On 23.05.10 21:24, Warp wrote:
> Thorsten Froehlich<tho### [at] trfde>  wrote:
>> On 23.05.10 20:33, Alain wrote:
>>> As it is now, there is NO preview and the image is NOT saved anywhere.
>
>> That is kind of the point of a processor benchmark and intentional :-)
>
>    How much overhead would displaying the image cause in reality? After all,
> it would be nicer to see the image being rendered instead of just some
> percentage...

Well, the overhead would not be much indeed. But that isn't the problem. The 
problem is that it cannot be predicted how much overhead it uses, and it 
will depend on the GPU (if any). Running this on a system meant as a server, 
which is usually fast running headless might add bias of a few percent 
consistently even when doing multiple runs...

Or imagine a slow CPU and an X display over an encrypted connection. The 
data transfer could draw so much CPU power...

Or a million of other alternative scenarios that could make the benchmarking 
go wrong...

In short: No display and no disk output simply eliminates two random 
variables from the measurement.

	Thorsten

Post a reply to this message

Am 23.05.2010 20:33, schrieb Alain:

> It would be good to remove at least one of those lines from benchmark.ini:
> Display=Off
> This disable the preview.
>
> Output_To_File=Off
> This disable saving the resulting image.
>
> As it is now, there is NO preview and the image is NOT saved anywhere.

This is by design. The benchmark is /only/ a benchmark of the render 
engine, and any output activity is /not/ part of what it should measure.

Post a reply to this message

Stephen <mca### [at] aolDOTcom> wrote:
....
> There is a "benchmark_Display.ini" which has the settings:
>
> ;Buffer_Output=Off
> ;Buffer_Size=0
> Display=On
> Output_To_File=On
>
>
> --
>
> Best Regards,
>  Stephen

I don't have this file, but that was what I changed.
Note: the internal benchmark lists only 44 total objects, and the benchmark.ini
when run lists about 172 objects. There is also a big difference in photon time.
I don't think this has anything to do with display or saveing files.

Stephen S

Post a reply to this message

Stephen <mca### [at] aoldotcom> wrote:
> My Intel Core2 Duo 2.20GHz 3 Gig ram, laptop rendered the benchmark in 
> 39m 40s with benchmark_Display.ini and 17m 56s with benchmark.ini.

  Displaying the image while rendering slows down rendering speed to half?
I can't believe that. There must be an error somewhere.

-- 
                                                          - Warp

Post a reply to this message

Le 24/05/2010 15:17, Warp nous fit lire :
> Stephen <mca### [at] aoldotcom> wrote:
>> My Intel Core2 Duo 2.20GHz 3 Gig ram, laptop rendered the benchmark in 
>> 39m 40s with benchmark_Display.ini and 17m 56s with benchmark.ini.
> 
>   Displaying the image while rendering slows down rendering speed to half?
> I can't believe that. There must be an error somewhere.
> 
There might be a bottleneck on display thread/display data ?

Post a reply to this message

On 24/05/2010 2:17 PM, Warp wrote:
> Stephen<mca### [at] aoldotcom>  wrote:
>> My Intel Core2 Duo 2.20GHz 3 Gig ram, laptop rendered the benchmark in
>> 39m 40s with benchmark_Display.ini and 17m 56s with benchmark.ini.
>
>    Displaying the image while rendering slows down rendering speed to half?
> I can't believe that. There must be an error somewhere.
>


benchmark_Display.ini. This time it took 58. 08s. Of course the render 
priority is low and other programs are running (but not actively being 
used). So it is not much of a proper test.

-- 

Best Regards,
	Stephen

Post a reply to this message

Le_Forgeron <jgr### [at] freefr> wrote:
> Le 24/05/2010 15:17, Warp nous fit lire :
> > Stephen <mca### [at] aoldotcom> wrote:
> >> My Intel Core2 Duo 2.20GHz 3 Gig ram, laptop rendered the benchmark in 
> >> 39m 40s with benchmark_Display.ini and 17m 56s with benchmark.ini.
> > 
> >   Displaying the image while rendering slows down rendering speed to half?
> > I can't believe that. There must be an error somewhere.
> > 
> There might be a bottleneck on display thread/display data ?

  Displaying an image takes 22 minutes? I don't think so. There must be an
error somewhere.

-- 
                                                          - Warp

Post a reply to this message

Le 24/05/2010 18:38, Warp nous fit lire :
> Le_Forgeron <jgr### [at] freefr> wrote:
>> Le 24/05/2010 15:17, Warp nous fit lire :
>>> Stephen <mca### [at] aoldotcom> wrote:
>>>> My Intel Core2 Duo 2.20GHz 3 Gig ram, laptop rendered the benchmark in 
>>>> 39m 40s with benchmark_Display.ini and 17m 56s with benchmark.ini.
>>>   Displaying the image while rendering slows down rendering speed to half?
>>> I can't believe that. There must be an error somewhere.
>>>
>> There might be a bottleneck on display thread/display data ?
> 
>   Displaying an image takes 22 minutes? I don't think so. There must be an
> error somewhere.
> 
Conflict/slowdown to get a mutex... to update the data... (just an idea,
untested)

Post a reply to this message

On 24/05/2010 5:38 PM, Warp wrote:
> Le_Forgeron<jgr### [at] freefr>  wrote:
>> Le 24/05/2010 15:17, Warp nous fit lire :
>>> Stephen<mca### [at] aoldotcom>  wrote:
>>>> My Intel Core2 Duo 2.20GHz 3 Gig ram, laptop rendered the benchmark in
>>>> 39m 40s with benchmark_Display.ini and 17m 56s with benchmark.ini.
>>>
>>>    Displaying the image while rendering slows down rendering speed to half?
>>> I can't believe that. There must be an error somewhere.
>>>
>> There might be a bottleneck on display thread/display data ?
>
>    Displaying an image takes 22 minutes? I don't think so. There must be an
> error somewhere.
>


priority set to High and all other applications shut down. The timings I 
got were:
With display: 17m 31s
Without display: 17m 31s
Without display and Task Manager running: 17m 40s


-- 

Best Regards,
	Stephen

Post a reply to this message

Le 25/05/2010 09:02, Stephen a écrit :
> On 24/05/2010 5:38 PM, Warp wrote:
>> Le_Forgeron<jgr### [at] freefr>  wrote:
>>> Le 24/05/2010 15:17, Warp nous fit lire :
>>>> Stephen<mca### [at] aoldotcom>  wrote:
>>>>> My Intel Core2 Duo 2.20GHz 3 Gig ram, laptop rendered the benchmark in
>>>>> 39m 40s with benchmark_Display.ini and 17m 56s with benchmark.ini.
>>>>
>>>>    Displaying the image while rendering slows down rendering speed
>>>> to half?
>>>> I can't believe that. There must be an error somewhere.
>>>>
>>> There might be a bottleneck on display thread/display data ?
>>
>>    Displaying an image takes 22 minutes? I don't think so. There must
>> be an
>> error somewhere.
>>
> 
> I thought so too, so I ran a more controlled test. With PovRay’s
> priority set to High and all other applications shut down. The timings I
> got were:
> With display: 17m 31s
> Without display: 17m 31s
> Without display and Task Manager running: 17m 40s
> 
> 
Now that's even stranger if the last is "without Task Manager running"!
If it is "With Task Manager running", looks normal: more charge, more time!

Good news seems to be that display does not change the time with High
Priority.
Now, the question would be: does it (with display or without display)
change the time when the priority is Low (as the default) ?
Might suggest to have a different default priority on Windows... at
least when more than one core is detected. (for 1 core only, it is
better to have Low Priority for the povray-thread, otherwise povray
would be killing the GUI)
On 2+ core, a normal priority might just be fine (unless constant render
time really need a High priority, in which case... well... the OS
scheduler sucks if we still get a 2:1 ratio!)

-- 
A: Because it messes up the order in which people normally read text.<br/>
Q: Why is it such a bad thing?<br/>
A: Top-posting.<br/>
Q: What is the most annoying thing on usenet and in e-mail?

Post a reply to this message