[Gegl-developer] Cache strategy

[Patrik Östman]

Hi.

I repost my previous message because of bad formatting. 
Hope this will be better...

I have some questions regarding the cache strategy in gegl.
I have tested using both 0.0.20 and 0.0.22 and I find them 
different in the way nodes are cached.

GEGL 0.0.20:
Creating the graph below:
1
|
2
|
3
|
4

Rendering node 4 and after that rendering node 2.  
When rendering node 2 the output is taken from the cache 
because it is already calculated when rendering node 4. 
This is also that I had expected. Now linking node 2 to 
node 5 and creating a new branch:
1
|
2--
|    |
3   5
|
4 

Rendering node 4 again and the graph is rendered from 
node 2 to node 4. This should not be necessary because 
the output of node 2 is not changed when the output pad
 of node 2 is connected to another node. 
What is the reason for this?

GEGL 0.0.22
In gegl 0.0.22 I are not able to use any cached node output
other than the last rendered node output. E.g. creating the 
first graph above, rendering node 4 and after that rendering 
node 4 again getting the result from cache.  But if rendering 
node 2 (after rendering node 4) the graph is rendered from 
node 1  to node 2. Are there any significant changes of cache 
handling done between 0.0.20 and 0.0.22 or are there a 
setting that must be turned on to get 'per node caches' 
functionality?


Another question: What is the difference between 
GEGL_BLIT_CACHE and GEGL_BLIT_DEFAULT flags of the 
'blit' function?

Regards
Patrik Östman