vcl woes
#11
Right, I already remove it from beta. Next release version will not ship it any longer.
#12
OK, so today I tried it with Ubuntu 12.04, Cat 12.8 and VCL 1.17. Now it works. I just have two minor issues:

1. Testing with crypt-md5, speed is very low unless I use a large figure for -n. Is this expected? Connection is gigabit copper. I tried bumping --gpu-loops (or whatever it's called) instead but that did not do it. With a max -n (which is possibly auto-tuned down, right?) I seem to get about same speed per GPU as when running locally.

2. Key-press does not work! Anyone else seen that? Eg. if I press 's' for status, the s gets echoed but nothing else happens. If I abort with ctrl-c I do get a status report showing everything did run as it should, so the session/restore feature made my day :-)

Pretty impressing stuff anyway.
#13
sweet i'll have to try this again cus i couldnt get it to work before either. got any numbers (benchmarks) to share?
#14
1. this is normal

2. this is also normal
#15
I'm getting a couple errors

libOpenCL.so.1: no version information available
[s]tatus [p]ause [r]esume [b]ypass [q]uit => ERROR: clEnqueueReadBuffer() -38

Looks like the broker is able to connect to the compute node but didn't crack anything. Could it be caused by the catalyst drivers installed on the broker? Which leads to my other question. I have two systems, both with GPUs installed. The wiki says not to configure the broker on a compute node but I've also read somewhere that having the broker on a compute node could reduce network chatter?

my setup:
PC-1: Broker Node -- has 6 GPU but not configured for computing yet, acting as broker only
PC-2: Compute Node -- has 8 GPU

Code:
root@crack-3:~/oclHashcat-plus-0.13b3# ./oclHashcat-plus64.bin example0.hash example.dict --gpu-temp-disable
./oclHashcat-plus64.bin: /usr/lib/vcl/libOpenCL.so.1: no version information available (required by ./oclHashcat-plus64.bin)
oclHashcat-plus v0.13 by atom starting...

Hashes: 6494 total, 1 unique salts, 6494 unique digests
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes
Rules: 1
Workload: 256 loops, 80 accel
Watchdog: Temperature abort trigger disabled
Watchdog: Temperature retain trigger disabled
Device #1: Cypress, 512MB, 0Mhz, 20MCU
Device #2: Cypress, 512MB, 0Mhz, 20MCU
Device #3: Cypress, 512MB, 0Mhz, 20MCU
Device #4: Cypress, 512MB, 0Mhz, 20MCU
Device #5: Cypress, 512MB, 0Mhz, 20MCU
Device #6: Cypress, 512MB, 0Mhz, 20MCU
Device #7: Cypress, 512MB, 0Mhz, 20MCU
Device #8: Cypress, 512MB, 0Mhz, 20MCU
Device #1: Kernel ./kernels/4098/m0000_a0.Cypress_938.2_CAL 1.4.1741.kernel (1227844 bytes)
Device #2: Kernel ./kernels/4098/m0000_a0.Cypress_938.2_CAL 1.4.1741.kernel (1227844 bytes)
Device #3: Kernel ./kernels/4098/m0000_a0.Cypress_938.2_CAL 1.4.1741.kernel (1227844 bytes)
Device #4: Kernel ./kernels/4098/m0000_a0.Cypress_938.2_CAL 1.4.1741.kernel (1227844 bytes)
Device #5: Kernel ./kernels/4098/m0000_a0.Cypress_938.2_CAL 1.4.1741.kernel (1227844 bytes)
Device #6: Kernel ./kernels/4098/m0000_a0.Cypress_938.2_CAL 1.4.1741.kernel (1227844 bytes)
Device #7: Kernel ./kernels/4098/m0000_a0.Cypress_938.2_CAL 1.4.1741.kernel (1227844 bytes)
Device #8: Kernel ./kernels/4098/m0000_a0.Cypress_938.2_CAL 1.4.1741.kernel (1227844 bytes)

Cache-hit dictionary stats example.dict: 1210228 bytes, 129988 words, 129988 keyspace

NOTE: autotuned --gpu-accel from 80 to 8

[s]tatus [p]ause [r]esume [b]ypass [q]uit => ERROR: clEnqueueReadBuffer() -38
#16
yeah, the vclHashcat binary is still needed. it does not work with the oclHashcat binary.
#17
Now I'm confused. Atom just said vclHashcat is not needed anymore and it's not present in the archive.
#18
right. but we found out that vcl 1.17 doesn't actually fix all the issues, and that the vclHashcat binaries are still required. that is why they're still mentioned in the updated wiki article. atom said a few days ago that he was going to add them back into the archives.
#19
oh man, I can't believe I missed that part...Thx, it's working now.

Also, is configuring the broker on a compute node a huge pain?

edit: Created a vm real quick, got it working as the broker, so all 14 gpus in my cluster are working now Smile was running oclhc-lite benchmark for a minute before blowing the power breaker lol. I need more power, Scotty!
#20
it's not a huge pain to configure the broker on a compute node, no. just follow all of the instructions in the wiki for the broker configuration on one of your compute nodes.