On Wed, Nov 07, 2007 at 02:38:27PM +0100, Jonas Meurer wrote: > Ok, the fact that pointers and long/double variables on 64bit systems do > take twice as much RAM as on ia32 systems sounds reasonable. Thanks for > information.
Pointers do. long's happen to be defined as 64bit on x86_64 while they are defined as 32bit on i386. Any program that uses longs better be aware that sizeof(int) != sizeof(long) on all systems. doubles are 64bit in all cases as far as I remember. I think there is a new 128bit floating point format available with 64bit that wasn't there on 32bit systems. I don't deal with floating point enough to be sure. > 30% is quite a lot. Can you point me to postings/articles/etc. which > claim to have discovered this? Well here is a randomly picked example: rceng02:~# ls -l /data/.chroot/debian-pure64/bin/ls -rwxr-xr-x 1 root root 85536 Jan 30 2007 /data/.chroot/debian-pure64/bin/ls rceng02:~# ls -l /bin/ls -rwxr-xr-x 1 root root 77352 Jan 30 2007 /bin/ls So /bin/ls appears to be 10% larger. rceng02:~# ls -l /bin/gzip -rwxr-xr-x 4 root root 52672 Sep 19 2006 /bin/gzip rceng02:~# ls -l /data/.chroot/debian-pure64/bin/gzip -rwxr-xr-x 4 root root 60216 Sep 19 2006 /data/.chroot/debian-pure64/bin/gzip So /bin/gzip appears to be 14% larger. I seem to recall gzip also runs quite a bit faster on 64bit. -- Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
