program.
For multiplying 2 1000x1000 matrices with floating point
values it used 12 seconds, the same time as compiled
with gcc4.0.
When I changed the program to use openmp and compiled it
with the new -fopenmp switch, everything went fine.
But what amazed me, on running this program it only used
6 seconds to complete the multiplication!
As I had always heard that, with parallel-computing on
a dual-core processor you can expect a performance boost
of at most about 1.7 X, I was very agreable surprised.
The software-overhead of your openmp-implementation
seems in this case to be nil!
I think You did a wonderful job with this implementation!
Thank you all very much (these thanks are long due,
because I am using gcc for more than 15 years), I hope
gcc4.2 will soon be the standard gcc-compiler.
If you want to look at the program concerned, please
let me know that. I can than make some small 
alterations (it is a little bit interactive, using the
Dutch language) and send it to you.
As it is an old program of my own making, there are no
copyrights whatsoever.
Thanks again and good luck to You all!!
Kees de Jong