|
|
Chambers <ben### [at] pacificwebguycom> wrote:
> On 3/24/2009 4:34 PM, Chris Cason wrote:
> > dkanter wrote:
> >> However, I cannot wait till beta 32 comes out (since that will probably be the
> >> middle of April), so I'd like to get my hands on beta 30 for win64. I don't
> >> want support, since I'm sure the benchmark test will run without crashing.
> >> Could Chris or someone email me the needed files?
> >
> > I'll try to get one built. The issue for me was the boost libraries, this isn't
> > difficult to fix, just fiddly.
> >
> > -- Chris
>
> As I've noticed. Though I've managed to compile all POV files for 64
> bits, I can't link the final .exe because I can't convince Boost to
> build 64 bit libraries.
>
> Grr...
>
> --
> ...Chambers
> www.pacificwebguy.com
Chambers <ben### [at] pacificwebguycom> wrote:
> On 3/24/2009 4:34 PM, Chris Cason wrote:
> > dkanter wrote:
> >> However, I cannot wait till beta 32 comes out (since that will probably be the
> >> middle of April), so I'd like to get my hands on beta 30 for win64. I don't
> >> want support, since I'm sure the benchmark test will run without crashing.
> >> Could Chris or someone email me the needed files?
> >
> > I'll try to get one built. The issue for me was the boost libraries, this isn't
> > difficult to fix, just fiddly.
> >
> > -- Chris
>
> As I've noticed. Though I've managed to compile all POV files for 64
> bits, I can't link the final .exe because I can't convince Boost to
> build 64 bit libraries.
>
> Grr...
>
> --
> ...Chambers
> www.pacificwebguy.com
Chris and Chambers,
Thanks a ton for looking at beta 31 for me. I was able to get a hold of beta 30
from a kindly user, so I'll be able to include POV-Ray results, although they
are slightly outdated I suppose.
Just to add a comment on 64b vs. 32b performance, the major differences:
1. 16 registers vs. 8
2. 64 bit pointers vs. 32b pointers
3. >4GB of memory
2 is a subtle point - it substantially increases the pressure on caches and
TLBs, since cache lines are fixed size (64B).
David
Post a reply to this message
|
|