Hello, I did ran afew more tests on 256x256 maps. To get some measurable improvement, I had to make some variations, but the code is more complex. At the end of the e-mail you can see the result from the latest code, to the best way I found with your idea. You can see a 2.5% improvement. That is a relative 8% improvement.
Now, the CVS is using the same code, but I put my working implementation of your idea into comment. When you have a chance to get this code, please run some wide tests to find out the fastest and cleanest way. It's not that I don't want to add your idea now. But it increases the complexitly of the code much, and maybe, another totaly different idea may increase the speed more significalty. So if you either find a simpler way, or a bit faster way, we'll definitively take it. You got the idea ? Nuage before: cpu usage graph: 100.0 % | ** 98.5 % | 95.0 % | 93.5 % | 90.0 % | 88.5 % | 85.0 % | 83.5 % | 80.0 % | 78.5 % | * 75.0 % | 73.5 % | 70.0 % | * 68.5 % | 65.0 % | 63.5 % | * 60.0 % | * 58.5 % | * 55.0 % | ** 53.5 % | *** 50.0 % | *** 48.5 % | ***** 45.0 % | ******* 43.5 % | *************** 40.0 % | *********** 38.5 % | ************ 35.0 % | ************** 33.5 % | ********** 30.0 % | **** 28.5 % | **** 25.0 % | 23.5 % | 20.0 % | 18.5 % | 15.0 % | 13.5 % | 10.0 % | 8.5 % | 5.0 % | 3.5 % | 0.0 % | after: cpu usage graph: 100.0 % | ** 98.5 % | 95.0 % | 93.5 % | 90.0 % | 88.5 % | 85.0 % | 83.5 % | 80.0 % | 78.5 % | 75.0 % | 73.5 % | 70.0 % | * 68.5 % | * 65.0 % | * 63.5 % | 60.0 % | * 58.5 % | * 55.0 % | * 53.5 % | ** 50.0 % | *** 48.5 % | ** 45.0 % | **** 43.5 % | ********* 40.0 % | ************* 38.5 % | ********* 35.0 % | *********** 33.5 % | **************** 30.0 % | ********* 28.5 % | ***** 25.0 % | ******** 23.5 % | 20.0 % | 18.5 % | 15.0 % | 13.5 % | 10.0 % | 8.5 % | 5.0 % | 3.5 % | 0.0 % | _______________________________________________ glob2-devel mailing list [email protected] http://lists.nongnu.org/mailman/listinfo/glob2-devel
