Brecht Van Lommel ea4ce9e4ea Cycles: centralized task scheduler for multithreading, which is basically the ...

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.

2012-04-24 11:43:41 +00:00

..

CMakeLists.txt

add some missing headers to cmake, also add some files as comments since it seems they should be added but evidently work fine without.

2011-11-10 06:05:22 +00:00

device_cpu.cpp

Cycles: centralized task scheduler for multithreading, which is basically the

2012-04-24 11:43:41 +00:00

device_cuda.cpp

Cycles: another fix for CUDA render passes, needed to align float4 passes.

2012-01-27 13:58:32 +00:00

device_intern.h

Cycles: device code refactoring, no functional changes.

2012-01-04 18:06:32 +00:00

device_memory.h

Cycles: device code refactoring, no functional changes.

2012-01-04 18:06:32 +00:00

device_multi.cpp

Cycles: centralized task scheduler for multithreading, which is basically the

2012-04-24 11:43:41 +00:00

device_network.cpp

Cycles: render passes for CUDA cards with compute model >= 2.x.

2012-01-26 19:07:01 +00:00

device_network.h

code cleanup: white space, spelling & ';;' end of lines.

2012-02-25 16:04:03 +00:00

device_opencl.cpp

Cycles/OpenCL:

2012-04-09 17:44:33 +00:00

device.cpp

Cycles: centralized task scheduler for multithreading, which is basically the

2012-04-24 11:43:41 +00:00

device.h

Cycles: centralized task scheduler for multithreading, which is basically the

2012-04-24 11:43:41 +00:00