So I finally built a new machine, meaning I don't have to lease one any 
more (long story).

Anyway, I'm happy with it... Phenom 2 X4 at 2.6gHz, 4gB of RAM, and a 
1TB hdd :)

Beta 33 renders the benchmark with 4 threads in 1m58s :) :) :)

...Chambers

Post a reply to this message

Chambers wrote:
> Beta 33 renders the benchmark with 4 threads in 1m58s :) :) :)

Impressive!

Just for fun I ran the benchmark, thinking the Phenom was one heck of a 
processor, Rendered the benchmark in under 2 minutes?

My Core2 Quad system rendered it in 1m47 s :-D

But then, my processor is a 2.8 ghz.
-- 
~Mike

Post a reply to this message

>> Beta 33 renders the benchmark with 4 threads in 1m58s :) :) :)
> 
> Impressive!
> 
> Just for fun I ran the benchmark, thinking the Phenom was one heck of a 
> processor, Rendered the benchmark in under 2 minutes?
> 
> My Core2 Quad system rendered it in 1m47 s :-D
> 
> But then, my processor is a 2.8 ghz.

My Amiga 1200 renders the benchmark - the *old* benchmark, SKYVASE.POV - 
in about 2.5 hours. :-P

Post a reply to this message

Invisible <voi### [at] devnull> wrote:
> >> Beta 33 renders the benchmark with 4 threads in 1m58s :) :) :)
> >
> > Impressive!
> >
> > Just for fun I ran the benchmark, thinking the Phenom was one heck of a
> > processor, Rendered the benchmark in under 2 minutes?
> >
> > My Core2 Quad system rendered it in 1m47 s :-D
> >
> > But then, my processor is a 2.8 ghz.
>
> My Amiga 1200 renders the benchmark - the *old* benchmark, SKYVASE.POV -
> in about 2.5 hours. :-P

Has anyone ever run the benchmark on an abacus?

Post a reply to this message

>> My Amiga 1200 renders the benchmark - the *old* benchmark, SKYVASE.POV -
>> in about 2.5 hours. :-P
> 
> Has anyone ever run the benchmark on an abacus?

That would be a vacuous test; it is the speed of the operator, not the 
speed of the abacus itself.

It might, however, be interesting to see how fast a human can do the 
computations by hand. (And, let us not forget, how accurately!)

[Actually, this would not be "interesting" at all for the poor **** 
doing the calculations!]

Interestingly, a human can theoretically perform X computations per 
minute. So if you work out how many computations are required to ray 
trace a single image, you can work out how many humans it would take, in 
principle, to achieve realtime framerates.

[Obviously, this somewhat neglects the latency. If it takes a human 10 
seconds to do a calculation, then no matter how many humans are working 
in parallel, it will always take at least 10 seconds to do any set of 
calculations.]

Lest I jest, I should point out that at one point I sat down and wrote 
out an algorithm for ray tracing a simple scene, optimised for hand 
computation. If you had a graph paper, a set of pencils, and a crapload 
of free time, you could in fact ray trace by hand following this 
algorithm. Jesus I was bored that day...

PS. "Lest I jest" looks French to me for some reason.

Post a reply to this message

Invisible <voi### [at] devnull> wrote:
> >> My Amiga 1200 renders the benchmark - the *old* benchmark, SKYVASE.POV -
> >> in about 2.5 hours. :-P
> >
> > Has anyone ever run the benchmark on an abacus?
>
> That would be a vacuous test; it is the speed of the operator, not the
> speed of the abacus itself.

Ooh, I don't know, what if it were a Fisher-Price 1200 with 16 64-bead racks,
magnetic bead locking and automatic reset springs? ;-)

> [Obviously, this somewhat neglects the latency. If it takes a human 10
> seconds to do a calculation, then no matter how many humans are working
> in parallel, it will always take at least 10 seconds to do any set of
> calculations.]

That's OK - if you get enough mates round, you might still beat the benchmarks
mentioned further up this thread!

> Lest I jest, I should point out that at one point I sat down and wrote
> out an algorithm for ray tracing a simple scene, optimised for hand
> computation. If you had a graph paper, a set of pencils, and a crapload
> of free time, you could in fact ray trace by hand following this
> algorithm. Jesus I was bored that day...

I was just wondering about that as I read the top bits. You'd want to practice,
too, to make sure you were performing optimally.

:)

Post a reply to this message

Nice one. But then, AMD and Intel seem to compute on par - in earlier times 
AMD was faster than Intel.

On a Q9550 with 2.83 MHz it renders in 99 seconds.

It would be interesting to know PovRay benchmarks on different OS - like 32 
/ 64 bit Windows XP / Vista, Linux, etc. Just to get a feeling how much of a 
brake the OS is, and how great the influence of DRAM type, speed and 
frequency is.

"Chambers" <Ben### [at] gmailcom> schrieb im Newsbeitrag 
news:4a83a3cd$1@news.povray.org...
> So I finally built a new machine, meaning I don't have to lease one any 
> more (long story).
>
> Anyway, I'm happy with it... Phenom 2 X4 at 2.6gHz, 4gB of RAM, and a 1TB 
> hdd :)
>
> Beta 33 renders the benchmark with 4 threads in 1m58s :) :) :)
>
> ...Chambers

Post a reply to this message

Bill Pragnell wrote:

> Has anyone ever run the benchmark on an abacus?

No, but now I have the urge to create an electromechanical computer and 
run the benchmark on that.


-- 
~Mike

Post a reply to this message

Invisible <voi### [at] devnull> wrote:
> Lest I jest, I should point out that at one point I sat down and wrote
> out an algorithm for ray tracing a simple scene, optimised for hand
> computation. If you had a graph paper, a set of pencils, and a crapload
> of free time, you could in fact ray trace by hand following this
> algorithm. Jesus I was bored that day...

Reminds me of ray-tracing spheres on the old Ti-86.

This is secondhand information, but a professor told us in the hall one day
about his Russian counterpart.  Now, this was in the days when fluid dynamics
were *very* important--high-speed flight, nuclear weapons, etc...--so they had
a 'computer room' devoted to solving computational fluid dynamics problems.
This guy in particular worked on shock waves.  The computations were set up on
a one-dimensional physical grid, so each 'computer' would tackle one grid
point, do the math with pencil and paper, pass the result to his/her neighbor,
and repeat.  Mistakes were not appreciated, I'm sure, especially when they were
due to bad input.  The story was that this guy had accidentally sent a series of
problems to be computed, and changed the space- and time-resolution in such a
way that the effect was contradictory and all the work was duplicated. Imagine
a computer that gets upset when you make programming errors!  There must be
room for an "In Soviet Russia..." joke somewhere around here.

 - Ricky

Post a reply to this message

Chambers <Ben### [at] gmailcom> wrote:
> Beta 33 renders the benchmark with 4 threads in 1m58s :) :) :)

Except it's not a bit faster than it was in 1999 when you go to render a real
scene.  It just looks a little better.

 - Ricky

Post a reply to this message