* BVH building was multithreaded. Not all building is multithreaded, packing
and the initial bounding/splitting is still single threaded, but recursive
splitting is, which was the main bottleneck.
* Object splitting now uses binning rather than sorting of all elements, using
code from the Embree raytracer from Intel.
http://software.intel.com/en-us/articles/embree-photo-realistic-ray-tracing-kernels/
* Other small changes to avoid allocations, pack memory more tightly, avoid
some unnecessary operations, ...
These optimizations do not work yet when Spatial Splits are enabled, for that
more work is needed. There's also other optimizations still needed, in
particular for the case of many low poly objects, the packing step and node
memory allocation.
BVH raytracing time should remain about the same, but BVH build time should be
significantly reduced, test here show speedup of about 5x to 10x on a dual core
and 5x to 25x on an 8-core machine, depending on the scene.
CPU device threading code wrapped into something reusable.
Basic idea is that there is a single TaskScheduler that keeps a pool of threads,
one for each core. Other places in the code can then create a TaskPool that they
can drop Tasks in to be executed by the scheduler, and wait for them to complete
or cancel them early.
- memset(..., 1.0); // isnt valid
- memset(pointer, sizeof(pointer)) // was using the sizeof the pointer, not the size of the array, since this was to fill in alpha values it was obviously wrong.
http://sourceforge.net/projects/mingw-w64/files/Toolchains%20targetting%20Win64/Personal%20Builds/ray_linn/GCC-4.7.0-with-ada/mingw-w64-gcc-4.7.0-runtime-2.0.1-static-ada-20120330.7z/download
Other builds may also work but due to the constantly changing nature of the compiler this cannot be guaranteed. I often had to change compilers while building the libraries and this one is the one that did the job for most of them.
This first support is experimental and considered "advanced". To enable pass -DWITH_MINGW64 during cmake configuration. Also make sure to extract the compiler on C:/MinGW and that MinGW/bin is in your path. To build check out lib/mingw64.
Initially the support is lacking until I get every library compiled correctly. For now you should disable WITH_CYCLES(sorry, I know some people are dying to do benchmarks, but still a few libs to go), WITH_IMAGE_OPENEXR, WITH_OPENCOLLADA, WITH_LIBMV and WITH_CODEC_FFMPEG(links but hangs on startup).
Still the tools are working, the memory limit is increased and due to the experimental nature of the setup, full optimization with SSE2 is available, which makes the build quite fast. Also the compiler and especially, the linker are way faster than regular MinGW.
The wiki docs have also updated. Happy testing!
Remark: I think that "!(nbored & CFBnd)" would be correct but it introduced other bugs so, I just quiet compiler warnings leaving the running system untouched.
