AMD Athlon64 Systems
Mike A. Harris
mharris at redhat.com
Sun Oct 19 19:18:15 UTC 2003
On Sat, 18 Oct 2003, Paul Jakma wrote:
>> If anyone has information to the contrary however, I'm definitely
>> open eared and eyed to have a look at their non-hypothetical test
>> results. ;o)
>
>The point is though exactly that with AMD64 this argument is
>hypothetical. The other posters are not talking about IA32 vs x86-64,
>they're talking about x86-64 versus a hypothetical ILP32 ABI for
>x86-64. All (i can think of at least) the other 64bit processors
>support ILP32 ABIs, and apps do run faster because it. (MIPS even has
>a 32bit ABI with 64bit doubles, MIPS n32 possibly).
I'm more interested in real world scenarios than hypothetical
scenarios when it comes to performance. Something that exists
only as thoughts in someone's mind, but isn't a reality isn't
useful to me while using a computer system to get real work done.
As a side note - AMD64 supports 32bit pointers being used in
64bit applications, although I'm not sure wether or not our gcc
(or any for that matter) support this yet. -mmodel=small
alledgedly enables it, although I haven't tested that either.
It'd be interesting to compare 64bit app with 32bit pointers
against 32bit app performancewise. I'll probably experiment with
that sometime for fun. ;o)
--
Mike A. Harris ftp://people.redhat.com/mharris
OS Systems Engineer - XFree86 maintainer - Red Hat
More information about the test
mailing list