Home
| Calendar
| Mail Lists
| List Archives
| Desktop SIG
| Hardware Hacking SIG
Wiki | Flickr | PicasaWeb | Video | Maps & Directions | Installfests | Keysignings Linux Cafe | Meeting Notes | Linux Links | Bling | About BLU |
On Sun, 28 Oct 2007 07:56:13 -0400 Nathan Meyers <[hidden email]> wrote: > 64 bits also places higher demands on the > system: more bits to sling around the bus and greater load on the heap > from the larger words. Unless you need that address space, moving to 64 > bits is pure downside. The incremental load on the bus is small if anything since it is designed for 64 bits. Why is there an extra load on the heap. The heap would be allocated on a 64-bit boundary, but malloc will allocate what you need. But, yes, because of boundary conditions, structures are aligned on 64-bit boundaries. So, your code may use some extra memory. On the upside, as I mentioned there are 16 64-bit registers. While this means saving more registers on context switches, it can mean better performance. I've been working with 64-bit systems since 1994 (Digital Alpha/ Tru64 Unix, as well as x86-64 and IA64). There are some cases where 32-bit applications run better in a 32-bit environment, and there are some cases where applications run better in 64-bits. I have also seen cases where 32-bit apps run better on a 64-bit OS even though they are 32-bit apps. Because of the larger register size, 64-bit linear address space, the OS in general runs better in 64-bits, and Linux has had a 64-bit native OS since 1996. Remember that the paging hardware is also 64-bits. -- Jerry Feldman <[hidden email]> Boston Linux and Unix user group http://www.blu.org PGP key id:C5061EA9 PGP Key fingerprint:053C 73EC 3AC1 5C44 3E14 9245 FB00 3ED5 C506 1EA9 _______________________________________________ Discuss mailing list [hidden email] http://lists.blu.org/mailman/listinfo/discuss
BLU is a member of BostonUserGroups | |
We also thank MIT for the use of their facilities. |