[Bf-committers] Cycles performance

[Mike Pan]

Not to start another OS debate. But...

I noticed that the performance of Cycles is very OS-dependent. With the old
rendering engine, the OS can influence the rendering time by ~10%. But with
Cycles, i am seeing a huge difference in performance between Windows and
Linux/Mac, where Linux/Mac is often twice as fast.

This cleaned up chart by
Olivierclearly
shows the discrepancy:
http://oenvoyage.files.wordpress.com/2012/02/benchmark_win_linux.png

I've done my own dual-boot test and the results as as follows:

Cycles Render: (huge difference in render time)
OS X: 3:27
Win 7: 6:14

Classic Render: (similar time, as expected)
OS X: 1:24
Win 7: 1:29

Both OS are running natively (not under virtual machine), using the 64bit
version of Blender 2.62.

My question is, Is there any technical reason behind this? thread
management? malloc overhead?

Mike
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance

[Brecht Van Lommel]

Hi,

It's probably more compiler dependent than OS-dependent. Visual studio
does not compile the render kernel as well as gcc. I've been
developing with gcc, so that has some influence, and it's probably
possible to tweak the code such that it compiles faster on visual
studio. Thread management could be related but last I checked
rendering threads were kept busy.

Brecht.

On Mon, Mar 5, 2012 at 11:26 PM, Mike Pan  wrote:
> Not to start another OS debate. But...
>
> I noticed that the performance of Cycles is very OS-dependent. With the old
> rendering engine, the OS can influence the rendering time by ~10%. But with
> Cycles, i am seeing a huge difference in performance between Windows and
> Linux/Mac, where Linux/Mac is often twice as fast.
>
> This cleaned up chart by
> Olivierclearly
> shows the discrepancy:
> http://oenvoyage.files.wordpress.com/2012/02/benchmark_win_linux.png
>
> I've done my own dual-boot test and the results as as follows:
>
> Cycles Render: (huge difference in render time)
> OS X: 3:27
> Win 7: 6:14
>
> Classic Render: (similar time, as expected)
> OS X: 1:24
> Win 7: 1:29
>
> Both OS are running natively (not under virtual machine), using the 64bit
> version of Blender 2.62.
>
> My question is, Is there any technical reason behind this? thread
> management? malloc overhead?
>
> Mike
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance

[Mike Pan]

You are right Brecht, I just tested with a GCC-built Windows version of
Blender an the result is comparable with that of Linux/Mac.
Thanks!

m


On Tue, Mar 6, 2012 at 5:17 AM, Brecht Van Lommel <
brechtvanlom...@pandora.be> wrote:

> Hi,
>
> It's probably more compiler dependent than OS-dependent. Visual studio
> does not compile the render kernel as well as gcc. I've been
> developing with gcc, so that has some influence, and it's probably
> possible to tweak the code such that it compiles faster on visual
> studio. Thread management could be related but last I checked
> rendering threads were kept busy.
>
> Brecht.
>
> On Mon, Mar 5, 2012 at 11:26 PM, Mike Pan  wrote:
> > Not to start another OS debate. But...
> >
> > I noticed that the performance of Cycles is very OS-dependent. With the
> old
> > rendering engine, the OS can influence the rendering time by ~10%. But
> with
> > Cycles, i am seeing a huge difference in performance between Windows and
> > Linux/Mac, where Linux/Mac is often twice as fast.
> >
> > This cleaned up chart by
> > Olivier<
> http://oenvoyage.wordpress.com/2012/02/25/blender-cycles-best-hardware-using-the-benchmark-spreadsheet-analysis/
> >clearly
> > shows the discrepancy:
> > http://oenvoyage.files.wordpress.com/2012/02/benchmark_win_linux.png
> >
> > I've done my own dual-boot test and the results as as follows:
> >
> > Cycles Render: (huge difference in render time)
> > OS X: 3:27
> > Win 7: 6:14
> >
> > Classic Render: (similar time, as expected)
> > OS X: 1:24
> > Win 7: 1:29
> >
> > Both OS are running natively (not under virtual machine), using the 64bit
> > version of Blender 2.62.
> >
> > My question is, Is there any technical reason behind this? thread
> > management? malloc overhead?
> >
> > Mike
> > ___
> > Bf-committers mailing list
> > Bf-committers@blender.org
> > http://lists.blender.org/mailman/listinfo/bf-committers
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
>
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

[Bf-committers] Cycles performance on Windows

[Jürgen Herrmann]

Hi there,

With all major bugs an porting issues fixed we ran some tests with different 
builds of blender for Windows 64 bit

Results can be seen here:
http://blenderartists.org/forum/showthread.php?290177-Lets-speed-up-blender

What seems strange is the fact that cycles performs best when built with 
MinGW64.
While the MSVC 2012 build perform equal or even better with smokesim, Blender 
internal and physics stuff.

I assume that the cycles code base is more or less optimized for gcc or gcc has 
some nice optimizations that fit well.
Is there any possibility to change this?

Best regards 
Jürgen
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance on Windows

[Brecht Van Lommel]

Cycles was developed with GCC / LLVM and so it's going to be faster
with those. Making it work faster with visual studio should be
possible, the way to do that is just to do profiling, find
bottlenecks, tweak code, test compiler flags, etc. Maybe it takes just
some simple changes but someone just needs to spend time on this to
figure them out.

Brecht.

On Fri, May 10, 2013 at 7:20 PM, Jürgen Herrmann  wrote:
> Hi there,
>
> With all major bugs an porting issues fixed we ran some tests with different 
> builds of blender for Windows 64 bit
>
> Results can be seen here:
> http://blenderartists.org/forum/showthread.php?290177-Lets-speed-up-blender
>
> What seems strange is the fact that cycles performs best when built with 
> MinGW64.
> While the MSVC 2012 build perform equal or even better with smokesim, Blender 
> internal and physics stuff.
>
> I assume that the cycles code base is more or less optimized for gcc or gcc 
> has some nice optimizations that fit well.
> Is there any possibility to change this?
>
> Best regards
> Jürgen
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance on Windows

[Antony Riakiotakis]

According to the MinGW64 developers, the math library implementation is
faster for gcc. The simulations use openmp which is disabled in MinGW64 due
to their buggy pthread implementation which makes openmp hang when used
during pthread execution.
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance on Windows

[Jürgen Herrmann]

This sounds reasonable. So we need a lightning fast math library replacement 
for MS compilers...
I'm just kidding, but the idea might be insane enough to try ;)

I am very satisfied with the speed improvement that MSVC 2012 has brought to 
blender. I would love to see this in the wild. It could make some people very 
happy.

I would volunteer to maintain this build platform if desired.

/Jürgen


Am 10.05.2013 um 20:17 schrieb Antony Riakiotakis :

> According to the MinGW64 developers, the math library implementation is
> faster for gcc. The simulations use openmp which is disabled in MinGW64 due
> to their buggy pthread implementation which makes openmp hang when used
> during pthread execution.
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance on Windows

[Ton Roosendaal]

Hi Jurgen,

You're very welcome to join the windows platform team as maintainer for MSVC 
2012.
Did you already have patches we should apply? We typically give people commit 
access after a couple of good patches.

-Ton-


Ton Roosendaal  Blender Foundation   t...@blender.orgwww.blender.org
Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands

On 10 May, 2013, at 22:02, Jürgen Herrmann wrote:

> This sounds reasonable. So we need a lightning fast math library replacement 
> for MS compilers...
> I'm just kidding, but the idea might be insane enough to try ;)
> 
> I am very satisfied with the speed improvement that MSVC 2012 has brought to 
> blender. I would love to see this in the wild. It could make some people very 
> happy.
> 
> I would volunteer to maintain this build platform if desired.
> 
> /Jürgen
> 
> 
> Am 10.05.2013 um 20:17 schrieb Antony Riakiotakis :
> 
>> According to the MinGW64 developers, the math library implementation is
>> faster for gcc. The simulations use openmp which is disabled in MinGW64 due
>> to their buggy pthread implementation which makes openmp hang when used
>> during pthread execution.
>> ___
>> Bf-committers mailing list
>> Bf-committers@blender.org
>> http://lists.blender.org/mailman/listinfo/bf-committers
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers

___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance on Windows

[Jürgen Herrmann]

Hi Ton, 

I would be proud to be a part of the blender team. I actually had some
patches in the Patch tracker that were committed by Brecht. He should be
able to judge about their quality.
Look here:
http://projects.blender.org/tracker/?func=detail&atid=127&aid=35158
http://projects.blender.org/tracker/?func=detail&atid=127&aid=35131
http://projects.blender.org/tracker/?func=detail&atid=127&aid=35234
http://projects.blender.org/tracker/?func=detail&atid=127&aid=35019
http://projects.blender.org/tracker/index.php?func=detail&aid=35153

I have a full set of x64 prerequisite libs freshly compiled and I am
currently working on compiling the x86 libs.
I've also extended the CMakeFiles to include the new libs and compiler
settings. I always doublecheck all changes with VC2008 so I don't break
compatibility.

/Jürgen.

-Ursprüngliche Nachricht-
Von: bf-committers-boun...@blender.org
[mailto:bf-committers-boun...@blender.org] Im Auftrag von Ton Roosendaal
Gesendet: Samstag, 11. Mai 2013 18:43
An: bf-blender developers
Betreff: Re: [Bf-committers] Cycles performance on Windows

Hi Jurgen,

You're very welcome to join the windows platform team as maintainer for MSVC
2012.
Did you already have patches we should apply? We typically give people
commit access after a couple of good patches.

-Ton-


Ton Roosendaal  Blender Foundation   t...@blender.orgwww.blender.org
Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands

On 10 May, 2013, at 22:02, Jürgen Herrmann wrote:

> This sounds reasonable. So we need a lightning fast math library
replacement for MS compilers...
> I'm just kidding, but the idea might be insane enough to try ;)
> 
> I am very satisfied with the speed improvement that MSVC 2012 has brought
to blender. I would love to see this in the wild. It could make some people
very happy.
> 
> I would volunteer to maintain this build platform if desired.
> 
> /Jürgen
> 
> 
> Am 10.05.2013 um 20:17 schrieb Antony Riakiotakis :
> 
>> According to the MinGW64 developers, the math library implementation 
>> is faster for gcc. The simulations use openmp which is disabled in 
>> MinGW64 due to their buggy pthread implementation which makes openmp 
>> hang when used during pthread execution.
>> ___
>> Bf-committers mailing list
>> Bf-committers@blender.org
>> http://lists.blender.org/mailman/listinfo/bf-committers
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers

___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance on Windows

[Ton Roosendaal]

Hi Jürgen,

You've been added now, and should have a welcome mail in your inbox.
Thanks!

-Ton-


Ton Roosendaal  Blender Foundation   t...@blender.orgwww.blender.org
Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands

On 11 May, 2013, at 19:38, Jürgen Herrmann wrote:

> Hi Ton, 
> 
> I would be proud to be a part of the blender team. I actually had some
> patches in the Patch tracker that were committed by Brecht. He should be
> able to judge about their quality.
> Look here:
> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35158
> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35131
> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35234
> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35019
> http://projects.blender.org/tracker/index.php?func=detail&aid=35153
> 
> I have a full set of x64 prerequisite libs freshly compiled and I am
> currently working on compiling the x86 libs.
> I've also extended the CMakeFiles to include the new libs and compiler
> settings. I always doublecheck all changes with VC2008 so I don't break
> compatibility.
> 
> /Jürgen.
> 
> -Ursprüngliche Nachricht-
> Von: bf-committers-boun...@blender.org
> [mailto:bf-committers-boun...@blender.org] Im Auftrag von Ton Roosendaal
> Gesendet: Samstag, 11. Mai 2013 18:43
> An: bf-blender developers
> Betreff: Re: [Bf-committers] Cycles performance on Windows
> 
> Hi Jurgen,
> 
> You're very welcome to join the windows platform team as maintainer for MSVC
> 2012.
> Did you already have patches we should apply? We typically give people
> commit access after a couple of good patches.
> 
> -Ton-
> 
> 
> Ton Roosendaal  Blender Foundation   t...@blender.orgwww.blender.org
> Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands
> 
> On 10 May, 2013, at 22:02, Jürgen Herrmann wrote:
> 
>> This sounds reasonable. So we need a lightning fast math library
> replacement for MS compilers...
>> I'm just kidding, but the idea might be insane enough to try ;)
>> 
>> I am very satisfied with the speed improvement that MSVC 2012 has brought
> to blender. I would love to see this in the wild. It could make some people
> very happy.
>> 
>> I would volunteer to maintain this build platform if desired.
>> 
>> /Jürgen
>> 
>> 
>> Am 10.05.2013 um 20:17 schrieb Antony Riakiotakis :
>> 
>>> According to the MinGW64 developers, the math library implementation 
>>> is faster for gcc. The simulations use openmp which is disabled in 
>>> MinGW64 due to their buggy pthread implementation which makes openmp 
>>> hang when used during pthread execution.
>>> ___
>>> Bf-committers mailing list
>>> Bf-committers@blender.org
>>> http://lists.blender.org/mailman/listinfo/bf-committers
>> ___
>> Bf-committers mailing list
>> Bf-committers@blender.org
>> http://lists.blender.org/mailman/listinfo/bf-committers
> 
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
> 
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers

___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance on Windows

[Jürgen Herrmann]

Hi Ton,

Just got it ;-) Thank you very much!
I'll read the rules completely first, promised :-D

Thanks
Jürgen

Am 13.05.2013 um 18:00 schrieb Ton Roosendaal :

> Hi Jürgen,
> 
> You've been added now, and should have a welcome mail in your inbox.
> Thanks!
> 
> -Ton-
> 
> 
> Ton Roosendaal  Blender Foundation   t...@blender.orgwww.blender.org
> Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands
> 
> On 11 May, 2013, at 19:38, Jürgen Herrmann wrote:
> 
>> Hi Ton, 
>> 
>> I would be proud to be a part of the blender team. I actually had some
>> patches in the Patch tracker that were committed by Brecht. He should be
>> able to judge about their quality.
>> Look here:
>> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35158
>> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35131
>> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35234
>> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35019
>> http://projects.blender.org/tracker/index.php?func=detail&aid=35153
>> 
>> I have a full set of x64 prerequisite libs freshly compiled and I am
>> currently working on compiling the x86 libs.
>> I've also extended the CMakeFiles to include the new libs and compiler
>> settings. I always doublecheck all changes with VC2008 so I don't break
>> compatibility.
>> 
>> /Jürgen.
>> 
>> -Ursprüngliche Nachricht-----
>> Von: bf-committers-boun...@blender.org
>> [mailto:bf-committers-boun...@blender.org] Im Auftrag von Ton Roosendaal
>> Gesendet: Samstag, 11. Mai 2013 18:43
>> An: bf-blender developers
>> Betreff: Re: [Bf-committers] Cycles performance on Windows
>> 
>> Hi Jurgen,
>> 
>> You're very welcome to join the windows platform team as maintainer for MSVC
>> 2012.
>> Did you already have patches we should apply? We typically give people
>> commit access after a couple of good patches.
>> 
>> -Ton-
>> 
>> 
>> Ton Roosendaal  Blender Foundation   t...@blender.orgwww.blender.org
>> Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands
>> 
>> On 10 May, 2013, at 22:02, Jürgen Herrmann wrote:
>> 
>>> This sounds reasonable. So we need a lightning fast math library
>> replacement for MS compilers...
>>> I'm just kidding, but the idea might be insane enough to try ;)
>>> 
>>> I am very satisfied with the speed improvement that MSVC 2012 has brought
>> to blender. I would love to see this in the wild. It could make some people
>> very happy.
>>> 
>>> I would volunteer to maintain this build platform if desired.
>>> 
>>> /Jürgen
>>> 
>>> 
>>> Am 10.05.2013 um 20:17 schrieb Antony Riakiotakis :
>>> 
>>>> According to the MinGW64 developers, the math library implementation 
>>>> is faster for gcc. The simulations use openmp which is disabled in 
>>>> MinGW64 due to their buggy pthread implementation which makes openmp 
>>>> hang when used during pthread execution.
>>>> ___
>>>> Bf-committers mailing list
>>>> Bf-committers@blender.org
>>>> http://lists.blender.org/mailman/listinfo/bf-committers
>>> ___
>>> Bf-committers mailing list
>>> Bf-committers@blender.org
>>> http://lists.blender.org/mailman/listinfo/bf-committers
>> 
>> ___
>> Bf-committers mailing list
>> Bf-committers@blender.org
>> http://lists.blender.org/mailman/listinfo/bf-committers
>> 
>> ___
>> Bf-committers mailing list
>> Bf-committers@blender.org
>> http://lists.blender.org/mailman/listinfo/bf-committers
> 
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers

Re: [Bf-committers] Cycles performance on Windows

[Gavin Howard]

Congratulations, Jürgen!
Gavin H.


On Mon, May 13, 2013 at 12:20 PM, Jürgen Herrmann  wrote:

> Hi Ton,
>
> Just got it ;-) Thank you very much!
> I'll read the rules completely first, promised :-D
>
> Thanks
> Jürgen
>
> Am 13.05.2013 um 18:00 schrieb Ton Roosendaal :
>
> > Hi Jürgen,
> >
> > You've been added now, and should have a welcome mail in your inbox.
> > Thanks!
> >
> > -Ton-
> >
> > 
> > Ton Roosendaal  Blender Foundation   t...@blender.orgwww.blender.org
> > Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands
> >
> > On 11 May, 2013, at 19:38, Jürgen Herrmann wrote:
> >
> >> Hi Ton,
> >>
> >> I would be proud to be a part of the blender team. I actually had some
> >> patches in the Patch tracker that were committed by Brecht. He should be
> >> able to judge about their quality.
> >> Look here:
> >> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35158
> >> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35131
> >> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35234
> >> http://projects.blender.org/tracker/?func=detail&atid=127&aid=35019
> >> http://projects.blender.org/tracker/index.php?func=detail&aid=35153
> >>
> >> I have a full set of x64 prerequisite libs freshly compiled and I am
> >> currently working on compiling the x86 libs.
> >> I've also extended the CMakeFiles to include the new libs and compiler
> >> settings. I always doublecheck all changes with VC2008 so I don't break
> >> compatibility.
> >>
> >> /Jürgen.
> >>
> >> -Ursprüngliche Nachricht-
> >> Von: bf-committers-boun...@blender.org
> >> [mailto:bf-committers-boun...@blender.org] Im Auftrag von Ton
> Roosendaal
> >> Gesendet: Samstag, 11. Mai 2013 18:43
> >> An: bf-blender developers
> >> Betreff: Re: [Bf-committers] Cycles performance on Windows
> >>
> >> Hi Jurgen,
> >>
> >> You're very welcome to join the windows platform team as maintainer for
> MSVC
> >> 2012.
> >> Did you already have patches we should apply? We typically give people
> >> commit access after a couple of good patches.
> >>
> >> -Ton-
> >>
> >> 
> >> Ton Roosendaal  Blender Foundation   t...@blender.orgwww.blender.org
> >> Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands
> >>
> >> On 10 May, 2013, at 22:02, Jürgen Herrmann wrote:
> >>
> >>> This sounds reasonable. So we need a lightning fast math library
> >> replacement for MS compilers...
> >>> I'm just kidding, but the idea might be insane enough to try ;)
> >>>
> >>> I am very satisfied with the speed improvement that MSVC 2012 has
> brought
> >> to blender. I would love to see this in the wild. It could make some
> people
> >> very happy.
> >>>
> >>> I would volunteer to maintain this build platform if desired.
> >>>
> >>> /Jürgen
> >>>
> >>>
> >>> Am 10.05.2013 um 20:17 schrieb Antony Riakiotakis :
> >>>
> >>>> According to the MinGW64 developers, the math library implementation
> >>>> is faster for gcc. The simulations use openmp which is disabled in
> >>>> MinGW64 due to their buggy pthread implementation which makes openmp
> >>>> hang when used during pthread execution.
> >>>> ___
> >>>> Bf-committers mailing list
> >>>> Bf-committers@blender.org
> >>>> http://lists.blender.org/mailman/listinfo/bf-committers
> >>> ___
> >>> Bf-committers mailing list
> >>> Bf-committers@blender.org
> >>> http://lists.blender.org/mailman/listinfo/bf-committers
> >>
> >> ___
> >> Bf-committers mailing list
> >> Bf-committers@blender.org
> >> http://lists.blender.org/mailman/listinfo/bf-committers
> >>
> >> ___
> >> Bf-committers mailing list
> >> Bf-committers@blender.org
> >> http://lists.blender.org/mailman/listinfo/bf-committers
> >
> > ___
> > Bf-committers mailing list
> > Bf-committers@blender.org
> > http://lists.blender.org/mailman/listinfo/bf-committers
> ___
> Bf-committers mailing list
> Bf-committers@blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
>
___
Bf-committers mailing list
Bf-committers@blender.org
http://lists.blender.org/mailman/listinfo/bf-committers