Please try out the patch and apply it to the source tree if you like it ;-)
--
Georg Acher, [EMAIL PROTECTED]
http://www.in.tum.de/~acher/
"Oh no, not again !" The bowl of petunias
--- whirlpinch.c.orgThu Apr 5 17:47:17 2001
++
4 and a P5.
Both have only very small L1-caches (Alpha has 8K) and relatively slow L2
caches (+L3 for Alpha). The best blocking factor for those CPUs was between
64 and 128. My Athlon now also tolerates 512, 32 only is only slightly (2%)
slower, but should work for all CPUs fairly good.
--
problem. I changed the code to get 32 rows,
calculate them and the write the 32 back. It took only 3s overall, the
resulting image is the same as with the 30s boiling time.
That's a speedup of 10!
Can someone please try the patch and confirm that I'm not dreaming
big knowledge of Gimp's internals, but that
seems preety easy to find out...
--
Georg Acher, [EMAIL PROTECTED]
http://www.in.tum.de/~acher/
"Oh no, not again !" The bowl of petunias
___
Gimp-developer mailing list
[EMAIL PROTECTED]
http://lists.xcf.berkeley.edu/mailman/listinfo/gimp-developer