XFX 290 Issues
#1
So I have a cracking box with 6 XFX r9 290s (black OC edition) and I have massive fluctuations in GPU utilization in oclHashcat. I've tried tweaking things with od6config and all the drivers and hashcat are up to date. The issue seems to show up regardless of what my clocks are set to (Stock or OC). I'll start a cracking job and things will jump between 1% and 100% utilization (and everything in between), no matter what kind of mode I'm running.

Running the benchmarks, the cards come in at 136.9 GH/s. When I'm running a regular cracking job, the cards are coming in around 60,000 MH/s.

Anyone experiencing the same issues?
Reply
#2
please specifieying your hardware and hashcat command to help youah
Reply
#3
Benchmark:
~/oclHashcat-1.36$ ./oclHashcat64.bin -m 1000 -b
oclHashcat v1.36 starting in benchmark-mode...

Device #1: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #2: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #3: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #4: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #5: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #6: Hawaii, 3072MB, 1100Mhz, 40MCU

Hashtype: NTLM
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 22822.2 MH/s
Speed.GPU.#2.: 22821.6 MH/s
Speed.GPU.#3.: 22828.0 MH/s
Speed.GPU.#4.: 22811.7 MH/s
Speed.GPU.#5.: 22819.5 MH/s
Speed.GPU.#6.: 22822.3 MH/s
Speed.GPU.#*.: 136.9 GH/s

Started: Thu May 21 12:14:25 2015
Stopped: Thu May 21 12:14:42 2015

8 Char Bruteforce:
~/oclHashcat-1.36$ ./oclHashcat64.bin -m 1000 aaaaaaaaddddddddaaaaaaaadddddddd -a 3 ?a?a?a?a?a?a?a?a
oclHashcat v1.36 starting...

Device #1: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #2: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #3: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #4: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #5: Hawaii, 3072MB, 1100Mhz, 40MCU
Device #6: Hawaii, 3072MB, 1100Mhz, 40MCU

Hashes: 1 hashes; 1 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates
Applicable Optimizers:
* Zero-Byte
* Precompute-Init
* Precompute-Merkle-Demgard
* Meet-In-The-Middle
* Early-Skip
* Not-Salted
* Not-Iterated
* Single-Hash
* Single-Salt
* Brute-Force
* Scalar-Mode
* Raw-Hash
Watchdog: Temperature abort trigger set to 90c
Watchdog: Temperature retain trigger set to 80c
Device #1: Kernel ./kernels/4098/m01000_a3.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (147652 bytes)
Device #1: Kernel ./kernels/4098/markov_le_v1.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (35068 bytes)
Device #2: Kernel ./kernels/4098/m01000_a3.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (147652 bytes)
Device #2: Kernel ./kernels/4098/markov_le_v1.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (35068 bytes)
Device #3: Kernel ./kernels/4098/m01000_a3.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (147652 bytes)
Device #3: Kernel ./kernels/4098/markov_le_v1.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (35068 bytes)
Device #4: Kernel ./kernels/4098/m01000_a3.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (147652 bytes)
Device #4: Kernel ./kernels/4098/markov_le_v1.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (35068 bytes)
Device #5: Kernel ./kernels/4098/m01000_a3.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (147652 bytes)
Device #5: Kernel ./kernels/4098/markov_le_v1.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (35068 bytes)
Device #6: Kernel ./kernels/4098/m01000_a3.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (147652 bytes)
Device #6: Kernel ./kernels/4098/markov_le_v1.Hawaii_1573.4_1573.4 (VM)_1429981600.kernel (35068 bytes)

[s]tatus [p]ause [r]esume [b]ypass [q]uit => s

Session.Name...: oclHashcat
Status.........: Running
Input.Mode.....: Mask (?a?a?a?a?a?a?a?a) [8]
Hash.Target....: aaaaaaaaddddddddaaaaaaaadddddddd
Hash.Type......: NTLM
Time.Started...: Thu May 21 12:17:23 2015 (4 secs)
Time.Estimated.: Fri May 22 03:45:49 2015 (15 hours, 28 mins)
Speed.GPU.#1...: 19914.2 MH/s
Speed.GPU.#2...: 19786.1 MH/s
Speed.GPU.#3...: 19828.3 MH/s
Speed.GPU.#4...: 19914.1 MH/s
Speed.GPU.#5...: 19899.1 MH/s
Speed.GPU.#6...: 19937.3 MH/s
Speed.GPU.#*...: 119.3 GH/s
Recovered......: 0/1 (0.00%) Digests, 0/1 (0.00%) Salts
Progress.......: 555848171520/6634204312890625 (0.01%)
Rejected.......: 0/555848171520 (0.00%)
Restore.Point..: 59310080/735091890625 (0.01%)
HWMon.GPU.#1...: 97% Util, 57c Temp, 100% Fan
HWMon.GPU.#2...: 98% Util, 54c Temp, 100% Fan
HWMon.GPU.#3...: 100% Util, 53c Temp, 100% Fan
HWMon.GPU.#4...: 1% Util, 58c Temp, 100% Fan
HWMon.GPU.#5...: 6% Util, 52c Temp, 100% Fan
HWMon.GPU.#6...: 0% Util, 59c Temp, 100% Fan

[s]tatus [p]ause [r]esume [b]ypass [q]uit => s

Session.Name...: oclHashcat
Status.........: Running
Input.Mode.....: Mask (?a?a?a?a?a?a?a?a) [8]
Hash.Target....: aaaaaaaaddddddddaaaaaaaadddddddd
Hash.Type......: NTLM
Time.Started...: Thu May 21 12:17:23 2015 (46 secs)
Time.Estimated.: Fri May 22 03:43:46 2015 (15 hours, 25 mins)
Speed.GPU.#1...: 20044.5 MH/s
Speed.GPU.#2...: 20190.4 MH/s
Speed.GPU.#3...: 19807.8 MH/s
Speed.GPU.#4...: 19967.9 MH/s
Speed.GPU.#5...: 19953.1 MH/s
Speed.GPU.#6...: 20228.0 MH/s
Speed.GPU.#*...: 120.2 GH/s
Recovered......: 0/1 (0.00%) Digests, 0/1 (0.00%) Salts
Progress.......: 5497327452160/6634204312890625 (0.08%)
Rejected.......: 0/5497327452160 (0.00%)
Restore.Point..: 606535680/735091890625 (0.08%)
HWMon.GPU.#1...: 100% Util, 67c Temp, 100% Fan
HWMon.GPU.#2...: 100% Util, 64c Temp, 100% Fan
HWMon.GPU.#3...: 9% Util, 63c Temp, 100% Fan
HWMon.GPU.#4...: 0% Util, 67c Temp, 100% Fan
HWMon.GPU.#5...: 26% Util, 61c Temp, 100% Fan
HWMon.GPU.#6...: 0% Util, 68c Temp, 100% Fan

[s]tatus [p]ause [r]esume [b]ypass [q]uit =>

It seems to be cutting down to 65k MH/s when doing large samples of hashes (which isn't a big deal). Single hashes are hitting 120 GH/s, but the Util is still bouncing around a lot.

Thanks.
Reply
#4
add -w 3 parameter
Reply
#5
(05-21-2015, 08:42 PM)Si2006 Wrote: add -w 3 parameter

That kind of helps. I'm getting better rates and more sustained 100% utils, but the drops are still happening occasionally. Not a big deal, just kind of annoying overall. Thanks!
Reply
#6
(05-21-2015, 08:48 PM)globus Wrote: I'm getting better rates and more sustained 100% utils, but the drops are still happening occasionally.


That's expected behavior. The kernels have to return at some point!
Reply
#7
most bad influences come from so called rizers , do you use 6 of them ?
Reply
#8
(05-23-2015, 11:06 AM)ati6990 Wrote: most bad influences come from so called rizers , do you use 6 of them ?

Yes, I'm currently using 6 of them. I haven't had the same issues in my box with 6 - 7950s in it (same setup).
Reply