-5 is an out of resources error.
You could try to use
-w 32
to reduce the memoy load for the gpu.
With -w 32 it segfaults
[2014-11-09 22:37:27] Found platform[0] name = NVIDIA CUDA
[2014-11-09 22:37:27] Found 1 device(s)
[2014-11-09 22:37:27] Loaded kernel binary size = 969615 bytes
[2014-11-09 22:37:27] Using GPU 0 [GRID K520]: which has 8 CUs
[2014-11-09 22:37:28] Got new target: 22.7124838 @ 22.7124838
Segmentation fault (core dumped)
--- SIGSEGV {si_signo=SIGSEGV, si_code=SEGV_ACCERR, si_addr=0x7ffc85400a30} ---