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

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

TC schrieb:
> 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. ;-)

Not really:

- The 32-bit beta won't install unless I uninstall the 64-bit version 
first (which, as you can guess, I'm rather reluctant to do ;-))

- Although I compile patched versions of beta.33 almost daily, and it 
wouldn't be a big deal to just run a "non-installed" 32-bit binary once 
I got it built, I never tried before on my 64-bit machine. So, for 
instance, I didn't have 32-bit boost libraries ready.

Well, you can see that I'm using past tense here, so obviously I went 
that extra mile ;-)

Note however that the results must be used with caution:

- Windows XP x64 is a native 64-bit operating system; I guess any 32-bit 
application will suffer some slowdown due to overhead for switching 
between 32-bit and 64-bit every time OS functions are called (such as 
mutexing and other multithreading related stuff, file access, etc). So 
part of the speed difference could indicate not an advantage of 64 bit, 
but a disadvantage of running a 32-bit app on a 64-bit OS.

- I found that the SSE version didn't compile in Visual Studio 2005 for 
some obscure optimization-related issue, so I had to turn off some 
optimization option. (The non-SSE version does compile "as is", but 
would of course distort the results because the 64-bit version always 
uses SSE.)

I also ran a "home-brewn" 64-bit build, to make sure I'm not comparing 
compilers (official releases are built with Visual Studio 2008) or the 
effect of some experimental patches presently in my working code.

The results I got are as follows:

32-bit:     150 s
32-bit SSE: 123 s
64-bit:      74 s

So at least it can be concluded that using the 64-bit binary /does/ give 
a significant advantage /when running a 64-bit OS anway/.

Given the impressive observed difference, I also /think/ that the 
overhead from running a 32-bit app on a 64-bit OS and/or lack of some 
optimization can't possibly account for all of it, and that a "64-64" 
system indeed gives an advantage over a "32-32" system. However, I can't 
guarantee.

Post a reply to this message

Thank you for taking the time and the trouble.



I find the results rather shocking - I would not have guessed that switching 
from 32 to 64 bit would make such a difference. I am thinking of installing 
a 64bit Linux and a 64bit PovRay and doing the benchmark again.



However, this explains the difference between this benchmark and the 
benchmarks I studied when deciding which processor to buy. On 32 bit OS the 
difference between Q9550 and i7 is significant but not too big. For daily 
work I do not need this much computing power and memory. But it is nice to 
have - experimenting with our favourite ray tracer is really fun now. Until 
last month I was still using a 32 bit Athlon 2.4 GHz processor, on which the 
benchmark took 989 seconds.



Since you seem to be intimately involved in Pov Ray beta testing, maybe you 
can answer the question if the benchmark makes extensive use of memory. 
Maybe the difference between 3 and 6 GB would account for the difference 
between 32/64 OS.

Post a reply to this message

clipka <ano### [at] anonymousorg> wrote:
> TC schrieb:
> > 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 became curious about how fast my machines would run and the differences
between Windows and Linux.

1.6Ghz Celeron, 1GB, Vista Home basic(32-bit) - 12m 40s
2.2Ghz Amd x2 4200, 1GB, XP Media Edition(32-bit) - 6m 17s (12m 37s on 1 cpu).
2.33Ghz Intel Quad 8200, 6GB, Vista Home Premium (64-bit) - 1m 59s (7m 49s on 1
cpu)
2.4Ghz Intel Quad 6600, 5GB, Vista Home premium (64-bit) - 1m 58s (7m 46s on 1
cpu)

I also have Mandriva 2008(32-bit) installed on the Q6600 - 1m 55s (7M 40s on 1
cpu).


So on the same hardware 32-bit Linux is very slightly faster than 64-bit Vista.

As soon as I get another hard drive for the Q8200 I plan to install a 64-bit
Linux in a dual-boot configuration.  I doubt that the 64-bit OS would make very
much difference in performance. The additional memory would help if I had an
extremely large number of objects, other than that there wouldn' be much
difference.

Isaac

Post a reply to this message

Mike Raiford wrote:
> 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.

Yes, I know.  Essentially, the Phenom 2 from AMD barely outpaces the 
Core 2 architecture in terms of performance, but IIRC it has better 
power usage and is generally more affordable than the Intel counterparts.

Still, it's my first quad core machine, and I'm excited about it :)

...Chambers

Post a reply to this message

Mike Raiford wrote:
> 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.
> 
> 

Ah, the Babbage Computational Engine :)

...Chambers

Post a reply to this message

clipka wrote:
> 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 !!

Yes... unfortunately, I'm on a budget, so I pretty much had to go with 
AMD :(

...Chambers

Post a reply to this message

clipka wrote:
> (I'll look up the speed next time I boot)

http://www.cpuid.com/download/cpuz/cpuz_152_setup.exe (with install, 
includes 32 & 64-bit binaries).

Click on Memory tab, for current memory performance status, and SPD tab 
for SPD memory config. variants. Your memory should be config. like one 
of the SPD variants if it isn't over-clocked.

Post a reply to this message

Are your memories in Dual Channel mode? and the speed of them? here, to 
know the memory speed: http://www.cpuid.com/download/cpuz/cpuz_152_setup.exe

Click on Memory tab, for current memory performance status, and SPD tab 
for SPD memory config. variants. Your memory should be config. like one 
of the SPD variants if it isn't over-clocked.

Post a reply to this message

Mike Raiford schrieb:
> 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.

Are you aware how many relays you'll need to even store the rendered 
image? :P

Even a device able to compute a b/w image of a RSOCP would be enough of 
a challenge I guess...

Post a reply to this message

Chambers wrote:
> 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
Congratulations, nice system man, I'm finally upgrading my gear so this 
makes a great reference as well as the others who posted their specs. If 
I were to freely choose my specs would be exactly what you have choosen, 
but since my budget is smaller I think I'll have to saddle for an Phenom 
X3 2.33 Ghz, 4GB DDR2-1066, SEAGATE/MAXTOR 500GB 7200 RPM SATA II HDD.

Post a reply to this message

Chambers schrieb:
> Still, it's my first quad core machine, and I'm excited about it :)

You have reason enough to be. Two months ago, I was still working with a 
P4, and was still so excited about the AMD Phenom 2 I had bought half a 
year ago (as a dedicated Linux/POV-Ray rendering machine :-P) that I was 
about to opt for another Phenom for Windows work, too (for a less 
frustrating modelling experience :-)). Fortunately the guy at the local 
store talked me into buying an i7 instead, but I'm convinced the Phenom 
would have done about as well for quite a few years, too, and I would 
have left me just as excited ;-)

If it wasn't for the modelling and raytracing, I could have lived 
happily with that P4 for another year or two: It's just about the 
computing power I needed for everything else, including software 
development. If it wasn't for games, I'd say a fast P4 (I had already 
upgraded it to the fastest I could get) is as much computing power as 
any sane person could possibly need.

... and we have way over 4 times that power on or under our desks - Gee!

Post a reply to this message

Saul Luizaga wrote:
  > but since my budget is smaller I think I'll have to saddle for an 
Phenom
> X3 2.33 Ghz, 4GB DDR2-1066, SEAGATE/MAXTOR 500GB 7200 RPM SATA II HDD.

I very nearly went for the x3, but since I was planning to upgrade it 
eventually anyway I figured there was no point in buying two processors 
for it.

I might as well get the one I wanted to begin with, and save the money 
by not buying the other :)

...Chambers

Post a reply to this message

TC schrieb:
> I find the results rather shocking - I would not have guessed that switching 
> from 32 to 64 bit would make such a difference.

Neither would I. I had expected the difference to be quite marginal, 
having thought that the only significant benefit of 64-bit was in making 
more memory available for a single application.

> Since you seem to be intimately involved in Pov Ray beta testing,

I actually consider myself more involved in development than in testing, 
but of course I need to test what I have implemented, so yes.

 > maybe you
> can answer the question if the benchmark makes extensive use of memory. 
> Maybe the difference between 3 and 6 GB would account for the difference 
> between 32/64 OS.

Definitely not - I just checked: While rendering the benchmark, POV-Ray 
is utilizing just about 30 MB more than when idle.

I've actually never ever managed to reach even the 2 GB limit on my old 
32-bit machine (well, it didn't have more installed anyway). On the 
64-bit Linux machine, the worst thing I ever observed was about 700 MB 
continuous load with a peak of 800 MB during parsing, IIRC (which was 
actually a problem, becaue I had only 4 GB installed at that time, and 
was running a full-throttle MegaPOV render - i.e. four separate 
instances of POV-Ray. The initial peak memory load kicked the whole 
system into "permanent swapping mode", with the MegaPOV instances 
busying themselves kicking each other (and of course everything else) 
out of physical memory instead of doing anything productive. Operating 
the system was of course no fun anymore until I had managed to pause one 
of the processes. Sustained memory load was low enough that I could 
ultimately resume the fourth process again, but startig them up 
simultaneously was too much.)

Post a reply to this message

Chambers wrote:
> Saul Luizaga wrote:
>  > but since my budget is smaller I think I'll have to saddle for an Phenom
>> X3 2.33 Ghz, 4GB DDR2-1066, SEAGATE/MAXTOR 500GB 7200 RPM SATA II HDD.
> 
> I very nearly went for the x3, but since I was planning to upgrade it 
> eventually anyway I figured there was no point in buying two processors 
> for it.
> 
> I might as well get the one I wanted to begin with, and save the money 
> by not buying the other :)
> 
> ....Chambers
Notice that my Phenom is not Phenom II, just Phenom.

Well if you need the money... but since we POV-Ray you might regret it 
later :)

Post a reply to this message

I have made a little research in www.amd.com and the improvements of 
Phenom II over Phenom are: Socket AM3, DDR3, +2/+4 MB L3 Cache. I think 
I'll make the jump and go for a Phenom II X3 2.8, 6MB L3, 4GB DDR3-1333. 
I can't go for the X4 since is only 2.6 and 4MB L3, each core in the X3 
will run more efficiently than the ones in the X4, and compensate for 
the +2 Ghz of the X4, me thinks.

Post a reply to this message

Another small improvement is +3.9 Ghz in memory bandwidth due to DDR3.

Post a reply to this message

>>> 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.
> 
> Are you aware how many relays you'll need to even store the rendered 
> image? :P
> 
> Even a device able to compute a b/w image of a RSOCP would be enough of 
> a challenge I guess...

Who said anything about *store*? You could make it output the binary 
data to some kind of storage device.

I would suggest that if you want hardware floating-point support, you're 
still going to need an absurd number of relays though. ;-)

Post a reply to this message

>>> 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.
>>
>>
> 
> Ah, the Babbage Computational Engine :)

I think you'll find that was mechanical, not electromechanical. :-P

Post a reply to this message

"clipka" <ano### [at] anonymousorg> wrote in message 
news:4a848a81$1@news.povray.org...

> 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.

      No, Vista Home is exactly the same time.  :)

      Win7 may be better though.

      ~Steve~

Post a reply to this message

clipka wrote:

> Are you aware how many relays you'll need to even store the rendered 
> image? :P

We have lots of empty space in the warehouse, right now. ;)

> Even a device able to compute a b/w image of a RSOCP would be enough of 
> a challenge I guess...

Definitely. It would be quite fun to build a simple processor like that, 
though

-- 
~Mike

Post a reply to this message

St. wrote:

> 
>       No, Vista Home is exactly the same time.  :)
> 
>       Win7 may be better though.
> 

These are gaming benchmarks, but not much appreciable difference between 
Win7 and Vista:

http://www.tweaktown.com/articles/2869/windows_7_final_oem_vs_windows_vista_vga_performance/index.html

-- 
~Mike

Post a reply to this message

clipka wrote:
> Chambers schrieb:
>> Still, it's my first quad core machine, and I'm excited about it :)
> 
> You have reason enough to be. Two months ago, I was still working with a 
> P4, and was still so excited about the AMD Phenom 2 I had bought half a 
> year ago (as a dedicated Linux/POV-Ray rendering machine :-P) that I was 
> about to opt for another Phenom for Windows work, too (for a less 
> frustrating modelling experience :-)). Fortunately the guy at the local 
> store talked me into buying an i7 instead, but I'm convinced the Phenom 
> would have done about as well for quite a few years, too, and I would 
> have left me just as excited ;-)

No doubt. My major consideration against the i7 was price, but when the 
prices drop, it'll be a less painful upgrade, though I'll have to get 
DDR3 memory.

One of these days I'll switch the OS to the 64 bit version. Retail Win7 
is going to lighten my wallet, though.

> If it wasn't for the modelling and raytracing, I could have lived 
> happily with that P4 for another year or two: It's just about the 
> computing power I needed for everything else, including software 
> development. If it wasn't for games, I'd say a fast P4 (I had already 
> upgraded it to the fastest I could get) is as much computing power as 
> any sane person could possibly need.
> 
> ... and we have way over 4 times that power on or under our desks - Gee!

Yup.

It still surprised me that with the same video chipset, same video 
memory from the same vendor (but PCIe instead of AGP) that gaming 
performance increased as much as it did, since most games don't really 
take advantage of multiple cores, yet!

-- 
~Mike

Post a reply to this message

Clarence1898 wrote:
> 2.4Ghz Intel Quad 6600, 5GB, Vista Home premium (64-bit) - 1m 58s (7m 46s on 1
> cpu)
> 
> I also have Mandriva 2008(32-bit) installed on the Q6600 - 1m 55s (7M 40s on 1
> cpu).
> 
> 
> So on the same hardware 32-bit Linux is very slightly faster than 64-bit Vista.

Interesting, I wonder how much overhead there is in running 32 bit 
applications on 64 bit windows, then?

Makes me want to stick with good ol' 32 bit for a while longer.

-- 
~Mike

Post a reply to this message

>> Even a device able to compute a b/w image of a RSOCP would be enough 
>> of a challenge I guess...
> 
> Definitely. It would be quite fun to build a simple processor like that, 
> though

When I was about 14, I learned all about logic gates, and became 
convinced that one day I would buy a bazillion 7400s and build an actual 
working computer. Hell, when I was at uni I even got as far as buying 
about 16 of them, and some breadboard, wires, etc.

And then I got stumped by the fact that the gates don't appear to do 
what the diagrams suggest they should...

-- 
http://blog.orphi.me.uk/
http://www.zazzle.com/MathematicalOrchid*

Post a reply to this message

Mike Raiford wrote:
> Interesting, I wonder how much overhead there is in running 32 bit 
> applications on 64 bit windows, then?

clipka posted several POV-Ray benchamrk tests about this and 64-64 
(OS-App) was way better than 32-32. I've seen this also in the disease 
research client I run (www.worldcommunitygrid.org), so as soon as I get 
my new PC I'm switching to 64-bits (WinXP x64, no Vista nor Win7). My 
main interest is the disease research client, I want to do more, alot 
more and 64-bit integers does one of the tricks to make this client go 
way faster.

Post a reply to this message

Orchid XP v8 schrieb:
> And then I got stumped by the fact that the gates don't appear to do 
> what the diagrams suggest they should...

In what way?

Post a reply to this message

Orchid XP v8 wrote:
> And then I got stumped by the fact that the gates don't appear to do 
> what the diagrams suggest they should...

Which brings us to the debate about whether information is intrinsic or 
an added characteristic.

That is, does the diagram actually say anything, or do you invent the 
meaning yourself? :)

...Chambers

Post a reply to this message

>> And then I got stumped by the fact that the gates don't appear to do 
>> what the diagrams suggest they should...
> 
> In what way?

The 7400 is a quad 2-input NAND gate. In other words, it's a box with 
four NAND gates in it.

What's supposed to happen is that you connect pins 1 and 14 to a power 
source, and the remaining pins are grouped into 3s. Each group is the 
connections for a single NAND gate. When the inputs aren't connected, 
the output pin is at logic high. When you connect both of the input pins 
to the (+) rail, the output should go low.

...except this doesn't seem to happen. I swear to God I built circuits 
like this when I was a kid, and it worked. But when I tried it as a 
teenager, it wouldn't work for toffee. No idea why.

-- 
http://blog.orphi.me.uk/
http://www.zazzle.com/MathematicalOrchid*

Post a reply to this message

On Sat, 15 Aug 2009 07:21:00 +0100, Orchid XP v8 <voi### [at] devnull> wrote:

>>> And then I got stumped by the fact that the gates don't appear to do 
>>> what the diagrams suggest they should...
>> 
>> In what way?
>
>The 7400 is a quad 2-input NAND gate. In other words, it's a box with 
>four NAND gates in it.
>
>What's supposed to happen is that you connect pins 1 and 14 to a power 
>source, and the remaining pins are grouped into 3s. Each group is the 
>connections for a single NAND gate. When the inputs aren't connected, 
>the output pin is at logic high. When you connect both of the input pins 
>to the (+) rail, the output should go low.
>
>...except this doesn't seem to happen. I swear to God I built circuits 
>like this when I was a kid, and it worked. But when I tried it as a 
>teenager, it wouldn't work for toffee. No idea why.


Good grief Andrew, 7400s, did you rob a museum? Do you know the power
consumption of TTL compared to CMOS? 
Besides pin 14 being Vcc and pin 7 ground. You cannot assume that inputs will
float high you really should drive them high or low.

-- 

Regards
     Stephen

Post a reply to this message

>> The 7400 is a quad 2-input NAND gate. In other words, it's a box with 
>> four NAND gates in it.
>>
>> What's supposed to happen is that you connect pins 1 and 14 to a power 
>> source, and the remaining pins are grouped into 3s. Each group is the 
>> connections for a single NAND gate. When the inputs aren't connected, 
>> the output pin is at logic high. When you connect both of the input pins 
>> to the (+) rail, the output should go low.
>>
>> ...except this doesn't seem to happen. I swear to God I built circuits 
>> like this when I was a kid, and it worked. But when I tried it as a 
>> teenager, it wouldn't work for toffee. No idea why.
> 
> 
> Good grief Andrew, 7400s, did you rob a museum?

Maplin.

IIRC, they charge 21.22p per chip. (Presumably the 0.22p only makes a 
difference if you buy hundreds of them...)

> Do you know the power consumption of TTL compared to CMOS?

TTL has the advantage that it doesn't break if you touch it. ;-)

> Besides pin 14 being Vcc and pin 7 ground.

OK. I was going from memory there.

> You cannot assume that inputs will
> float high you really should drive them high or low.

...?

-- 
http://blog.orphi.me.uk/
http://www.zazzle.com/MathematicalOrchid*

Post a reply to this message