opencv 3.1 - CUDA 8.0.44 - ubuntu 16.04 - driver 367.57 - gcc 5.4.0

edit

Couldn't find anyone with these compilation errors:

As with the title I'm installing: opencv 3.1 - CUDA 8.0.44 - ubuntu 16.04 - driver 367.57 - gcc 5.4.0

I get to 70% build, when it fails in graphcuts.cpp. There are many errors but they all have to do with NppiGraphcutState.

/home/willem/software/opencv/opencv-3.1.0/modules/cudalegacy/src/graphcuts.cpp:120:54: error: ‘NppiGraphcutState’ has not been declared
 typedef NppStatus (*init_func_t)(NppiSize oSize, NppiGraphcutState** ppState, Npp8u* pDeviceMem);

cmake command:

cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D WITH_CUDA=ON \
-D ENABLE_FAST_MATH=1 \
-D CUDA_FAST_MATH=1 \
-D WITH_CUBLAS=1 \
-D INSTALL_PYTHON_EXAMPLES=ON \
-D BUILD_EXAMPLES=ON ..

device query:

Device 0: "GeForce GTX 1070"
CUDA Driver Version / Runtime Version          8.0 / 8.0
CUDA Capability Major/Minor version number:    6.1
Total amount of global memory:                 8112 MBytes (8506179584 bytes)
(15) Multiprocessors, (128) CUDA Cores/MP:     1920 CUDA Cores
GPU Max Clock rate:                            1772 MHz (1.77 GHz)
Memory Clock rate:                             4004 Mhz
Memory Bus Width:                              256-bit
L2 Cache Size:                                 2097152 bytes
Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers
Total amount of constant memory:               65536 bytes
Total amount of shared memory per block:       49152 bytes
Total number of registers available per block: 65536
Warp size:                                     32
Maximum number of threads per multiprocessor:  2048
Maximum number of threads per block:           1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch:                          2147483647 bytes
Texture alignment:                             512 bytes
Concurrent copy and kernel execution:          Yes with 2 copy engine(s)
Run time limit on kernels:                     Yes
Integrated GPU sharing Host Memory:            No
Support host page-locked memory mapping:       Yes
Alignment requirement for Surfaces:            Yes
Device has ECC support:                        Disabled
Device supports Unified Addressing (UVA):      Yes
Device PCI Domain ID / Bus ID / location ID:   0 / 1 / 0
Compute Mode:
 < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 8.0, CUDA Runtime Version = 8.0, NumDevs = 1, Device0 = GeForce GTX 1070
Result = PASS

Do I need a lower version of gcc? Any ideas?