Strange but true 8.04 updates today May 26[long]

[Manuel McLure]

On Tue, 27 May 2008 16:18:11 -0700, chuck adams <k7qo at commspeed.net> wrote:
> A cry went up from the crowd!   STICK TO i386!!   Use it.
> 
> I can't do that.  Here is why.  I need 64-bit floating point numbers
> for some heavy computations.  How neat would it be if some one
> from this group did the calculations, using kubuntu, to generate
> the last 1024x1024 image that the Phoenix Mars explorer takes
> before it dies 3 months from now?   Could ubuntu/kubuntu use
> the braggin rights????  I think so.
> 
> My expertise is radiative transfer.  I have done calculations for
> light scattering from lasers, remote sensing both land and satellite
> based, twilight color calculations for the earth, and polarization
> calculations and measurements for Venus.
> 
> I need 64-bits to do the calculations for Mars.  I want the above
> system to do it  so that I can use the fastest processor
> I own and save more that 25% on CPU times.
> 
> I refuse to give up on this quest.  Stand by.  Film at 11.
> I will not be defeated, but I might be out scored.... :-)

You don't need a 64-bit processor to do fast 64-bit floating point
processing. A 64 bit processor will do 64-bit *integer* processing faster
than a 32-bit processor, but the floating point processor in a 32-bit
processor handles 64-bit floating point numbers just as well as the one on
a 64-bit processor. This has been true from the original 80287 (which
handled *80* bit floating point numbers.) For floating point math, the only
advantage a 64-bit processor might have is wider memory bandwidth, but if
you're running the 64-bit processor in 32-bit mode you have that anyway.
The floating point registers in 32-bit mode are the same width as the ones
in 64-bit mode.

-- 
Manuel A. McLure WW1FA <manuel at mclure.org> <http://www.mclure.org>
...for in Ulthar, according to an ancient and significant law,
no man may kill a cat.                       -- H.P. Lovecraft