<![CDATA[hashcat Forum - Very old oclHashcat-lite Announcements]]> https://hashcat.net/forum/ Thu, 29 Oct 2026 05:17:11 +0000 MyBB <![CDATA[oclHashcat-lite v0.15]]> https://hashcat.net/forum/thread-2700.html Wed, 09 Oct 2013 22:09:51 +0000 d0znpp]]> https://hashcat.net/forum/thread-2700.html
Code:
~/h/oclHashcat-lite-0.15/oclHashcat-lite64.bin --force -m132 0x010014b8775afa7a455000000000000000000000000000000000 -d 2 -1 '?l?u?d' '?1?1?1?1?1?1?1?1?1?1' Device #1: skipped by user Device #2: Cayman, 1024MB, 830Mhz, 24MCU Device #3: skipped by user Device #4: skipped by user ... Speed.GPU.#1...: 1834.0M/s

Code:
~/h/oclHashcat-lite-0.15/oclHashcat-lite64.bin --force -m132 0x010014b8775afa7a455000000000000000000000000000000000 -d 1 -1 '?l?u?d' '?1?1?1?1?1?1?1?1?1?1' Device #1: Tahiti, 2967MB, 1000Mhz, 32MCU Device #2: skipped by user Device #3: skipped by user Device #4: skipped by user [s]tatus [p]ause [r]esume [q]uit => Segmentation fault

But MD5 is OK...]]>
Code:
~/h/oclHashcat-lite-0.15/oclHashcat-lite64.bin --force -m132 0x010014b8775afa7a455000000000000000000000000000000000 -d 2 -1 '?l?u?d' '?1?1?1?1?1?1?1?1?1?1' Device #1: skipped by user Device #2: Cayman, 1024MB, 830Mhz, 24MCU Device #3: skipped by user Device #4: skipped by user ... Speed.GPU.#1...: 1834.0M/s

Code:
~/h/oclHashcat-lite-0.15/oclHashcat-lite64.bin --force -m132 0x010014b8775afa7a455000000000000000000000000000000000 -d 1 -1 '?l?u?d' '?1?1?1?1?1?1?1?1?1?1' Device #1: Tahiti, 2967MB, 1000Mhz, 32MCU Device #2: skipped by user Device #3: skipped by user Device #4: skipped by user [s]tatus [p]ause [r]esume [q]uit => Segmentation fault

But MD5 is OK...]]> <![CDATA[oclHashcat-lite v0.10]]> https://hashcat.net/forum/thread-1344.html Fri, 29 Jun 2012 10:32:12 +0000 atom]]> https://hashcat.net/forum/thread-1344.html
Download it here: http://hashcat.net/oclhashcat-lite/

This release is a big step forward. We have added both, many major and many minor features.

Per-position markov-chains, aka markov-attack/incremental-attack/charset-files

The markov-attack is a statistically based brute-force like attack, but instead of specifying a charset or a mask, we specify a file. This file is once generated by ourself in a previous step. It contains statistical informations which are made out an automated analysis of a given dictionary.

It can fully replace Brute-Force since it covers the full keyspace.

In Brute-Force Attack (or in Mask Attack) we can limit the keyspace by setting a smaller charset in order to reduce the attack-time. In Markov Attack we have something similar, the "threshold". All you do is to specify a number. The higher the number, the higher the threshold to add a new link between two characters on the two-level table on which the markov-attack bases on.

This background is not so important, just remember that the lower the value, the smaller the keyspace and thus the faster the attack is.

Check these threads for more details

Use .ptx ad .llvmir intermediate kernels

The kernels are distributed in an "intermediate" format (aka IL). It cant be reversed to original C code but still its not a binary format that can be used for execution.

The JIT (just-in-time) compilers from both OpenCL and CUDA, which ship with the driver, compile the final byte-code out of the IL. This takes a few seconds per kernel but once its done the byte-code is cached (CUDA does it automatically, OpenCL not but we add a function to do the same as CUDA does).

This has some nice advantages:
  • Not 32/64 bit specific
  • Less HDD space
  • Smaller .7z
  • Less problems with driver specific problems as we often see with Catalyst
  • There is no more need to release a new oclHashcat-* in case a new driver optimization has been added. oclHashcat-* caches driver specific. If it recognizes a driver change it will rebuild thge byte-code from the IL, but using the new JIT from the new driver resulting in driver specific optimized byte-code.

Retaining GPU temperature

When I started with oclHashcat-* Hardware mangement support, some people asked me for add support for fan-speed. For a long time I was not interessted in adding fan-speed code to oclHashcat-* since this is the job for the driver or some specialized controling software.

I did not change my mind completly on this, but still we have added some fan-speed controlling code. The new parameters are:

Code:
--gpu-temp-disable Disable temperature and fanspeed readings and triggers --gpu-temp-abort=NUM Abort session if GPU temperature reaches NUM degrees celsius --gpu-temp-retain=NUM Try to retain GPU temperature at NUM degrees celsius (AMD only)

So what this thing is doing is: If the temperature configured with the new --gpu-temp-retain parameter is reached, it starts to increase the fan-speed by 1 percent each second. Thats all.

If you imagine a scenario what this means you will come to the conclusion that this feature also enables you to enfore your GPU running always to a very specific temperature.

Some notes:
  • --gpu-temp-disable you can completly disable all the temperature stuff.
  • --gpu-temp-retain currently only works for AMD.
  • --gpu-temp-abort parameter is just the renamed version of the old --gpu-watchdog.
  • Both parameters accept the 0 value which disables only this specific feature. This means you can step back to the old behavior by specifying --gpu-temp-retain 0.
  • The default for --gpu-temp-abort is still 90c.
  • The default for --gpu-temp-retain is 80c.

Built-in benchmarking mode

Code:
* Benchmark: -b, --benchmark Run benchmark --benchmark-mode Benchmark-mode, see references below

Nothing much to explain here I think, but some notes to the benchmark mode:
  • As long as you do not set the --benchmark-mode you can modify all the configuration parameters you always use. Something like -d, -n, --gpu-accel or --runtime.
  • With --runtime you can specify the duration how long each test lasts.
  • If you add -m you can limit to a specific hash-type. If you do not set it, it will iterate through all hash-types.
  • All unneccessary parallel threads like hardware monitor, restore-support and outfile-watch are disabled. Also the quiet mode is enabled.
  • On NVidia, the hashes based on SHA256, SHA512 and DES are limited to -n 32, otherwise the driver throws the error cuStreamSynchronize() 702.

New Algorithms supported
  • SHA512
  • Oracle 7-10g, DES(Oracle)
  • md4($pass.$salt)
  • sha256($pass.$salt)
  • sha512($pass.$salt)

Full changelog

Code:
type: feature file: kernels desc: added -m 0910 = md4($pass.$salt) type: feature file: kernels desc: added -m 1410 = sha256($pass.$salt) type: feature file: kernels desc: added -m 1700 = SHA512 type: feature file: kernels desc: added -m 1710 = sha512($pass.$salt) type: feature file: kernels desc: added -m 3100 = Oracle 7-10g, DES(Oracle) type: feature file: kernels desc: on AMD, switched from .kernel to .llvmir to reduce diskspace type: feature file: kernels desc: on NV, switched from .cubin to .ptx to reduce diskspace type: feature file: kernels desc: added kernel cache to avoid unnecessary recompilation cred: m4tr1x type: driver file: kernels desc: added support for NVidia CUDA 4.2 type: driver file: kernels desc: added support for NVidia sm_30 gpu-architecture [ Kepler ] type: driver file: host programs desc: added support for NVAPI R300 type: driver file: host programs desc: added support for NVidia NVML library and got rid of nvidia-smi command type: driver file: host programs desc: added support for AMD ADL v4.0 library type: feature file: host programs desc: splitted --gpu-watchdog to --gpu-temp-disable and --gpu-temp-abort type: feature file: kernels desc: added benchmarking mode cred: m4tr1x type: feature file: host programs desc: added --gpu-temp-retain to try retain temperature at NUM degrees celsius cred: m4tr1x type: feature file: host programs desc: workarounded AMD bug in clGetDeviceInfo() CL_DEVICE_MAX_CLOCK_FREQUENCY cred: m4tr1x type: feature file: kernels desc: added early check for zero-length password hashes cred: m4tr1x type: feature file: host programs desc: show LM-half as soon as it is cracked type: feature file: host programs desc: added support for charset files and some example charset files type: feature file: host programs desc: added support to read hashes from file type: feature file: host programs desc: implemented base64 parser that would allow for dynamic salt lengths in nsldaps type: feature file: host programs desc: added fan-speeds to status display type: feature file: host programs desc: removed --pw-skip-plain and --pw-limit-plain as they are incompatible to markov type: bug file: host programs desc: fixed bug in status display if ETA calculated > 60 years cred: arex type: bug file: host programs desc: fixed bug in Oracle 11g hash parsing function, salt length increased to 10 byte cred: flipit type: bug file: host programs desc: fixed bug in salt-length parser for MyBB1.2 hashes cred: code841 type: change file: host programs desc: changed default charset to the one which passpal outputs running on rockyou.txt cred: arex
]]>
Download it here: http://hashcat.net/oclhashcat-lite/

This release is a big step forward. We have added both, many major and many minor features.

Per-position markov-chains, aka markov-attack/incremental-attack/charset-files

The markov-attack is a statistically based brute-force like attack, but instead of specifying a charset or a mask, we specify a file. This file is once generated by ourself in a previous step. It contains statistical informations which are made out an automated analysis of a given dictionary.

It can fully replace Brute-Force since it covers the full keyspace.

In Brute-Force Attack (or in Mask Attack) we can limit the keyspace by setting a smaller charset in order to reduce the attack-time. In Markov Attack we have something similar, the "threshold". All you do is to specify a number. The higher the number, the higher the threshold to add a new link between two characters on the two-level table on which the markov-attack bases on.

This background is not so important, just remember that the lower the value, the smaller the keyspace and thus the faster the attack is.

Check these threads for more details

Use .ptx ad .llvmir intermediate kernels

The kernels are distributed in an "intermediate" format (aka IL). It cant be reversed to original C code but still its not a binary format that can be used for execution.

The JIT (just-in-time) compilers from both OpenCL and CUDA, which ship with the driver, compile the final byte-code out of the IL. This takes a few seconds per kernel but once its done the byte-code is cached (CUDA does it automatically, OpenCL not but we add a function to do the same as CUDA does).

This has some nice advantages:
  • Not 32/64 bit specific
  • Less HDD space
  • Smaller .7z
  • Less problems with driver specific problems as we often see with Catalyst
  • There is no more need to release a new oclHashcat-* in case a new driver optimization has been added. oclHashcat-* caches driver specific. If it recognizes a driver change it will rebuild thge byte-code from the IL, but using the new JIT from the new driver resulting in driver specific optimized byte-code.

Retaining GPU temperature

When I started with oclHashcat-* Hardware mangement support, some people asked me for add support for fan-speed. For a long time I was not interessted in adding fan-speed code to oclHashcat-* since this is the job for the driver or some specialized controling software.

I did not change my mind completly on this, but still we have added some fan-speed controlling code. The new parameters are:

Code:
--gpu-temp-disable Disable temperature and fanspeed readings and triggers --gpu-temp-abort=NUM Abort session if GPU temperature reaches NUM degrees celsius --gpu-temp-retain=NUM Try to retain GPU temperature at NUM degrees celsius (AMD only)

So what this thing is doing is: If the temperature configured with the new --gpu-temp-retain parameter is reached, it starts to increase the fan-speed by 1 percent each second. Thats all.

If you imagine a scenario what this means you will come to the conclusion that this feature also enables you to enfore your GPU running always to a very specific temperature.

Some notes:
  • --gpu-temp-disable you can completly disable all the temperature stuff.
  • --gpu-temp-retain currently only works for AMD.
  • --gpu-temp-abort parameter is just the renamed version of the old --gpu-watchdog.
  • Both parameters accept the 0 value which disables only this specific feature. This means you can step back to the old behavior by specifying --gpu-temp-retain 0.
  • The default for --gpu-temp-abort is still 90c.
  • The default for --gpu-temp-retain is 80c.

Built-in benchmarking mode

Code:
* Benchmark: -b, --benchmark Run benchmark --benchmark-mode Benchmark-mode, see references below

Nothing much to explain here I think, but some notes to the benchmark mode:
  • As long as you do not set the --benchmark-mode you can modify all the configuration parameters you always use. Something like -d, -n, --gpu-accel or --runtime.
  • With --runtime you can specify the duration how long each test lasts.
  • If you add -m you can limit to a specific hash-type. If you do not set it, it will iterate through all hash-types.
  • All unneccessary parallel threads like hardware monitor, restore-support and outfile-watch are disabled. Also the quiet mode is enabled.
  • On NVidia, the hashes based on SHA256, SHA512 and DES are limited to -n 32, otherwise the driver throws the error cuStreamSynchronize() 702.

New Algorithms supported
  • SHA512
  • Oracle 7-10g, DES(Oracle)
  • md4($pass.$salt)
  • sha256($pass.$salt)
  • sha512($pass.$salt)

Full changelog

Code:
type: feature file: kernels desc: added -m 0910 = md4($pass.$salt) type: feature file: kernels desc: added -m 1410 = sha256($pass.$salt) type: feature file: kernels desc: added -m 1700 = SHA512 type: feature file: kernels desc: added -m 1710 = sha512($pass.$salt) type: feature file: kernels desc: added -m 3100 = Oracle 7-10g, DES(Oracle) type: feature file: kernels desc: on AMD, switched from .kernel to .llvmir to reduce diskspace type: feature file: kernels desc: on NV, switched from .cubin to .ptx to reduce diskspace type: feature file: kernels desc: added kernel cache to avoid unnecessary recompilation cred: m4tr1x type: driver file: kernels desc: added support for NVidia CUDA 4.2 type: driver file: kernels desc: added support for NVidia sm_30 gpu-architecture [ Kepler ] type: driver file: host programs desc: added support for NVAPI R300 type: driver file: host programs desc: added support for NVidia NVML library and got rid of nvidia-smi command type: driver file: host programs desc: added support for AMD ADL v4.0 library type: feature file: host programs desc: splitted --gpu-watchdog to --gpu-temp-disable and --gpu-temp-abort type: feature file: kernels desc: added benchmarking mode cred: m4tr1x type: feature file: host programs desc: added --gpu-temp-retain to try retain temperature at NUM degrees celsius cred: m4tr1x type: feature file: host programs desc: workarounded AMD bug in clGetDeviceInfo() CL_DEVICE_MAX_CLOCK_FREQUENCY cred: m4tr1x type: feature file: kernels desc: added early check for zero-length password hashes cred: m4tr1x type: feature file: host programs desc: show LM-half as soon as it is cracked type: feature file: host programs desc: added support for charset files and some example charset files type: feature file: host programs desc: added support to read hashes from file type: feature file: host programs desc: implemented base64 parser that would allow for dynamic salt lengths in nsldaps type: feature file: host programs desc: added fan-speeds to status display type: feature file: host programs desc: removed --pw-skip-plain and --pw-limit-plain as they are incompatible to markov type: bug file: host programs desc: fixed bug in status display if ETA calculated > 60 years cred: arex type: bug file: host programs desc: fixed bug in Oracle 11g hash parsing function, salt length increased to 10 byte cred: flipit type: bug file: host programs desc: fixed bug in salt-length parser for MyBB1.2 hashes cred: code841 type: change file: host programs desc: changed default charset to the one which passpal outputs running on rockyou.txt cred: arex
]]> <![CDATA[oclHashcat-lite v0.09]]> https://hashcat.net/forum/thread-898.html Fri, 03 Feb 2012 22:05:41 +0000 atom]]> https://hashcat.net/forum/thread-898.html
I am proud to announce version 0.09 of the oclHashcat-lite series.

Download it here: http://hashcat.net/oclhashcat-lite/

The highlights of this release are:

  • Support for AMD GCN cards (hd7xxx series)
I already wrote some more detailed informations about the integration here: http://hashcat.net/forum/thread-817.html

This card is a true DES killer. I wrote some more detailed informations about this topic here: http://hashcat.net/forum/thread-846.html

  • Added the LM Algorithm
After so many people requested this algorithm in the feature request section I decided to add it even I had not interesst in it.

However, it turned out it was a good investment of time. I realized how many pentester still have need for it.

See here for discussion: http://hashcat.net/forum/thread-167.html

  • Vectorized datatype kernels for sm_21 NVidia architecture
This a massive improvement for low- and mid-ranged NVidia GPUs.

The gtx560Ti @ MD5, for example, increased by 23% (1252 Mhash/s -> 1660 Mhash/s).

This improvement can be seen on nearly all algorithms for this architecture.

  • MD4 based algorithm tuning
To make it short: I found a way to reverse another step in MD4.

Especially the NTLM and DCC algorithm benefit from this code change.

The hd6990 @ NTLM broke the 20000 Mhash/s mark on stock clocks. Average increase is around + 9% (19100 Mhash/s -> 20864 Mhash/s).

  • Updated EULA
This goes back to a discussion we had HD Moore from Rapid7.

The updated EULA is a lot more relaxed for professional pentesters than before.

See changelog for more details.

  • Fixed some major issues
On thing that many user complained about in oclHashcat-lite 0.08 was its "instability" and problems with session restore.

This popped in because of a default-settings change in oclHashcat-lite v0.07. It has been set back to oclHashcat-lite v0.06 default.

Discussion can be found here: http://hashcat.net/forum/thread-681.html

  • Harmonization with oclHashcat-plus
The --help page, the --outfile-format and the -m parameter values, in case of an overlap, are now equal to oclHashcat-plus v0.08.

It will help to avoid confusion, thats why I am planning to do the same change on CPU hashcat in the next version.


Full changelog:

Code:
type: feature file: kernels cred: added -m 2811 = IPB 2.0, MyBB1.2 type: feature file: kernels cred: added -m 3000 = LM type: driver file: kernels desc: added support for AMD APP SDK 2.6 type: driver file: kernels desc: added support for NVidia CUDA 4.1 type: feature file: kernels desc: added support for AMD GPU's "Devastator" and "Scrapper" type: feature file: kernels desc: added support for AMD GPU's "Capeverde", "Pitcairn" and "Tahiti" type: feature file: host programs desc: backported --outfile-format from oclHashcat-plus v0.07 type: feature file: host programs desc: backported --seperator-char feature from hashcat v0.38 cred: thorsheim type: feature file: host programs desc: add support for passwords smaller length 4 type: bug file: host programs desc: fixed issue with unaligned --pw-skip, did not auto-shutdown when 100% keyspace reached cred: MrUltimate type: bug file: host programs desc: fixed issue when using --pw-skip-plain in combination with --hex-charset type: change file: host programs desc: changed hash parser for Joomla hashes to allow salt-length of 16 - 32 cred: sono type: change file: host programs desc: changed default setting for CPU affinity: Linux unlocked, Windows unlocked type: change file: host programs desc: ETA is now calculated regarding to configured value of --pw-skip and --pw-limit cred: MrUltimate type: change file: host programs desc: changed restore-timer default value to 60 due to GPU utilization issue cred: MrUltimate, d-unknown, khempanhom type: change file: host programs desc: EULA. Removed sections 2, 6, 8 and 9. Relaxed sections 3 and 7. cred: hdmoore type: change file: kernels desc: renamed -m 1 to -m 10 desc: renamed -m 3 to -m 2600 desc: renamed -m 5 to -m 2611 desc: renamed -m 15 to -m 2711 desc: renamed -m 101 to -m 110 desc: renamed -m 600 to -m 101 desc: renamed -m 700 to -m 111 desc: renamed -m 1300 to -m 131 desc: renamed -m 2000 to -m 112 desc: renamed -m 2300 to -m 132 type: change file: rules desc: redesigned usage screen cred: http://hashcat.net/forum/thread-716.html

--
atom
]]>
I am proud to announce version 0.09 of the oclHashcat-lite series.

Download it here: http://hashcat.net/oclhashcat-lite/

The highlights of this release are:

  • Support for AMD GCN cards (hd7xxx series)
I already wrote some more detailed informations about the integration here: http://hashcat.net/forum/thread-817.html

This card is a true DES killer. I wrote some more detailed informations about this topic here: http://hashcat.net/forum/thread-846.html

  • Added the LM Algorithm
After so many people requested this algorithm in the feature request section I decided to add it even I had not interesst in it.

However, it turned out it was a good investment of time. I realized how many pentester still have need for it.

See here for discussion: http://hashcat.net/forum/thread-167.html

  • Vectorized datatype kernels for sm_21 NVidia architecture
This a massive improvement for low- and mid-ranged NVidia GPUs.

The gtx560Ti @ MD5, for example, increased by 23% (1252 Mhash/s -> 1660 Mhash/s).

This improvement can be seen on nearly all algorithms for this architecture.

  • MD4 based algorithm tuning
To make it short: I found a way to reverse another step in MD4.

Especially the NTLM and DCC algorithm benefit from this code change.

The hd6990 @ NTLM broke the 20000 Mhash/s mark on stock clocks. Average increase is around + 9% (19100 Mhash/s -> 20864 Mhash/s).

  • Updated EULA
This goes back to a discussion we had HD Moore from Rapid7.

The updated EULA is a lot more relaxed for professional pentesters than before.

See changelog for more details.

  • Fixed some major issues
On thing that many user complained about in oclHashcat-lite 0.08 was its "instability" and problems with session restore.

This popped in because of a default-settings change in oclHashcat-lite v0.07. It has been set back to oclHashcat-lite v0.06 default.

Discussion can be found here: http://hashcat.net/forum/thread-681.html

  • Harmonization with oclHashcat-plus
The --help page, the --outfile-format and the -m parameter values, in case of an overlap, are now equal to oclHashcat-plus v0.08.

It will help to avoid confusion, thats why I am planning to do the same change on CPU hashcat in the next version.


Full changelog:

Code:
type: feature file: kernels cred: added -m 2811 = IPB 2.0, MyBB1.2 type: feature file: kernels cred: added -m 3000 = LM type: driver file: kernels desc: added support for AMD APP SDK 2.6 type: driver file: kernels desc: added support for NVidia CUDA 4.1 type: feature file: kernels desc: added support for AMD GPU's "Devastator" and "Scrapper" type: feature file: kernels desc: added support for AMD GPU's "Capeverde", "Pitcairn" and "Tahiti" type: feature file: host programs desc: backported --outfile-format from oclHashcat-plus v0.07 type: feature file: host programs desc: backported --seperator-char feature from hashcat v0.38 cred: thorsheim type: feature file: host programs desc: add support for passwords smaller length 4 type: bug file: host programs desc: fixed issue with unaligned --pw-skip, did not auto-shutdown when 100% keyspace reached cred: MrUltimate type: bug file: host programs desc: fixed issue when using --pw-skip-plain in combination with --hex-charset type: change file: host programs desc: changed hash parser for Joomla hashes to allow salt-length of 16 - 32 cred: sono type: change file: host programs desc: changed default setting for CPU affinity: Linux unlocked, Windows unlocked type: change file: host programs desc: ETA is now calculated regarding to configured value of --pw-skip and --pw-limit cred: MrUltimate type: change file: host programs desc: changed restore-timer default value to 60 due to GPU utilization issue cred: MrUltimate, d-unknown, khempanhom type: change file: host programs desc: EULA. Removed sections 2, 6, 8 and 9. Relaxed sections 3 and 7. cred: hdmoore type: change file: kernels desc: renamed -m 1 to -m 10 desc: renamed -m 3 to -m 2600 desc: renamed -m 5 to -m 2611 desc: renamed -m 15 to -m 2711 desc: renamed -m 101 to -m 110 desc: renamed -m 600 to -m 101 desc: renamed -m 700 to -m 111 desc: renamed -m 1300 to -m 131 desc: renamed -m 2000 to -m 112 desc: renamed -m 2300 to -m 132 type: change file: rules desc: redesigned usage screen cred: http://hashcat.net/forum/thread-716.html

--
atom
]]> <![CDATA[oclHashcat-lite v0.08]]> https://hashcat.net/forum/thread-676.html Sat, 26 Nov 2011 07:50:45 +0000 atom]]> https://hashcat.net/forum/thread-676.html here

If you are using oclHashcat-lite for SL3 you must upgrade to this version.

Much thanks to the users reporting Smile

Code:
type: feature file: host programs desc: added version check for restore sessions cred: utuh type: bug file: host programs desc: fixed issue in SL3 leading to "code not found" and bad GPU utilization cred: romke, d-unknown, khempanhom

--
atom]]> here

If you are using oclHashcat-lite for SL3 you must upgrade to this version.

Much thanks to the users reporting Smile

Code:
type: feature file: host programs desc: added version check for restore sessions cred: utuh type: bug file: host programs desc: fixed issue in SL3 leading to "code not found" and bad GPU utilization cred: romke, d-unknown, khempanhom

--
atom]]> <![CDATA[oclHashcat-lite v0.07]]> https://hashcat.net/forum/thread-670.html Fri, 25 Nov 2011 12:29:39 +0000 atom]]> https://hashcat.net/forum/thread-670.html
I am very proud to present you oclHashcat-lite v0.07. You can download it here.

Highlights:
  • Full support for mixed GPU types due to own thread management.
  • NVidia kernels has been vectorized - gave nice GPU utilization boost.
  • Improved DES kernel, more than 20% performance boost on AMD cards.
  • Broke 20B/s mark on stock clocked hd6990 @ MD4.
  • Switched to AMD APP SDK v2.5.
  • Added kernels for nsldap, nsldaps, MSSQL(2000), MSSQL(2005) and Cisco-PIX MD5.
  • Rewritten --restore code from scratch. It is much more intuitive now.
  • Parameters for distributed computing simplified.

NVidia driver notes:

Nothing special here. Everything should work out-of-the-box.

AMD driver notes:

Starting with this version, Catalyst v11.11 is the new recommended driver version.

Nothing to worry, even if oclHashcat-plus has not been updated yet, it will continue to work fine.

Linux users benefit from Catalyst v11.11 for two more reasons:
  • The 100% CPU killer bug problem is fixed.
  • It finally ships with an embedded OpenCL runtime. In other words: no more need to install the AMD APP SDK.

Important: You have to uninstall the AMD APP SDK v2.4. Then, after uninstalling the SDK, make sure the correct libOpenCL.so is loaded (the one which ships with the driver). You can verify this by doing an "ldd oclHashcat-lite64.bin" and check the path. It should link to "/usr/lib/libOpenCL.so.1". If it is not found, you may have to create an symlink from "libOpenCL.so" to "libOpenCL.so.1". For some unknown reason the Catalyst installer did not do this automatically on my box.

Performance improvements:

AMD hd5970 (Linux Ubuntu 11.10, 64bit, Catalyst v11.11)

Code:
vBulletin > v3.8.5: 33,50% SHA1: 0.47% sha1($pass.$salt): 0.56% MySQL > v4.1: 1.73% MD4: 1.11% SHA256: 12.58% descrypt, DES(Unix): 23.21% SL3: 2.44%

AMD hd6990 (Windows7, 64bit, Catalyst v11.11)

Code:
MD5: 4.64% md5($pass.$salt): 4.50% md5(md5($pass)): 11.22% vBulletin < v3.8.5: 11.55% vBulletin > v3.8.5: 29.96% SHA1: 3.39% sha1($pass.$salt): 3.14% MySQL > v4.1: 7.65% MD4: 2.22% NTLM: 0.43% DCC: 6.77% MSSQL: 3.19% SHA256: 8.35% descrypt, DES(Unix): 20.44% SL3: 3.33% Oracle 11G: 3.20%

NVidia gtx580 (Ubuntu 10.10, 64 bit, ForceWare 280.13)

Code:
MD5: 1.53% md5($pass.$salt): 1.53% md5(md5($pass)): 2.93% vBulletin < v3.8.5: 2.93% SHA1: 6.21% sha1($pass.$salt): 6.21% MySQL > v4.1: 1.89% MD4: 17.67% NTLM: 18.67% DCC: 16.57% descrypt, DES(Unix): 5.60% SL3: 6.06% Oracle 11G: 6.33%

NVidia 560 Ti (Ubuntu 11.10, 64 bit, ForceWare 280.13)

Code:
MD5: 2.53% md5($pass.$salt): 2.53% MD4: 23.69% NTLM: 14.97% DCC: 0.85%

Full changelog:


Quote:type: feature
file: kernels
desc: added support for AMD GPU's "Devastator" and "Scrapper"

type: feature
file: kernels
desc: added -m 600 = nsldap, SHA-1(Base64), Netscape LDAP SHA

type: feature
file: kernels
desc: added -m 700 = nsldaps, SSHA-1(Base64), Netscape LDAP SSHA

type: feature
file: kernels
desc: added -m 1300 = MSSQL(2000)

type: feature
file: kernels
desc: added -m 2300 = MSSQL(2005)

type: feature
file: kernels
desc: added -m 2400 = Cisco-PIX MD5

type: feature
file: kernels
desc: added support for vector datatypes on NV for better sm_21 utilization

type: feature
file: host programs
desc: added support for mixed GPU types (example: hd5970 and hd6850)

type: feature
file: host programs
desc: simplified --pw-skip and --pw-limit for more intuitive usuage, see hashcat wiki for details

type: feature
file: host programs
desc: added --pw-skip-plain and --pw-limit-plain, user can specify a string instead of a number

type: feature
file: host programs
desc: added support for setting CPU affinity. Defaults: Linux unlocked, Windows locked to CPU #1
cred: MrUltimate

type: feature
file: host programs
desc: added display of the mask in status screen
cred: tatgdi

type: feature
file: host programs
desc: added display of the hash in status screen

type: feature
file: host programs
desc: changed restore-timer function. if set to 0, the restore-file is written instantly on progress

type: change
file: host programs
desc: changed restore-timer default value to 0

type: change
file: kernels
desc: switched to AMD Accelerated Parallel Processing "APP" SDK v2.5

type: change
file: host programs
desc: changed outfile-formats for more flexibility. default value is 3. see --help for more
cred: TheFire

type: change
file: host programs
desc: recalibrated defaults for gpu_accel and gpu_loops that kernels run fast but not to aggressive

type: change
file: host programs
desc: changed speed display compressing threshold from 10000 to 100000

type: change
file: kernels
desc: removed kernel encryption. thus, archive file became smaller and startup-time reduced

type: bug
file: host programs
desc: fixed some typos in error messages

type: bug
file: host programs
desc: fixed bug in --gpu-async which was not enabled even if specified

type: bug
file: host programs
desc: fixed NVidia issue: cuStreamsynchronize() 700

type: bug
file: host programs
desc: workarounded AMD issue: "100% CPU killer bug". Linux only, requires Catalyst >= 11.11

type: bug
file: host programs
desc: workarounded AMD issue: ../../src/xcb_io.c:140: dequeue_pending_request

--
atom
]]>
I am very proud to present you oclHashcat-lite v0.07. You can download it here.

Highlights:
  • Full support for mixed GPU types due to own thread management.
  • NVidia kernels has been vectorized - gave nice GPU utilization boost.
  • Improved DES kernel, more than 20% performance boost on AMD cards.
  • Broke 20B/s mark on stock clocked hd6990 @ MD4.
  • Switched to AMD APP SDK v2.5.
  • Added kernels for nsldap, nsldaps, MSSQL(2000), MSSQL(2005) and Cisco-PIX MD5.
  • Rewritten --restore code from scratch. It is much more intuitive now.
  • Parameters for distributed computing simplified.

NVidia driver notes:

Nothing special here. Everything should work out-of-the-box.

AMD driver notes:

Starting with this version, Catalyst v11.11 is the new recommended driver version.

Nothing to worry, even if oclHashcat-plus has not been updated yet, it will continue to work fine.

Linux users benefit from Catalyst v11.11 for two more reasons:
  • The 100% CPU killer bug problem is fixed.
  • It finally ships with an embedded OpenCL runtime. In other words: no more need to install the AMD APP SDK.

Important: You have to uninstall the AMD APP SDK v2.4. Then, after uninstalling the SDK, make sure the correct libOpenCL.so is loaded (the one which ships with the driver). You can verify this by doing an "ldd oclHashcat-lite64.bin" and check the path. It should link to "/usr/lib/libOpenCL.so.1". If it is not found, you may have to create an symlink from "libOpenCL.so" to "libOpenCL.so.1". For some unknown reason the Catalyst installer did not do this automatically on my box.

Performance improvements:

AMD hd5970 (Linux Ubuntu 11.10, 64bit, Catalyst v11.11)

Code:
vBulletin > v3.8.5: 33,50% SHA1: 0.47% sha1($pass.$salt): 0.56% MySQL > v4.1: 1.73% MD4: 1.11% SHA256: 12.58% descrypt, DES(Unix): 23.21% SL3: 2.44%

AMD hd6990 (Windows7, 64bit, Catalyst v11.11)

Code:
MD5: 4.64% md5($pass.$salt): 4.50% md5(md5($pass)): 11.22% vBulletin < v3.8.5: 11.55% vBulletin > v3.8.5: 29.96% SHA1: 3.39% sha1($pass.$salt): 3.14% MySQL > v4.1: 7.65% MD4: 2.22% NTLM: 0.43% DCC: 6.77% MSSQL: 3.19% SHA256: 8.35% descrypt, DES(Unix): 20.44% SL3: 3.33% Oracle 11G: 3.20%

NVidia gtx580 (Ubuntu 10.10, 64 bit, ForceWare 280.13)

Code:
MD5: 1.53% md5($pass.$salt): 1.53% md5(md5($pass)): 2.93% vBulletin < v3.8.5: 2.93% SHA1: 6.21% sha1($pass.$salt): 6.21% MySQL > v4.1: 1.89% MD4: 17.67% NTLM: 18.67% DCC: 16.57% descrypt, DES(Unix): 5.60% SL3: 6.06% Oracle 11G: 6.33%

NVidia 560 Ti (Ubuntu 11.10, 64 bit, ForceWare 280.13)

Code:
MD5: 2.53% md5($pass.$salt): 2.53% MD4: 23.69% NTLM: 14.97% DCC: 0.85%

Full changelog:


Quote:type: feature
file: kernels
desc: added support for AMD GPU's "Devastator" and "Scrapper"

type: feature
file: kernels
desc: added -m 600 = nsldap, SHA-1(Base64), Netscape LDAP SHA

type: feature
file: kernels
desc: added -m 700 = nsldaps, SSHA-1(Base64), Netscape LDAP SSHA

type: feature
file: kernels
desc: added -m 1300 = MSSQL(2000)

type: feature
file: kernels
desc: added -m 2300 = MSSQL(2005)

type: feature
file: kernels
desc: added -m 2400 = Cisco-PIX MD5

type: feature
file: kernels
desc: added support for vector datatypes on NV for better sm_21 utilization

type: feature
file: host programs
desc: added support for mixed GPU types (example: hd5970 and hd6850)

type: feature
file: host programs
desc: simplified --pw-skip and --pw-limit for more intuitive usuage, see hashcat wiki for details

type: feature
file: host programs
desc: added --pw-skip-plain and --pw-limit-plain, user can specify a string instead of a number

type: feature
file: host programs
desc: added support for setting CPU affinity. Defaults: Linux unlocked, Windows locked to CPU #1
cred: MrUltimate

type: feature
file: host programs
desc: added display of the mask in status screen
cred: tatgdi

type: feature
file: host programs
desc: added display of the hash in status screen

type: feature
file: host programs
desc: changed restore-timer function. if set to 0, the restore-file is written instantly on progress

type: change
file: host programs
desc: changed restore-timer default value to 0

type: change
file: kernels
desc: switched to AMD Accelerated Parallel Processing "APP" SDK v2.5

type: change
file: host programs
desc: changed outfile-formats for more flexibility. default value is 3. see --help for more
cred: TheFire

type: change
file: host programs
desc: recalibrated defaults for gpu_accel and gpu_loops that kernels run fast but not to aggressive

type: change
file: host programs
desc: changed speed display compressing threshold from 10000 to 100000

type: change
file: kernels
desc: removed kernel encryption. thus, archive file became smaller and startup-time reduced

type: bug
file: host programs
desc: fixed some typos in error messages

type: bug
file: host programs
desc: fixed bug in --gpu-async which was not enabled even if specified

type: bug
file: host programs
desc: fixed NVidia issue: cuStreamsynchronize() 700

type: bug
file: host programs
desc: workarounded AMD issue: "100% CPU killer bug". Linux only, requires Catalyst >= 11.11

type: bug
file: host programs
desc: workarounded AMD issue: ../../src/xcb_io.c:140: dequeue_pending_request

--
atom
]]> <![CDATA[oclHashcat-lite v0.06]]> https://hashcat.net/forum/thread-411.html Wed, 17 Aug 2011 08:20:05 +0000 atom]]> https://hashcat.net/forum/thread-411.html http://hashcat.net/oclhashcat-lite/

* changes v0.05 -> v0.06:

Code:
type: performance increase file: kernels desc: MD5: AMD 1,07%, NVidia 0,62% desc: md5($pass.$salt): AMD 1,37%, NVidia 8,10% desc: md5(md5($pass)): AMD 0,94%, NVidia 0% desc: vBulletin < v3.8.5: AMD 0,30%, NVidia 0% desc: SHA1: AMD 11,14%, NVidia 13,62% desc: sha1($pass.$salt): AMD 16,96%, NVidia 39,10% desc: MySQL > v4.1: AMD 1,99%, NVidia 7,15% desc: MD4: AMD 13,46%, NVidia 3,34% desc: NTLM: AMD 13,16%, NVidia 2,57% desc: DCC: AMD 34,20%, NVidia 0,89% desc: MSSQL: AMD 11,23%, NVidia 17,89% desc: SL3: AMD 12,24%, NVidia 13,48% desc: Oracle 11G: AMD 16,93%, NVidia 13,53% type: password length increase file: kernels desc: MD5: from 15 to 55 desc: md5($pass.$salt): from 15 to 55 desc: md5(md5($pass)): from 15 to 55 desc: vBulletin < v3.8.5: from 15 to 55 desc: SHA1: from 15 to 55 desc: sha1($pass.$salt): from 15 to 55 desc: MySQL > v4.1: from 15 to 55 desc: MD4: from 15 to 55 desc: NTLM: from 15 to 27 desc: DCC: from 15 to 27 desc: MSSQL: from 15 to 25 desc: SHA256: from 15 to 55 desc: Oracle 11G: from 15 to 45 type: feature file: kernels desc: added -m 15 = vBulletin > v3.8.5 cred: chick0n type: feature file: kernels desc: increased salt length for DCC from 7 to 19 cred: Rabbitz type: feature file: host programs desc: hardcoded cpu affinity mask to one (cpu #0) to save energy cred: randyberger type: feature file: host programs desc: added --pw-skip and --pw-limit parameters for distributed computing cred: d3ad0ne type: feature file: host programs desc: added status codes on exit, see status_codes.txt for listing cred: hermix type: bug file: host programs desc: rewritten restore function check from scratch cred: anonymous type: bug file: host programs desc: fixed multiple instances check cred: FractalizeR type: bug file: host programs desc: fixed 8 bit characters from russian alphabet cred: Rolf

--
atom
]]> http://hashcat.net/oclhashcat-lite/

* changes v0.05 -> v0.06:

Code:
type: performance increase file: kernels desc: MD5: AMD 1,07%, NVidia 0,62% desc: md5($pass.$salt): AMD 1,37%, NVidia 8,10% desc: md5(md5($pass)): AMD 0,94%, NVidia 0% desc: vBulletin < v3.8.5: AMD 0,30%, NVidia 0% desc: SHA1: AMD 11,14%, NVidia 13,62% desc: sha1($pass.$salt): AMD 16,96%, NVidia 39,10% desc: MySQL > v4.1: AMD 1,99%, NVidia 7,15% desc: MD4: AMD 13,46%, NVidia 3,34% desc: NTLM: AMD 13,16%, NVidia 2,57% desc: DCC: AMD 34,20%, NVidia 0,89% desc: MSSQL: AMD 11,23%, NVidia 17,89% desc: SL3: AMD 12,24%, NVidia 13,48% desc: Oracle 11G: AMD 16,93%, NVidia 13,53% type: password length increase file: kernels desc: MD5: from 15 to 55 desc: md5($pass.$salt): from 15 to 55 desc: md5(md5($pass)): from 15 to 55 desc: vBulletin < v3.8.5: from 15 to 55 desc: SHA1: from 15 to 55 desc: sha1($pass.$salt): from 15 to 55 desc: MySQL > v4.1: from 15 to 55 desc: MD4: from 15 to 55 desc: NTLM: from 15 to 27 desc: DCC: from 15 to 27 desc: MSSQL: from 15 to 25 desc: SHA256: from 15 to 55 desc: Oracle 11G: from 15 to 45 type: feature file: kernels desc: added -m 15 = vBulletin > v3.8.5 cred: chick0n type: feature file: kernels desc: increased salt length for DCC from 7 to 19 cred: Rabbitz type: feature file: host programs desc: hardcoded cpu affinity mask to one (cpu #0) to save energy cred: randyberger type: feature file: host programs desc: added --pw-skip and --pw-limit parameters for distributed computing cred: d3ad0ne type: feature file: host programs desc: added status codes on exit, see status_codes.txt for listing cred: hermix type: bug file: host programs desc: rewritten restore function check from scratch cred: anonymous type: bug file: host programs desc: fixed multiple instances check cred: FractalizeR type: bug file: host programs desc: fixed 8 bit characters from russian alphabet cred: Rolf

--
atom
]]> <![CDATA[oclHashcat-lite v0.05]]> https://hashcat.net/forum/thread-409.html Wed, 17 Aug 2011 08:16:57 +0000 atom]]> https://hashcat.net/forum/thread-409.html http://hashcat.net/oclhashcat-lite/

* changes v0.04 -> v0.05:

Code:
type: bug file: host programs desc: fixed bug, option parsing, --restore-timer aborted oclHashcat cred: Farras type: bug file: host programs desc: fixed bug, option parsing, --restore was not using correct position cred: adolfotregos

--
atom
]]> http://hashcat.net/oclhashcat-lite/

* changes v0.04 -> v0.05:

Code:
type: bug file: host programs desc: fixed bug, option parsing, --restore-timer aborted oclHashcat cred: Farras type: bug file: host programs desc: fixed bug, option parsing, --restore was not using correct position cred: adolfotregos

--
atom
]]> <![CDATA[oclHashcat-lite v0.04]]> https://hashcat.net/forum/thread-408.html Wed, 17 Aug 2011 08:16:20 +0000 atom]]> https://hashcat.net/forum/thread-408.html http://hashcat.net/oclhashcat-lite/

* changes v0.03 -> v0.04:

Code:
type: feature file: kernels desc: added -m 1300 = MSSQL type: feature file: kernels desc: added -m 1500 = DES(Unix) cred: boy1284 type: feature file: kernels desc: added -m 1900 = SL3 type: feature file: kernels desc: added -m 2000 = Oracle 11G type: improvement file: kernels desc: performance increase in NTLM and DCC kernels between +1% and +2% type: improvement file: kernels desc: performance increase in SL3 between +2% and +4% type: driver file: kernels desc: added support for AMD Catalyst v11.4 and SDK 2.4 type: driver file: kernels desc: added support for NVidia ForceWare v270.x type: feature file: host programs desc: added --restore-timer parameter, default 60 cred: Mr.Ultimate type: feature file: host programs desc: added --outfile-watchdog parameter, default 60 cred: ATF type: improvement file: host programs desc: improved performance on plains with length 4 and 5 type: improvement file: host programs desc: renamed parameters --output-* to --outfile-* cred: radix type: improvement file: host programs desc: added plain length to status display cred: tatgdi type: improvement file: host programs desc: added hash type to status display cred: radix type: improvement file: host programs desc: added status types "Cracked" and "Exhausted" to status display type: bug file: host programs desc: fixed bug, race-condition, rename new restore-file to current cred: Alinus type: bug file: host programs desc: fixed bug, divide-by-zero, crashes oclHashcat-lite when hitting "s"

--
atom
]]> http://hashcat.net/oclhashcat-lite/

* changes v0.03 -> v0.04:

Code:
type: feature file: kernels desc: added -m 1300 = MSSQL type: feature file: kernels desc: added -m 1500 = DES(Unix) cred: boy1284 type: feature file: kernels desc: added -m 1900 = SL3 type: feature file: kernels desc: added -m 2000 = Oracle 11G type: improvement file: kernels desc: performance increase in NTLM and DCC kernels between +1% and +2% type: improvement file: kernels desc: performance increase in SL3 between +2% and +4% type: driver file: kernels desc: added support for AMD Catalyst v11.4 and SDK 2.4 type: driver file: kernels desc: added support for NVidia ForceWare v270.x type: feature file: host programs desc: added --restore-timer parameter, default 60 cred: Mr.Ultimate type: feature file: host programs desc: added --outfile-watchdog parameter, default 60 cred: ATF type: improvement file: host programs desc: improved performance on plains with length 4 and 5 type: improvement file: host programs desc: renamed parameters --output-* to --outfile-* cred: radix type: improvement file: host programs desc: added plain length to status display cred: tatgdi type: improvement file: host programs desc: added hash type to status display cred: radix type: improvement file: host programs desc: added status types "Cracked" and "Exhausted" to status display type: bug file: host programs desc: fixed bug, race-condition, rename new restore-file to current cred: Alinus type: bug file: host programs desc: fixed bug, divide-by-zero, crashes oclHashcat-lite when hitting "s"

--
atom
]]> <![CDATA[oclHashcat-lite v0.03]]> https://hashcat.net/forum/thread-407.html Wed, 17 Aug 2011 08:15:37 +0000 atom]]> https://hashcat.net/forum/thread-407.html http://hashcat.net/oclhashcat-lite/

* changes v0.02 -> v0.03:

Code:
type: bug file: cudaHashcat-lite, oclHashcat-lite desc: fixed a bug in security causing hash was not found randomly cred: RaNdy type: bug file: cudaHashcat-lite, oclHashcat-lite desc: fixed a bug in --restore if command-line contains --pw-skip cred: Ciukut type: bug file: cudaHashcat-lite, oclHashcat-lite desc: fixed a bug in --restore if command-line contains --pw-min cred: hermix

--
atom
]]> http://hashcat.net/oclhashcat-lite/

* changes v0.02 -> v0.03:

Code:
type: bug file: cudaHashcat-lite, oclHashcat-lite desc: fixed a bug in security causing hash was not found randomly cred: RaNdy type: bug file: cudaHashcat-lite, oclHashcat-lite desc: fixed a bug in --restore if command-line contains --pw-skip cred: Ciukut type: bug file: cudaHashcat-lite, oclHashcat-lite desc: fixed a bug in --restore if command-line contains --pw-min cred: hermix

--
atom
]]> <![CDATA[oclHashcat-lite v0.02]]> https://hashcat.net/forum/thread-362.html Sun, 10 Apr 2011 19:51:06 +0000 atom]]> https://hashcat.net/forum/thread-362.html
The main features of oclHashcat-lite is that it focuses on single hash cracking to get highest possible performance. It utilizes BIT_ALIGN and BFI_INT on AMD gpus and reverses MD4 and MD5 kernels.

Check out the homepage http://hashcat.net/oclhashcat-lite for downloads, features and more detailed informations.

Happy cracking!!
]]>
The main features of oclHashcat-lite is that it focuses on single hash cracking to get highest possible performance. It utilizes BIT_ALIGN and BFI_INT on AMD gpus and reverses MD4 and MD5 kernels.

Check out the homepage http://hashcat.net/oclhashcat-lite for downloads, features and more detailed informations.

Happy cracking!!
]]> <![CDATA[oclHashcat-lite leaked !!!]]> https://hashcat.net/forum/thread-345.html Sat, 26 Mar 2011 20:16:12 +0000 atom]]> https://hashcat.net/forum/thread-345.html
today i got some bad news. It seems a oclHashcat-lite beta tester ripped me off and now sells his modified oclHashcat-lite version as a new SL3 unlocking solution. Needless to say this is clear violation of my EULA.

See here: http://forum.gsmhosting.com/vbb/f299/sl3...l-1235118/

To all potential customers: The beta version this guys sells is not working.
  • The version has Bugs. It will find your hash only sporadically. Chances are 50/50.
  • The version does not support restore at all.
  • He says it works on windows with hd5970. He is wrong. oclHashcat-lite bases on OpenCL but OpenCL support for hd5970 it not yet working on windows. It is known the 2nd GPU does not work, see AMDs driver compatibility List: http://developer.amd.com/gpu/AMDAPPSDK/p...ility.aspx

It makes no sense to sell it. oclHashcat-lite will be free for all when i release it. I did not yet release it because it is not finished. Now i have to think about the consequences of this violation. I feel myself deceived.

--
atom
]]>
today i got some bad news. It seems a oclHashcat-lite beta tester ripped me off and now sells his modified oclHashcat-lite version as a new SL3 unlocking solution. Needless to say this is clear violation of my EULA.

See here: http://forum.gsmhosting.com/vbb/f299/sl3...l-1235118/

To all potential customers: The beta version this guys sells is not working.
  • The version has Bugs. It will find your hash only sporadically. Chances are 50/50.
  • The version does not support restore at all.
  • He says it works on windows with hd5970. He is wrong. oclHashcat-lite bases on OpenCL but OpenCL support for hd5970 it not yet working on windows. It is known the 2nd GPU does not work, see AMDs driver compatibility List: http://developer.amd.com/gpu/AMDAPPSDK/p...ility.aspx

It makes no sense to sell it. oclHashcat-lite will be free for all when i release it. I did not yet release it because it is not finished. Now i have to think about the consequences of this violation. I feel myself deceived.

--
atom
]]>