Subject: Re: Preliminary test of i386 kernel compiling with GCC 4.0
To: Vincent <10.50@free.fr>
From: Simon Burge <simonb@wasabisystems.com>
List: tech-kern
Date: 10/08/2004 10:48:15
[ Moving well away from kernel issues now... ]

Vincent wrote:

> GCC tends to be stricter as time passes. Also, I was a bit disappointed, 
> even if that doesn't regards the kernel : bladeenc appears to be twice 
> slower when compiled with 4.0 than with 3.3.3. Go figure :)

Interesting that you saw 4.0 being slower that 3.3.3.  Here's some
numbers for gcc floating-point performance, using the time for glucas (a
FFT-based prime number testing program) self tests in order from fastest
to slowest:

	icc 8.0:       1511.657u 0.309s 25:26.36
	gcc 3.4:       1779.724u 0.239s 29:57.07
	gcc 4.0exp:    1845.911u 0.249s 31:03.67
	gcc 3.3.3:     2192.964u 0.249s 36:54.81
	gcc 3.5exp:    2259.040u 0.239s 38:01.40

where:

	icc = Intel C Compiler
	3.5exp == "gcc (GCC) 3.5.0 20040610 (experimental)"
	4.0exp == "gcc version 4.0.0 20041006 (experimental)"

Simon.
--
Simon Burge                            <simonb@wasabisystems.com>
NetBSD Support and Service:         http://www.wasabisystems.com/