Update performance note.

This commit is contained in:
Syoyo Fujita
2016-07-09 01:31:13 +09:00
parent b8c33156de
commit d2793bf454

View File

@@ -158,8 +158,9 @@ Note that the optimized loader uses C++11 thread and it does less error checks b
Here is some benchmark result. Time are measured on MacBook 12(Early 2016, Core m5 1.2GHz). Here is some benchmark result. Time are measured on MacBook 12(Early 2016, Core m5 1.2GHz).
* Rungholt scene(6M triangles) * Rungholt scene(6M triangles)
* baseline: 6800 msecs * old version(v0.9.x): 15500 msecs.
* optimised: 1500 msecs(4.5x faster) * baseline(v1.0.x): 6800 msecs(2.3x faster than old version)
* optimised: 1500 msecs(10x faster than old version, 4.5x faster than basedline)
Tests Tests