ERROR: cuLaunchKernel() 1
#1
Maybe it's the sleep deprivation, but am I missing something here? I've tried a few different drivers and eliminated as many command line switches I could.

Code:
>cudaHashcat-plus64.exe -m 0 example0.hash -a 3 ?l?l?l
cudaHashcat-plus v0.13 by atom starting...

Hashes: 6494 total, 1 unique salts, 6494 unique digests
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes
Workload: 256 loops, 80 accel
Watchdog: Temperature abort trigger set to 90c
Watchdog: Temperature retain trigger set to 80c
Device #1: GeForce 9800 GTX+, 512MB, 1836Mhz, 16MCU
Device #1: Kernel ./kernels/4318/m0000_a3.sm_11.ptx

[s]tatus [p]ause [r]esume [b]ypass [q]uit => ERROR: cuLaunchKernel() 1
#2
Seems to be that old card, cant reproduce locally. Try with -n 1 -u 1, also try 32 bit version and most important, update your driver (by hand, not by using distribution driver).
#3
(02-15-2013, 12:35 PM)atom Wrote: Seems to be that old card, cant reproduce locally. Try with -n 1 -u 1, also try 32 bit version and most important, update your driver (by hand, not by using distribution driver).

No difference with -n 1 -u 1.
I never update my video drivers through my distro (Win7 in this case). Just tried the lasted beta and that didn't change anything either.
The same thing happens with 32bit.

The really weird thing is that all other attacks seem to work. And lite has no problems with any modes.

-m 500 works so I guess it's just the md5 kernel?
#4
Sorry, I do not speak in English, but I have the exact same problem:
[Image: 202c9ef8e028t.jpg]
[Image: d23abd45aea1t.jpg]
they are two different computer(first x86, second x64).
#5
(02-17-2013, 09:14 PM)Euler Wrote: Sorry, I do not speak in English, but I have the exact same problem:
[Image: 202c9ef8e028t.jpg]
[Image: d23abd45aea1t.jpg]
they are two different computer(first x86, second x64).

Have you got the latest drivers installed for your cards?
#6
(02-18-2013, 12:24 AM)Dolphin Wrote: Have you got the latest drivers installed for your cards?
Yes, latest stable version. The only problem with MD5.
#7
Did you unpack it over an already existing directory? I had this issue on my 580's and it was because of that.
#8
(02-18-2013, 06:22 AM)radix Wrote: Did you unpack it over an already existing directory? I had this issue on my 580's and it was because of that.

I did, that gave me hope, but a fresh extraction resulted in the same error.
#9
C:\Users\Home\Desktop\PAPA\oclHashcat-plus-0.13>cudaHashcat-plus64.exe -a 3 -m 1000 dad.hash dad.dict
cudaHashcat-plus v0.13 by atom starting...

Hashes: 2 total, 1 unique salts, 2 unique digests
Bitmaps: 8 bits, 256 entries, 0x000000ff mask, 1024 bytes
Workload: 256 loops, 80 accel
Watchdog: Temperature abort trigger set to 90c
Watchdog: Temperature retain trigger set to 80c
Device #1: GeForce GTX 260, 896MB, 1242Mhz, 27MCU
Device #1: Kernel ./kernels/4318/m1000_a3.sm_13.ptx

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

same problem for me... see the results above
i use a Win7 64 with Nvidia GTX260² and newest / latest NVidia drivers 314.07
problem seems to be only on NTLM and Bruto Force Attack.
Any ideas how to solve this problem?
#10
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