Hey,
should “Distrube memory across devices” work in Blender 3?
I’ve 2x RTX 2080ti with NVLink.
In Blender 2.93 I was able to render a 17GB scene via memory pooling (at least as long Blender didn’t lost the focus, otherwise I got an error message).
But in Blender 3.0 I just get this error, even if Blender stays in focus:
Failed to build OptiX acceleration structure
OPTIX_ERROR_INVALID_VALUE in optixAccelBuild(context, 0, &options, &build_input, 1, temp_mem.device_pointer, sizes.tempSizeInBytes, out_data.device_pointer, sizes.outputSizeInBytes, &out_handle, use_fast_trace_bvh ? &compacted_size_prop : 0, use_fast_trace_bvh ? 1 : 0) (C:\Users\blender\git\blender-v300\blender.git\intern\cycles\device\optix\device_impl.cpp:1066)OPTIX_ERROR_INVALID_VALUE in optixAccelBuild(context, 0, &options, &build_input, 1, temp_mem.device_pointer, sizes.tempSizeInBytes, out_data.device_pointer, sizes.outputSizeInBytes, &out_handle, use_fast_trace_bvh ? &compacted_size_prop : 0, use_fast_trace_bvh ? 1 : 0) (C:\Users\blender\git\blender-v300\blender.git\intern\cycles\device\optix\device_impl.cpp:1066)
Is memory pooling working for you in Blender 3.0?