What exactly are the real world benefits?

I'm supposing it doesn't render twice as fast, but you can address more RAM
(double the address size limit?), thus allowing for bigger and more complex
renders?

Would have been nice if it rendered twice as fast, though... but what is the
real spead increase factor (if any?) on a benchmark scene? Seeing (if I'm
not wrong, as usual) that the size of the processing "bites" you can take
at one given instant is twice as large as on a 32-bit architecture? Or is
this illusionary (the bus on most of these systems not being 64 bits wide?
Or not?)
-- 
Stefan Viljoen
Software Support Technician / Programmer
Polar Design Solutions

Post a reply to this message

Stefan Viljoen wrote:

> What exactly are the real world benefits?
> 
> I'm supposing it doesn't render twice as fast, but you can address more
> RAM (double the address size limit?), thus allowing for bigger and more
> complex renders?

About 20-30% speed increase should be typical but having said that I know
I'm gonna get my head slapped because those figures depend heavily on what
you're rendering.

Under 32bit OS your max-mem is 3Gb, under 64bit it's 2^64 which is huge.
I have run renders as large as 22Gb. (With 4Gb internal memory)

> 
> Would have been nice if it rendered twice as fast, though... but what is
> the real spead increase factor (if any?) on a benchmark scene? Seeing (if
> I'm not wrong, as usual) that the size of the processing "bites" you can
> take at one given instant is twice as large as on a 32-bit architecture?
> Or is this illusionary (the bus on most of these systems not being 64 bits
> wide? Or not?)

-- 
Ger

Post a reply to this message

Stefan Viljoen  wrote in message <44cc7a88@news.povray.org>:
> Would have been nice if it rendered twice as fast, though... but what is the
> real spead increase factor (if any?) on a benchmark scene?

It is not a benchmark, but it is possible to make some estimate:

- 64-bit processors break compatibility with 32-bit processors, that enables
  them to forget some bad conception problems of their ancestors, and thus
  to run somewhat faster globally.

- Povray uses mostly floating-point arithmetic, to which the 64-bit quality
  of the processor does not change anything. For arbitrary precision integer
  arithmetics, like in asymmetric cryptography, on the other hand, it
  changes a lot.

- 64-bit processor means bigger pointers, and therefore slower operations
  when storing and fetching pointers to/from memory. Thus, operations on
  complex data structures will be slower than they would have been on an
  equivalent 32-bit processor.

All this, of course, applies in the common working domain of 32- and 64-bit
processors. 64-bit processors allow to handle much more memory at once, thus
allowing them either to work with subjects that a 32-bit processor just
could not handle, or to do it in a much simpler -- and therefore faster --
way.

Post a reply to this message

Ger wrote:
> About 20-30% speed increase should be typical

   Should be typical on which processor?

   A 64-bit binary in a Sun Sparc is not faster than a 32-bit binary.
The same is probably true in a Macintosh.
   In the AMD64 there's a speedup when running 64-bit binaries, but
that speedup has basically nothing to do with the amount of bits.

> Under 32bit OS your max-mem is 3Gb

   This is based on what? Which OS?

> under 64bit it's 2^64 which is huge.

   Current hardware probably puts a limit and 2^64 bytes of RAM
is (in current hardware) not possible.

Post a reply to this message

Stefan Viljoen <spamnot@ wrote:
> Would have been nice if it rendered twice as fast, though...

   Think about it for a moment. Exactly *what* would be the thing
in a 64-bit binary which could possibly make it twice as fast compared
to a 32-bit binary?
   Would adding two numbers together be twice as fast in a 64-bit
binary than in a 32-bit one? Why would it? What would 64-bitness
have to do with the speed at which eg. additions are made? You can
naturally have twice the precision in the (integer) addition, but
what exactly could make it *faster*?

   Where does this idea that increasing bitness can make a binary
faster come from? I don't get it. It's a bit like saying that reading
a book is faster if we make the pages twice as big. It doesn't make
any sense.

   Most processor which support both 32-bit and 64-bit binaries do
not run the 64-bit ones faster. And of course: Why would they? Where
could any speedup come from?
   In fact, eg. the Sun UltraSparc processors run 64-bit binaries
slightly slower than 32-bit binaries. This is because pointers are
twice as big and the data cache of the processor fills faster. This
slowdown isn't big, though; something like 5% or so.

   Now, the AMD64 is a special case: 64-bit binaries optimized for the
AMD64 run slightly faster than 32-bit binaries optimized for the same
processor. However, this speedup has nothing to do with the amount of
bits used. It is because in 64-bit mode the CPU has enhancements which
the binary can use for faster performance (the biggest enhancement is
a bunch of additional CPU registers). This is why it is quite
recommended to run a 64-bit OS and 64-bit binaries on an AMD64 in
order to get full performance.

Post a reply to this message

Warp wrote:

> Ger wrote:
>> About 20-30% speed increase should be typical
> 
>    Should be typical on which processor?

Like I said, "I will get my head slapped" :)
But on my setup, which is an AMD64 X2 3800+ , the measured differences were
in that range.

> 
>    A 64-bit binary in a Sun Sparc is not faster than a 32-bit binary.
> The same is probably true in a Macintosh.
>    In the AMD64 there's a speedup when running 64-bit binaries, but
> that speedup has basically nothing to do with the amount of bits.

Running 64bit Suse here and then there's a definite difference between
the "stock" 32bit binary and a self compiled 64bit version

> 
>> Under 32bit OS your max-mem is 3Gb
> 
>    This is based on what? Which OS?

The only comparisons that I can make are between the various Linux versions
I have running here.

> 
>> under 64bit it's 2^64 which is huge.
> 
>    Current hardware probably puts a limit and 2^64 bytes of RAM
> is (in current hardware) not possible.

Agreed, hardware limits how far you can go. The OS however doesn't cut you
short on how far you can take it.
-- 
Ger

Post a reply to this message

Warp wrote:
>   Where does this idea that increasing bitness can make a binary
> faster come from? I don't get it. It's a bit like saying that reading
> a book is faster if we make the pages twice as big. It doesn't make
> any sense.

Except that case does; you spend less time turning pages... ;)

-- 
Tim Cook
http://home.bellsouth.net/p/PWP-empyrean

-----BEGIN GEEK CODE BLOCK-----
Version: 3.12
GFA dpu- s: a?-- C++(++++) U P? L E--- W++(+++)>$
N++ o? K- w(+) O? M-(--) V? PS+(+++) PE(--) Y(--)
PGP-(--) t* 5++>+++++ X+ R* tv+ b++(+++) DI
D++(---) G(++) e*>++ h+ !r--- !y--
------END GEEK CODE BLOCK------

Post a reply to this message

Tim Cook <z99### [at] bellsouthnet> wrote:
> Warp wrote:
> >   Where does this idea that increasing bitness can make a binary
> > faster come from? I don't get it. It's a bit like saying that reading
> > a book is faster if we make the pages twice as big. It doesn't make
> > any sense.
>
> Except that case does; you spend less time turning pages... ;)
>
> --
> Tim Cook
> http://home.bellsouth.net/p/PWP-empyrean
>



Stephen

Post a reply to this message

Warp <war### [at] tagpovrayorg> wrote:
> Stefan Viljoen <spamnot@ wrote:
> > Would have been nice if it rendered twice as fast, though...
>
>    Think about it for a moment. Exactly *what* would be the thing
> in a 64-bit binary which could possibly make it twice as fast compared
> to a 32-bit binary?
>
>    Where does this idea that increasing bitness can make a binary
> faster come from? I don't get it. It's a bit like saying that reading
> a book is faster if we make the pages twice as big. It doesn't make
> any sense.
>

If a 64-bit processor could run two 32-bit programs at the same time, or if
a 64-bit binary ran two equivalent 32-bit processes simultaneously, then it
would make sense that it could be twice as fast.  But, that's only true if
it takes the same amount of time to perform a 64-bit operation as a 32-bit
operation (which isn't the case).

Mike

Post a reply to this message

Mike Sobers wrote:
> If a 64-bit processor could run two 32-bit programs at the same time

   How the heck could it do that?

Post a reply to this message