Exporting benchmarks v2

General discussion regarding photography practices and Capture One workflow as well as integration with third party applications.
Please DO NOT post to this thread regarding OS specific concerns or questions.
Forum rules
For the sake of being thorough, please remember to note if you are using Mac or Windows.
Hopefully this will keep any confusion to a minimum.

Re: Exporting benchmarks v2

Postby WPNL » Thu Jan 25, 2018 10:32 pm

I could see in NZXT Cam software that the GPU takes quite some long breaks during the process, just a few spikes.
This could be the time between a batch of TIFF's?
I'll provide a screenshot tomorrow.
WPNL
 
Posts: 347
Joined: Tue Dec 02, 2014 11:11 am

Re: Exporting benchmarks v2

Postby Chad Dahlquist » Fri Jan 26, 2018 4:01 am

StephanR wrote:
In my opinion this is also the reason why two fast GPU cards do not show much performance differences.
Therefore the times for TiF would be also very interessting for other CPU/GPU combinations.



I know in Craig's original thread Christian Gruner (phase one guy)
his jpg and tiff times on the 7900x were very close to each other and his times for the 12 files were 3x faster than mine :)

would love to see him post times with his dual GPU 7900x machine :)
Last edited by Chad Dahlquist on Fri Jan 26, 2018 4:30 am, edited 1 time in total.
Chad Dahlquist
 
Posts: 43
Joined: Thu Dec 02, 2010 12:58 am

Re: Exporting benchmarks v2

Postby Chad Dahlquist » Fri Jan 26, 2018 4:25 am

WPNL wrote:I could see in NZXT Cam software that the GPU takes quite some long breaks during the process, just a few spikes.
This could be the time between a batch of TIFF's?
I'll provide a screenshot tomorrow.

noticed that :) not sure what the polling time is on that and the time the files actually peak :)
my cpu and gpu were about %60 peaks using the cam software

view it in the task manager in the details view on performance tab and ya get a lot better idea what its doing :)
Chad Dahlquist
 
Posts: 43
Joined: Thu Dec 02, 2010 12:58 am

Re: Exporting benchmarks v2

Postby CraigJohn » Fri Jan 26, 2018 2:07 pm

In the task manager, it doesn’t show my GPU working at all. In the NZXT window, it shows intermittent spikes of performance up to 100%.
CraigJohn
 
Posts: 55
Joined: Thu Jun 09, 2011 5:26 pm

Re: Exporting benchmarks v2

Postby Bobtographer » Fri Jan 26, 2018 3:08 pm

CPU+GPU 0:36
CPU only 1:34
Bobtographer
 
Posts: 509
Joined: Tue Feb 12, 2008 1:01 am
Location: England

Re: Exporting benchmarks v2

Postby WPNL » Fri Jan 26, 2018 4:19 pm

I promised a screenshot:
Image
WPNL
 
Posts: 347
Joined: Tue Dec 02, 2014 11:11 am

Re: Exporting benchmarks v2

Postby garrison » Sun Jan 28, 2018 2:59 pm

StephanR wrote:. . .
Compressing to jpg seems to be a single core operation (I think I've read this somewhere in this forum) as it uses the JPG functions from Microsoft.
This means first the GPU is converting the raw picture and then only the CPU saves the jpg. At this time the GPU is idle until the next raw file is done. As the AMD Ryzen processor is not as fast in single core operations as Intel it will take a bit more time to store the jpg.
. . .
In my opinion this is also the reason why two fast GPU cards do not show much performance differences.
Therefore the times for TiF would be also very interessting for other CPU/GPU combinations.

That could explain a lot! StephanR, thank you for such a useful information! Based on your data it can be concluded that JPEG compression in C1 is bottlenecking the overall export process: it seems to be one-thread process (only 1 CPU core is used) and all other hardware (CPU & GPU) is waiting until it is done. So no matter how many CPU cores you have or how much fast is your GPU (or even more than one GPU), the total RAW export time will be limited mostly on single-core CPU speed. That applies to configurations with quite fast CPU and GPU. Therefore, overclocked CPUs show better results in this bench than multi-core CPUs (if fast enough GPU is used).

For example, there were two interesting benches to compare:
  • Core i7 3770 + GTX1070 - 55 seconds (SSD disk)
  • Core i7 5820k + 2x GTX1080Ti in SLI - 52..55 seconds (depending on disk used)
The hardware is very different, but the benchmark results are the same!

And I've made some monitoring of CPU, GPU & SSD when making the benchmark (using MSI Afterburner).
First graph is for JPEG export (55 seconds on my Intel Core i7 3770 + GTX1070)
Image

The second one is for TIFF format export (uncompressed, 8-bit, scale 100%).
Image
The bench is 28 seconds - 2 times faster than exporting to JPEG! Although TIFF files are 4x larger than JPEG files.
You can see that with TIFF export there is more intensive use of all hardware: CPU, GPU & SSD (GPU acceleration enabled). And there is even performance margin, so Phase One has potential for optimization: some operations in exporting pipeline are still one-threaded and bottlenecking as I may suggest.
Last edited by garrison on Sun Jan 28, 2018 7:52 pm, edited 11 times in total.
garrison
 
Posts: 51
Joined: Sat Sep 20, 2008 12:56 am

Re: Exporting benchmarks v2

Postby garrison » Sun Jan 28, 2018 3:01 pm

photoGrant wrote:
StephanR wrote:Some time ago I've had an idea to improve the speed!
I'm using a small program made by myself to convert the TIF to JPG with the "open with" operation.
After the file is stored as TIF Capture One starts my program in parallel. The program just converts the TIF to JPG
(keeping meta data) and then erases the TIF file.

Here the results with my extra program:
TIF uncompressed 8 Bit -> open with to jpg CPU+GPU - 27s
TIF uncompressed 8 Bit -> open with to jpg CPU only - 88s
As you can see the speed with GPU is only 1s slower then only the TIF conversion.
Even the CPU only test is faster (all cores are running around 100%) as the jpg conversion in CO1
And as you can see my AMD 280x is very old in comparison to a NVidia 1080.

In my opinion this is also the reason why two fast GPU cards do not show much performance differences.
Therefore the times for TiF would be also very interessting for other CPU/GPU combinations.


This is a great solution but it simply tells me that Phase One can do a much better job at utilizing available resources (you're parallel tasking where Capture ONE should be).

I'd give this information to Phase in a technical support case and hope it lands on good ears..

G


photoGrant, we all will be waiting for the answer, that is very interesting :roll:
garrison
 
Posts: 51
Joined: Sat Sep 20, 2008 12:56 am

Re: Exporting benchmarks v2

Postby garrison » Sun Jan 28, 2018 5:47 pm

WPNL, can you please make the same spreadsheet on your site for this thread benchmarks as you kindly have made before for GPU benchmarks? :roll:
https://phodograf.com/capture-one-benchmarks/
Will very appreciate you with this
garrison
 
Posts: 51
Joined: Sat Sep 20, 2008 12:56 am

Re: Exporting benchmarks v2

Postby Christian Gruner » Mon Jan 29, 2018 11:14 am

Intel I9 7900x (stock)
M.2 storage
2 x AMD R9 Nano
1 x AMD RX580 (eGPU on TB3)
Windows 1709

Jpeg:
CPU only: 1m07s
CPU + GPUs: 48s

Tiff:
CPU only: 1m09s
CPU + GPU's: 13s
Christian Gruner
Crew
Crew
 
Posts: 1832
Joined: Fri Nov 30, 2012 9:48 pm
Location: Copenhagen, Denmark

Re: Exporting benchmarks v2

Postby WPNL » Mon Jan 29, 2018 11:21 am

garrison wrote:WPNL, can you please make the same spreadsheet on your site for this thread benchmarks as you kindly have made before for GPU benchmarks? :roll:
https://phodograf.com/capture-one-benchmarks/
Will very appreciate you with this


Sounds like a great project, I'll start with this :-)
WPNL
 
Posts: 347
Joined: Tue Dec 02, 2014 11:11 am

Re: Exporting benchmarks v2

Postby garrison » Mon Jan 29, 2018 12:53 pm

WPNL wrote:
garrison wrote:WPNL, can you please make the same spreadsheet on your site for this thread benchmarks as you kindly have made before for GPU benchmarks? :roll:
https://phodograf.com/capture-one-benchmarks/
Will very appreciate you with this


Sounds like a great project, I'll start with this :-)

Yeap! :D
How do you think, is it a good idea to include also a TIFF export benchmark values there? Because JPEG benchmarks do not always show all the capabilities of hardware in current version of CO. For example, Christian's benchmark above on Intel i9 7900x and 3 GPUs is very little faster (48s) than mine (i7 3770 & single GPU - 55s) - for JPEG. With TIFF there is much more difference: Christian's system goes for 13s, mine is 28s.
garrison
 
Posts: 51
Joined: Sat Sep 20, 2008 12:56 am

Re: Exporting benchmarks v2

Postby WPNL » Mon Jan 29, 2018 6:07 pm

WPNL
 
Posts: 347
Joined: Tue Dec 02, 2014 11:11 am

Re: Exporting benchmarks v2

Postby garrison » Mon Jan 29, 2018 9:20 pm


Great job, William! Looks VERY nice! 8)
What do you think about adding 'format type' column - tiff or jpeg (see my post above)? Maybe I should update this benchmark too for tiff format in addition to jpeg?
garrison
 
Posts: 51
Joined: Sat Sep 20, 2008 12:56 am

Re: Exporting benchmarks v2

Postby WPNL » Mon Jan 29, 2018 9:49 pm

Of course we can add a column, I didn't right away because the 'normal' workflow is RAW > JPG.
But I can add the column and put in some values, no problem :-)
WPNL
 
Posts: 347
Joined: Tue Dec 02, 2014 11:11 am

PreviousNext

Return to Workflow and Common Photography Exploration



Who is online

Users browsing this forum: No registered users and 2 guests