ERROR: cuLaunchKernel() 1

[mailmuncher2000]

Yup! I have a GTS250 (win7 64bit with NVIDIA drivers v314.22) and was getting the same error. Experimenting with couple of different -u -n settings didn't help either (same problem with cudahashcat 32bit and 64 bit) I'm trying to narrow down whats causing it. So far as I can see it only happens with brute force mode i.e. -a3

Also so far it seems to be helping to remove the --increment attribute (though I am pretty sure I had this happen when I didn't use increment as well):
eg1:
WORKS:
cudaHashcat-plus64 -a3 -m 1000 --gpu-temp-abort=100 --remove -u 1024 -n 8 --markov-hcstat=..\all_hashcat.hcstat -t 100 -o ..\all_ntlm.out ..\all_ntlm.txt ?a?a?a?a?a?a?a?a?a

DOESN'T WORK:
cudaHashcat-plus64 -a3 -m 1000 --gpu-temp-abort=100 --increment --remove -u 1024 -n 8 --markov-hcstat=..\all_hashcat.hcstat -t 100 -o ..\all_ntlm.out ..\all_ntlm.txt ?a?a?a?a?a?a?a?a?a

ERROR:
Workload: 1024 loops, 8 accel
Watchdog: Temperature abort trigger set to 100c
Watchdog: Temperature retain trigger set to 80c
Device #1: GeForce GTS 250, 1024MB, 1836Mhz, 16MCU
Device #1: Kernel ./kernels/4318/m1000_a3.sm_11.64.ptx

[s]tatus [p]ause [r]esume [b]ypass [q]uit => ERROR: cuLaunchKernel() 1

eg2:
WORKS:
cudaHashcat-plus64 -a3 -m 1000 --gpu-temp-abort=100 --remove -u 1024 -n 8 -o ..\all_ntlm.out ..\all_ntlm.txt ?a?a?a?a?a?a?a?a?a

DOESN'T WORK:
cudaHashcat-plus64 -a3 -m 1000 --gpu-temp-abort=100 --remove --increment -u 1024 -n 8 -o ..\all_ntlm.out ..\all_ntlm.txt ?a?a?a?a?a?a?a?a?a

In fact this time my screen flashed off and my driver popped up a driver reset message in additional to the above ERROR: cuLaunchKernel() 1