Tweet
Hi,
For some reason I am not able to post this in the RT section of the forum.
This is the full error that I get: ./src/ocl_tracedevice.cpp(4047) : CUDA error 2 : unable to allocate enough memory to perform the requested operation (out-of-mem)
I understand that it seems like the GPU is out of memory. In order for me to adjust my scene, I need to know how far over the memory limit I am. Is there any way to see how big the memory requirements are?
I am running an 8gb GTX 1080. Note that renders do work when I render simple scenes, so I know RT is working.
I see here that hair is 4.6 gbs worth of space. What is the "hair" in scenes?
Mtls 439.81MB, Geo 912.92MB, Lights 16.03MB, LightCache 0.00MB, Hair 4655.97MB, Other 261.92MB (data index 467891)
Building optimized CUDA kernel (0) for comp cap 6.1 for device 0...
PTX file generated with CUDA Toolkit v7.5 for CUDA compute capability 2.0
Optimized CUDA kernel assembled successfully
Total memory for device 0 : 8192 MB, free 38 MB
./src/ocl_tracedevice.cpp(4047) : CUDA error 2 : unable to allocate enough memory to perform the requested operation (out-of-mem)
Device 0 statistics:
GPU time: 0.619208 %
GPU ray trace time -1.#IND00 %
Transfer to GPU time -1.#IND00 %
Transfer from GPU time -1.#IND00 %
Closing RTEngine (cancelled)
For some reason I am not able to post this in the RT section of the forum.
This is the full error that I get: ./src/ocl_tracedevice.cpp(4047) : CUDA error 2 : unable to allocate enough memory to perform the requested operation (out-of-mem)
I understand that it seems like the GPU is out of memory. In order for me to adjust my scene, I need to know how far over the memory limit I am. Is there any way to see how big the memory requirements are?
I am running an 8gb GTX 1080. Note that renders do work when I render simple scenes, so I know RT is working.
I see here that hair is 4.6 gbs worth of space. What is the "hair" in scenes?
Mtls 439.81MB, Geo 912.92MB, Lights 16.03MB, LightCache 0.00MB, Hair 4655.97MB, Other 261.92MB (data index 467891)
Building optimized CUDA kernel (0) for comp cap 6.1 for device 0...
PTX file generated with CUDA Toolkit v7.5 for CUDA compute capability 2.0
Optimized CUDA kernel assembled successfully
Total memory for device 0 : 8192 MB, free 38 MB
./src/ocl_tracedevice.cpp(4047) : CUDA error 2 : unable to allocate enough memory to perform the requested operation (out-of-mem)
Device 0 statistics:
GPU time: 0.619208 %
GPU ray trace time -1.#IND00 %
Transfer to GPU time -1.#IND00 %
Transfer from GPU time -1.#IND00 %
Closing RTEngine (cancelled)
Comment