In article <web.4a8416c5481dd0af6dd25f0b0@news.povray.org>,
Bill Pragnell wrote:

> Has anyone ever run the benchmark on an abacus?

Taking this seriously, an abacus is not comparable to a computer. The
abacus is like... just the RAM memory. We need a processor.

Post a reply to this message

Daniel Bastos <dbastos+0### [at] toledocom> wrote:
> Taking this seriously, an abacus is not comparable to a computer. The
> abacus is like... just the RAM memory. We need a processor.

  Actually an abacus is more like one single integer register (or a few,
if you split the "bits" among several "registers"). It could only be used
to store and manipulate one value (or a couple) at a time. You would not
only need a processor to actually execute the raytracing opcodes, but you
would also need some external "RAM" to store intermediate results. The abacus
by itself is certainly not enough for any of this.

  (Not to talk that an abacus probably wouldn't have enough "bits" to do
any kind of sensible raytracing anyways.)

-- 
                                                          - Warp

Post a reply to this message

In article <4a8461d0@news.povray.org>,
Warp wrote:

> Daniel Bastos <dbastos+0### [at] toledocom> wrote:
>> Taking this seriously, an abacus is not comparable to a computer. The
>> abacus is like... just the RAM memory. We need a processor.
>
>   Actually an abacus is more like one single integer register (or a few,
> if you split the "bits" among several "registers"). It could only be used
> to store and manipulate one value (or a couple) at a time. You would not
> only need a processor to actually execute the raytracing opcodes, but you
> would also need some external "RAM" to store intermediate results. The abacus
> by itself is certainly not enough for any of this.

Hm. I don't really know how an abacus works. I only have a vague idea,
which is (or was): you move those beads to remind you of numbers. :-)
So I said: well, that's just RAM.

Anyway, I could go out on the web to find out how it works, but if you
feel like, why not explain it to a slow person?

>   (Not to talk that an abacus probably wouldn't have enough "bits" to do
> any kind of sensible raytracing anyways.)

Indeed. But we can imagine a huge one?

Post a reply to this message

Mike Raiford schrieb:
>> Beta 33 renders the benchmark with 4 threads in 1m58s :) :) :)
> 
> My Core2 Quad system rendered it in 1m47 s :-D
> 
> But then, my processor is a 2.8 ghz.

So you think 10s less is a big win? Then dig this - Core i7 Quad 920, 
2.67 GHz (probably running at 2.8 GHz though, too):

	1m 15s !!

Gee, I guess I love this machine :P

Post a reply to this message

triple_r schrieb:
>> 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.

LOL - indeed :-)

Post a reply to this message

clipka wrote:

> 
> So you think 10s less is a big win? Then dig this - Core i7 Quad 920, 

Nah, I was surprised that it was so close though. The 1m57s time seemed 
really fast.

> 2.67 GHz (probably running at 2.8 GHz though, too):
> 
>     1m 15s !!
> 
> Gee, I guess I love this machine :P

Yep, the i7's are speedy little beasts, from what I've seen. Does 
hyperthreading help at all?

-- 
~Mike

Post a reply to this message

TC schrieb:
> 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.

As already posted: 75 seconds on a Core i7 920 @ effectively 2.8 GHz, 6 
GB DDR3-RAM (I'll look up the speed next time I boot), running Windows 
XP Prof. x64 Ed. (using the 64-bit binary of POV-Ray of course).

Post a reply to this message

Could you run the benchmark with 32-bit PoyRay binaries? It should not take 
too much time to download - and less then two minutes for you to run. ;-)

I really would like to know if there is any influence and how much of it.

When I built my new PC I toyed with the idea of an i7 but found it a bit too 
expensive in relation to the benchmarks I saw. Then I pondered the idea of a 
64-bit XP instead of the 32-bit I am currently using. Decided against it 
because of possible driver-problems and because I had no idea if it really 
would be a lot faster. I did not really see much sense in using 64-bit 
Vista - I hate the Vista OS from the bottom of my heart.

Then, of course, the i7 is the better processor anyway.

"clipka" <ano### [at] anonymousorg> schrieb im Newsbeitrag 
news:4a84721d$1@news.povray.org...
> TC schrieb:
>> 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.
>
> As already posted: 75 seconds on a Core i7 920 @ effectively 2.8 GHz, 6 GB 
> DDR3-RAM (I'll look up the speed next time I boot), running Windows XP 
> Prof. x64 Ed. (using the 64-bit binary of POV-Ray of course).

Post a reply to this message

Mike Raiford schrieb:
>>     1m 15s !!
> 
> Yep, the i7's are speedy little beasts, from what I've seen. Does 
> hyperthreading help at all?

Yep.

Running on a single thread, the benchmark takes 6m 10s = 370 seconds; 
therefore, even under ideal conditions, without hyperthreading it could 
run no faster than 93s. So although hyperthreading doesn't halve this, 
at least it reduces the render time by another 20%.

So in terms of computing power, for the sake of raytracing it's roughly 
equivalent to adding a 5th core.

I guess it depends on the main memory speed though: I guess HT mainly 
serves to reduce the idle time while the CPU is waiting for data from 
the main memory; so for machines with slower RAM (speaking of latency), 
it may be even more of a benefit.

I also heard tell there may also be differences between OS. I'm running 
XP Pro x64, maybe Vista or Win7 do an even better job at making use of 
HT. Don't know about this though.

Post a reply to this message

TC schrieb:
> Then I pondered the idea of a 
> 64-bit XP instead of the 32-bit I am currently using. Decided against it 
> because of possible driver-problems and because I had no idea if it really 
> would be a lot faster. I did not really see much sense in using 64-bit 
> Vista - I hate the Vista OS from the bottom of my heart.

When I bought the i7, I had the dealer install Windows 7 on it, having 
heard that its UI fixed a lot of annoyances in Vista (which I never 
tested, btw).

Two days later I had them order XP Professional x64 Edition for me.

Works like a charm.

BTW, 64 bit is not mainly about speed, but support for more memory. You 
know, when rendering scenes with 8 GB of texture data and such...

Post a reply to this message