Blender Farm - Histórico de revisão

V1z: 12598d8

2015-10-02T23:04:59Z

12598d8

← Edição anterior		Edição das 20h04min de 2 de outubro de 2015
Linha 45:		Linha 45:

	== Multiple nodes ==		== Multiple nodes ==
			=== Manual GUI approach for multiple nodes ===

			====Netrender====
			The main instructions are: [http://wiki.blender.org/index.php/Doc%3A2.6/Manual/Render/Performance/Netrender]
			* Activate Preferences - addons - Render - Network Render
			* On the Render Context, you'll have options such as Client/Master/Slave
			* Follow the instructions in the aforementioned link

			=== Automation for multiple nodes ===
	We wrote scripts on a software package called '''bfarmx''' to control blender		We wrote scripts on a software package called '''bfarmx''' to control blender
	using Netrender to distribute frames. These are still in a very early experimental phase.		using Netrender to distribute frames. These are still in a very early experimental phase.
Linha 50:		Linha 59:
	http://github.com/rfabbri/bfarmx		http://github.com/rfabbri/bfarmx

	=== Installing Blender on a Cluster ===		=== Other Approaches ===

			* Flamenco: Very large scale job render management [https://gooseberry.blender.org/announcing-flamenco-2-0alpha-release]
			** A much larger system, but the more primitive netrender techniques above are still useful for learning purposes and for small experiments due to their simplicity.

			=== Installing Blender on each node of a Cluster ===

	The easiest way was to download the self-contained binary tarball from the		The easiest way was to download the self-contained binary tarball from the

V1z: 6cafb52

2015-10-02T21:03:42Z

6cafb52

← Edição anterior		Edição das 18h03min de 2 de outubro de 2015
Linha 35:		Linha 35:

	== Single node GPU parallel rendering ==		== Single node GPU parallel rendering ==

	# Install NVidia CUDA on a linux or [[Mac]] OSX node (follow a post on stackoverflow by Gandalf)		# Install NVidia CUDA on a linux or [[Mac]] OSX node (follow a post on stackoverflow by Gandalf)
	# If you succeeded, then GPU will ~~show up~~ in preferences:		# If you succeeded, then GPU will showup in preferences:
	# Go to Preferences - System. Compute device must show CUDA (likely OpenCL too). Select that.		# Go to Preferences - System. Compute device must show CUDA (likely OpenCL too). Select that.
	# On the render context, set Compute Device to GPU. Make sure the Cycles Render engine is selected.		# On the render context, set Compute Device to GPU. Make sure the Cycles Render engine is selected.
Linha 43:		Linha 44:
	==== Choosing the block size ====		==== Choosing the block size ====

	== Multiple ~~node~~ ==		== Multiple nodes ==
	We wrote scripts on a software package called '''bfarmx''' to control blender		We wrote scripts on a software package called '''bfarmx''' to control blender
	using Netrender to distribute frames. These are still in a very early experimental phase.		using Netrender to distribute frames. These are still in a very early experimental phase.
	Dowload them at:		Dowload them at:
	http://github.com/rfabbri/bfarmx		http://github.com/rfabbri/bfarmx

			=== Installing Blender on a Cluster ===

			The easiest way was to download the self-contained binary tarball from the
			downloads section of the official website (it runs on most distros), then install that on the cluster,
			either in the user NFS home folder (install once for the entire cluster),
			or system-wide at each node.


	== See Also ==		== See Also ==

V1z: /* Single node GPU parallel rendering */

2015-10-02T20:16:40Z

Single node GPU parallel rendering

← Edição anterior		Edição das 17h16min de 2 de outubro de 2015
Linha 35:		Linha 35:

	== Single node GPU parallel rendering ==		== Single node GPU parallel rendering ==

	# Install NVidia CUDA on a linux or [[Mac]] OSX node (follow a post on stackoverflow by Gandalf)		# Install NVidia CUDA on a linux or [[Mac]] OSX node (follow a post on stackoverflow by Gandalf)
	# If you succeeded, then GPU will ~~showup~~ in preferences:		# If you succeeded, then GPU will show up in preferences:
	# Go to Preferences - System. Compute device must show CUDA (likely OpenCL too). Select that.		# Go to Preferences - System. Compute device must show CUDA (likely OpenCL too). Select that.
	# On the render context, set Compute Device to GPU.		# On the render context, set Compute Device to GPU. Make sure the Cycles Render engine is selected.

	=== Optimizing parameters ===		=== Optimizing parameters ===

V1z: acbe7ab

2015-10-02T20:15:30Z

acbe7ab

@@ Linha 8: / Linha 8: @@
 from a fairly complex scene using the Cycles engine.
-=== Test Data / Sample Applications ===
+=== Test Data / Applications ===
 To feel the need for high-performance numeric crunching, download the a demo
 file from
@@ Linha 24: / Linha 24: @@
 In practice, we'd like to setup a workflow where we render a scene under multiple conditions and parameters, eg to generate ground-truth for big-data apps such as machine learning and computer vision as in 3D reconstrution and Video Understanding.
-Another applicatio would be to devise real-time computer vision systems to process the videos, which is effectively inverse computer graphics.
+Another application would be to devise real-time computer vision systems to process the videos, which is effectively inverse computer graphics.
 == See Also ==
@@ Linha 32: / Linha 56: @@
 Douglas Pio, Hilton Guaraldi and Ricardo Fabbri
-Polytechnic Institute at UERJ - Rio de Janeiro State University
+* [[IPRJ|Polytechnic Institute at UERJ - Rio de Janeiro State University]]
-http://pt.wikipedia.org/wiki/IPRJ
+* [[Lab Macambira]]

V1z: https://github.com/rfabbri/bfarmx/commit/a873b2ede533484792d9a33380e28aab7d580c52

2015-10-02T19:53:04Z

https://github.com/rfabbri/bfarmx/commit/a873b2ede533484792d9a33380e28aab7d580c52

Página nova

We describe some basic experiments on running Blender on
a hybrid compute cluster.

== Goal ==

One main goal is to speed up rendering.
Full HD Videos can take weeks to render
from a fairly complex scene using the Cycles engine.

=== Test Data / Sample Applications ===
To feel the need for high-performance numeric crunching, download the a demo
file from

https://www.blender.org/download/demo-files

The barcelona pavilion scene won't even load on a 1GB NVidia GPU (it says: out of memory)!
An SD video with 100 frames takes over 3 days on a top-of-the-line Core i7 (as of 2015).

On our compute cluster with Tesla GPUs, each having 4GB RAM, Blender is able to render such videos,
but is still not fast enough to render the entire video in reasonable time. Therefore, we'd like to use both CPU and GPU, and distribute frames to be rendered across nodes.

We have Xeon Phi's as well, which we'd like to use as CPU-rendering within blender, but with a high number of threads (over 100).

In practice, we'd like to setup a workflow where we render a scene under multiple conditions and parameters, eg to generate ground-truth for big-data apps such as machine learning and computer vision as in 3D reconstrution and Video Understanding.

Another applicatio would be to devise real-time computer vision systems to process the videos, which is effectively inverse computer graphics.

== See Also ==
* [[Introduction to Parallel Computing]]: a graduate-level course on parallel computing taught at [[IPRJ]]

== Contact ==

Douglas Pio, Hilton Guaraldi and Ricardo Fabbri
Polytechnic Institute at UERJ - Rio de Janeiro State University
http://pt.wikipedia.org/wiki/IPRJ
www.iprj.uerj.br
labMacambira.sf.net

[[Category: Grafico]]
[[Category: Video]]
[[Category: Blender]]
[[Category: Linux]]
[[Category: IPRJ]]
[[Category: Lab Macambira]]