stewartmiles
commented
8 years ago A good starting point for this would be to profile an application (e.g the Testbed) to determine which areas are most expensive given a particular simulation. This would enable you to determine where to focus optimization efforts.
If you're running on Linux boxes consider using https://perf.wiki.kernel.org/index.php/Main_Page If you're using OS X you could profile using XCode Instruments On Windows there is a huge selection VTune, AMD CodeX, Visual Studio Profiling Tools etc.
Jason (see the git log) - after profiling - spent a lot of time rewriting the particle simulation in ARM SIMD which yielded significant gains. An x86_64 version using intrinsics may be reasonable and maintainable. You could also try plumbing MathFu https://github.com/google/mathfu in to get SIMD optimization across the library to see whether that yields a gain.
Cheers, Stewart
On Tue, Oct 6, 2015 at 12:17 PM, Patrick Drumm notifications@github.com wrote:
Hello all,
Similarly to Jim Hye (who posted an issue about a year and a half ago), my team and I found LiquidFun very intriguing and have selected it as the subject of our final project. Rather than parallelizing the code however, we are looking for ways to make LiquidFun run faster or more efficiently relating to data stuctures. Basically we are looking for anywhere in the program that might slow up a little bit - where we might be able to implement an alternative, more efficient sorting algorithm, searching algorithm, or data structure to store things.
We would appreciate any advice as to where in the program these optimizations might be most useful!
Thanks, Patrick Drumm
— Reply to this email directly or view it on GitHub https://github.com/google/liquidfun/issues/57.
Razzlegames
migdalskiy
Hello all,
Similarly to Jim Hye (who posted an issue about a year and a half ago), my team and I found LiquidFun very intriguing and have selected it as the subject of our final project. Rather than parallelizing the code however, we are looking for ways to make LiquidFun run faster or more efficiently relating to data stuctures. Basically we are looking for anywhere in the program that might slow up a little bit - where we might be able to implement an alternative, more efficient sorting algorithm, searching algorithm, or data structure to store things.
We would appreciate any advice as to where in the program these optimizations might be most useful!
Thanks, Patrick Drumm