hashcat Forum › Support › hashcat v
7.1.2 slower than 6.1.2 for SHA512

Threaded Mode
7.1.2 slower than 6.1.2 for SHA512
zamgold Offline
Member
***
Posts: 53
Threads: 15
Joined: Jan 2015
#1
08-26-2025, 12:44 PM
Hi. I'm testing new version of hashcat 7.1.2..
I noticed that algorithm 1800 (sha512) works 3x slower than previos version hashcat 6.1.2...


hashcat (v7.1.2) starting

* Device #2: Outdated or broken Intel OpenCL runtime '495.29.05' detected!

You are STRONGLY encouraged to use the officially supported runtime.
See hashcat.net for the officially supported Intel OpenCL runtime.
See also: https://hashcat.net/faq/wrongdriver
You can use --force to override this, but do not report related errors.

CUDA API (CUDA 11.5)
====================
* Device #01: NVIDIA GeForce RTX 3080, 9576/10018 MB, 68MCU

OpenCL API (OpenCL 3.0 CUDA 11.5.56) - Platform #1 [NVIDIA Corporation]
=======================================================================
* Device #02: NVIDIA GeForce RTX 3080, skipped

Minimum password length supported by kernel: 0
Maximum password length supported by kernel: 256
Minimum salt length supported by kernel: 0
Maximum salt length supported by kernel: 256

Hashes: 1 digests; 1 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates
Rules: 1

Optimizers applied:
* Zero-Byte
* Single-Hash
* Single-Salt
* Uses-64-Bit
* Register-Limit

ATTENTION! Pure (unoptimized) backend kernels selected.
Pure kernels can crack longer passwords, but drastically reduce performance.
If you want to switch to optimized kernels, append -O to your commandline.
See the above message to find out about the exact limits.

Watchdog: Temperature abort trigger set to 90c

Host memory allocated for this attack: 1305 MB (56445 MB free)

Dictionary cache hit:
* Filename..: /media/ntfs1/dictionary/dict.dic
* Passwords.: 855284955
* Bytes.....: 10027391827
* Keyspace..: 855284955

Cracking performance lower than expected?

* Append -O to the commandline.
  This lowers the maximum supported password/salt length (usually down to 32).

* Append -w 3 to the commandline.
  This can cause your screen to lag.

* Append -S to the commandline.
  This has a drastic speed impact but can be better for specific attacks.
  Typical scenarios are a small wordlist but a large ruleset.

* Update your backend API runtime / driver the right way:
  https://hashcat.net/faq/wrongdriver

* Create more work items to make use of your parallelization power:
  https://hashcat.net/faq/morework

[s]tatus [p]ause ypass [c]heckpoint [f]inish [q]uit =>


Session..........: hashcat
Status...........: Running
Hash.Mode........: 1800 (sha512crypt $6$, SHA512 (Unix))
Hash.Target......: $6$rounds=10000$salt$data_hash
Time.Started.....: Tue Aug 26 15:19:03 2025 (12 secs)
Time.Estimated...: Wed Aug 27 03:18:52 2025 (11 hours, 59 mins)
Kernel.Feature...: Pure Kernel (password length 0-256 bytes)
Guess.Base.......: File (/media/ntfs1/dictionary/dict.dic)
Guess.Queue......: 1/1 (100.00%)
[b]Speed.#01........:    19804 H/s (14.87ms) @ Accel:4 Loops:124 Thr:96 Vec:1[/b]
Recovered........: 0/1 (0.00%) Digests (total), 0/1 (0.00%) Digests (new)
Progress.........: 208896/855284955 (0.02%)
Rejected.........: 0/208896 (0.00%)
Restore.Point....: 208896/855284955 (0.02%)
Restore.Sub.#01..: Salt:0 Amplifier:0-1 Iteration:5208-5332
Candidate.Engine.: Device Generator
Candidates.#01...: !mpl@u5!8!l!7y -> !n4d3qu4+3n3ss
Hardware.Mon.#01.: Temp: 55c Fan: 59% Util: 94% Core:1950MHz Mem:9251MHz Bus:16

[s]tatus [p]ause ypass [c]heckpoint [f]inish [q]uit =>


[b]For version 6.1.2:[/b]

hashcat (v6.2.6) starting

* Device #1: WARNING! Kernel exec timeout is not disabled.
            This may cause "CL_OUT_OF_RESOURCES" or related errors.
            To disable the timeout, see: https://hashcat.net/q/timeoutpatch
* Device #2: WARNING! Kernel exec timeout is not disabled.
            This may cause "CL_OUT_OF_RESOURCES" or related errors.
            To disable the timeout, see: https://hashcat.net/q/timeoutpatch
CUDA API (CUDA 11.5)
====================
* Device #1: NVIDIA GeForce RTX 3080, 9576/10018 MB, 68MCU

OpenCL API (OpenCL 3.0 CUDA 11.5.56) - Platform #1 [NVIDIA Corporation]
=======================================================================
* Device #2: NVIDIA GeForce RTX 3080, skipped

Minimum password length supported by kernel: 0
Maximum password length supported by kernel: 256

Hashes: 1 digests; 1 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates
Rules: 1

Optimizers applied:
* Zero-Byte
* Single-Hash
* Single-Salt
* Uses-64-Bit

ATTENTION! Pure (unoptimized) backend kernels selected.
Pure kernels can crack longer passwords, but drastically reduce performance.
If you want to switch to optimized kernels, append -O to your commandline.
See the above message to find out about the exact limits.

Watchdog: Temperature abort trigger set to 90c

Host memory required for this attack: 281 MB

Dictionary cache hit:
* Filename..: /media/ntfs1/dictionary/dict.dic
* Passwords.: 855284955
* Bytes.....: 10027391827
* Keyspace..: 855284955

Cracking performance lower than expected?

* Append -O to the commandline.
  This lowers the maximum supported password/salt length (usually down to 32).

* Append -w 3 to the commandline.
  This can cause your screen to lag.

* Append -S to the commandline.
  This has a drastic speed impact but can be better for specific attacks.
  Typical scenarios are a small wordlist but a large ruleset.

* Update your backend API runtime / driver the right way:
  https://hashcat.net/faq/wrongdriver

* Create more work items to make use of your parallelization power:
  https://hashcat.net/faq/morework

[s]tatus [p]ause ypass [c]heckpoint [f]inish [q]uit =>


Session..........: hashcat
Status...........: Running
Hash.Mode........: 1800 (sha512crypt $6$, SHA512 (Unix))
Hash.Target......: $6$rounds=10000$salt$data_hash
Time.Started.....: Tue Aug 26 15:21:20 2025 (18 secs)
Time.Estimated...: Tue Aug 26 19:08:44 2025 (3 hours, 47 mins)
Kernel.Feature...: Pure Kernel
Guess.Base.......: File (/media/ntfs1/dictionary/dict.dic)
Guess.Queue......: 1/1 (100.00%)
[b]Speed.#1.........:    62680 H/s (6.16ms) @ Accel:256 Loops:128 Thr:128 Vec:1[/b]
Recovered........: 0/1 (0.00%) Digests (total), 0/1 (0.00%) Digests (new)
Progress.........: 1146880/855284955 (0.13%)
Rejected.........: 0/1146880 (0.00%)
Restore.Point....: 1146880/855284955 (0.13%)
Restore.Sub.#1...: Salt:0 Amplifier:0-1 Iteration:1664-1792
Candidate.Engine.: Device Generator
Candidates.#1....: ,ecmrf1985 -> ,fcntn05
Hardware.Mon.#1..: Temp: 56c Fan: 59% Util: 89% Core:1905MHz Mem:9251MHz Bus:16

[s]tatus [p]ause ypass [c]heckpoint [f]inish [q]uit =>


[b]I tested on different GPUs NVidia 3080 and   GPUs NVidia 4090..this algorithm on version 7.1.2 works slower.[/b]
Find
Reply
atom Offline
Administrator
*******
Posts: 5,233
Threads: 233
Joined: Apr 2010
#2
08-26-2025, 02:05 PM
It should not, please update to latest CUDA version 12.9 or higher.
Website Find
Reply
zamgold Offline
Member
***
Posts: 53
Threads: 15
Joined: Jan 2015
#3
08-27-2025, 10:15 AM
(08-26-2025, 02:05 PM)atom Wrote: It should not, please update to latest CUDA version 12.9 or higher.

Hi. I installed CUDA version 13.0...But 7.1.2 slower than 6.1.2


hashcat (v7.1.2) starting

CUDA API (CUDA 13.0)
====================
* Device #01: NVIDIA GeForce RTX 3080, 9400/9875 MB, 68MCU

OpenCL API (OpenCL 3.0 CUDA 13.0.78) - Platform #1 [NVIDIA Corporation]
=======================================================================
* Device #02: NVIDIA GeForce RTX 3080, skipped

Minimum password length supported by kernel: 0
Maximum password length supported by kernel: 256
Minimum salt length supported by kernel: 0
Maximum salt length supported by kernel: 256

Hashes: 1 digests; 1 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates
Rules: 1

Optimizers applied:
* Zero-Byte
* Single-Hash
* Single-Salt
* Uses-64-Bit
* Register-Limit

ATTENTION! Pure (unoptimized) backend kernels selected.
Pure kernels can crack longer passwords, but drastically reduce performance.
If you want to switch to optimized kernels, append -O to your commandline.
See the above message to find out about the exact limits.

Watchdog: Temperature abort trigger set to 90c

Host memory allocated for this attack: 1267 MB (61238 MB free)

Dictionary cache hit:
* Filename..: /media/ntfs1/dictionary/dict.dic
* Passwords.: 855284955
* Bytes.....: 10027391827
* Keyspace..: 855284955

Cracking performance lower than expected?

* Append -O to the commandline.
  This lowers the maximum supported password/salt length (usually down to 32).

* Append -w 3 to the commandline.
  This can cause your screen to lag.

* Append -S to the commandline.
  This has a drastic speed impact but can be better for specific attacks.
  Typical scenarios are a small wordlist but a large ruleset.

* Update your backend API runtime / driver the right way:
  https://hashcat.net/faq/wrongdriver

* Create more work items to make use of your parallelization power:
  https://hashcat.net/faq/morework

[s]tatus [p]ause ypass [c]heckpoint [f]inish [q]uit =>


Session..........: hashcat
Status...........: Running
Hash.Mode........: 1800 (sha512crypt $6$, SHA512 (Unix))
Hash.Target......: $6$rounds=10000$salt$data_hash
Time.Started.....: Wed Aug 27 13:13:54 2025 (15 secs)
Time.Estimated...: Thu Aug 28 01:11:19 2025 (11 hours, 57 mins)
Kernel.Feature...: Pure Kernel (password length 0-256 bytes)
Guess.Base.......: File (/media/ntfs1/dictionary/dict.dic)
Guess.Queue......: 1/1 (100.00%)
[b]Speed.#01........:    19870 H/s (15.28ms) @ Accel:4 Loops:124 Thr:96 Vec:1
Recovered........: 0/1 (0.00%) Digests (total), 0/1 (0.00%) Digests (new)
Progress.........: 261120/855284955 (0.03%)
Rejected.........: 0/261120 (0.00%)
Restore.Point....: 261120/855284955 (0.03%)
Restore.Sub.#01..: Salt:0 Amplifier:0-1 Iteration:7440-7564
Candidate.Engine.: Device Generator
Candidates.#01...: !nc4rcer4+0rs -> !ngra+e$
Hardware.Mon.#01.: Temp: 55c Fan: 59% Util: 99% Core:1950MHz Mem:9251MHz Bus:16

[s]tatus [p]ause ypass [c]heckpoint [f]inish [q]uit => q
Find
Reply
atom Offline
Administrator
*******
Posts: 5,233
Threads: 233
Joined: Apr 2010
#4
08-27-2025, 11:38 AM
OK, please run again command on 7.1.2, add to command line: -n256 -u128 -T128 --force
Website Find
Reply
zamgold Offline
Member
***
Posts: 53
Threads: 15
Joined: Jan 2015
#5
08-27-2025, 12:11 PM
(08-27-2025, 11:38 AM)atom Wrote: OK, please run again command on 7.1.2, add to command line: -n256 -u128 -T128 --force

that didn't help Sad
Find
Reply
matrix Offline
c0d3r
**
Posts: 20
Threads: 1
Joined: May 2012
#6
08-27-2025, 04:25 PM
(08-27-2025, 12:11 PM)zamgold Wrote:
(08-27-2025, 11:38 AM)atom Wrote: OK, please run again command on 7.1.2, add to command line: -n256 -u128 -T128 --force

that didn't help Sad

But it can help us. Could you paste the output for the test Jens asked you to do? Thanks
Find
Reply
zamgold Offline
Member
***
Posts: 53
Threads: 15
Joined: Jan 2015
#7
08-28-2025, 12:07 PM
(08-27-2025, 04:25 PM)matrix Wrote:
(08-27-2025, 12:11 PM)zamgold Wrote:
(08-27-2025, 11:38 AM)atom Wrote: OK, please run again command on 7.1.2, add to command line: -n256 -u128 -T128 --force

that didn't help Sad

But it can help us. Could you paste the output for the test Jens asked you to do? Thanks

No problem. My command and output:

./hashcat -n256 -u128 -T128 --force -m 1800 -a 0 1800.hash /media/ntfs1/dictionary/dict.dic

hashcat (v7.1.2) starting

You have enabled --force to bypass dangerous warnings and errors!
This can hide serious problems and should only be done when debugging.
Do not report hashcat issues encountered when using --force.

CUDA API (CUDA 13.0)
====================
* Device #01: NVIDIA GeForce RTX 3080, 9400/9875 MB, 68MCU

OpenCL API (OpenCL 3.0 CUDA 13.0.78) - Platform #1 [NVIDIA Corporation]
=======================================================================
* Device #02: NVIDIA GeForce RTX 3080, skipped

Minimum password length supported by kernel: 0
Maximum password length supported by kernel: 256
Minimum salt length supported by kernel: 0
Maximum salt length supported by kernel: 256

Hashes: 1 digests; 1 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates
Rules: 1

Optimizers applied:
* Zero-Byte
* Single-Hash
* Single-Salt
* Uses-64-Bit
* Register-Limit

ATTENTION! Pure (unoptimized) backend kernels selected.
Pure kernels can crack longer passwords, but drastically reduce performance.
If you want to switch to optimized kernels, append -O to your commandline.
See the above message to find out about the exact limits.

Watchdog: Temperature abort trigger set to 90c

Host memory allocated for this attack: 1109 MB (60685 MB free)

Dictionary cache hit:
* Filename..: /media/ntfs1/dictionary/dict.dic
* Passwords.: 855284955
* Bytes.....: 10027391827
* Keyspace..: 855284955

[s]tatus [p]ause ypass [c]heckpoint [f]inish [q]uit =>


Session..........: hashcat
Status...........: Running
Hash.Mode........: 1800 (sha512crypt $6$, SHA512 (Unix))
Hash.Target......: $6$rounds=10000$salt$data_hash
Time.Started.....: Thu Aug 28 15:05:58 2025, (42 secs)
Time.Estimated...: Fri Aug 29 03:25:01 2025, (12 hours, 18 mins)
Kernel.Feature...: Pure Kernel (password length 0-256 bytes)
Guess.Base.......: File (/media/ntfs1/dictionary/dict.dic)
Guess.Queue......: 1/1 (100.00%)
[b]Speed.#01........:    19306 H/s (1471.60ms) @ Accel:256 Loops:128 Thr:128 Vec:1[/b]
Recovered........: 0/1 (0.00%) Digests (total), 0/1 (0.00%) Digests (new)
Progress.........: 0/855284955 (0.00%)
Rejected.........: 0/0 (0.00%)
Restore.Point....: 0/855284955 (0.00%)
Restore.Sub.#01..: Salt:0 Amplifier:0-1 Iteration:3712-3840
Candidate.Engine.: Device Generator
Candidates.#01...: $HEX[2020202020202020] -> 00v53u9b7fayqgva
Hardware.Mon.#01.: Temp: 62c Fan: 70% Util:100% Core:1935MHz Mem:9251MHz Bus:16
Find
Reply
atom Offline
Administrator
*******
Posts: 5,233
Threads: 233
Joined: Apr 2010
#8
08-28-2025, 03:49 PM
Yes I can reproduce. Not sure what's the issue.
Website Find
Reply
atom Offline
Administrator
*******
Posts: 5,233
Threads: 233
Joined: Apr 2010
#9
08-28-2025, 04:53 PM (This post was last modified: 08-28-2025, 04:56 PM by atom. Edit Reason: format )
As a workaround, you can stick to optimized mode, unless you really need password length >= 16 support, and enjoy 7.1.2 improved performance.

This is a 10k iterated sh512crypt on my 4090:

7.1.2:

Code:
Session..........: hashcat
Status...........: Running
Hash.Mode........: 1800 (sha512crypt $6$, SHA512 (Unix))
Hash.Target......: $6$rounds=10000$87$s7eRJvRffP/tMSxP8JfH8xHXN459xOC9...YGvBM1
Time.Started.....: Thu Aug 28 14:52:00 2025 (0 secs)
Time.Estimated...: Fri May 25 22:39:42 2029 (3 years, 270 days)
Kernel.Feature...: Optimized Kernel (password length 0-15 bytes)
Guess.Mask.......: ?a?a?a?a?a?a?a [7]
Guess.Queue......: 1/1 (100.00%)
Speed.#01........:   591.6 kH/s (86.88ms) @ Accel:16 Loops:1000 Thr:256 Vec:1
Recovered........: 0/1 (0.00%) Digests (total), 0/1 (0.00%) Digests (new)
Progress.........: 0/69833729609375 (0.00%)
Rejected.........: 0/0 (0.00%)
Restore.Point....: 0/735091890625 (0.00%)
Restore.Sub.#01..: Salt:0 Amplifier:0-1 Iteration:9000-10000
Candidate.Engine.: Device Generator
Candidates.#01...: sarieri -> s;iBONA
Hardware.Mon.#01.: Temp: 57c Fan:  0% Util: 99% Core:2655MHz Mem:10251MHz Bus:16

6.2.6:

Code:
Session..........: hashcat
Status...........: Running
Hash.Mode........: 1800 (sha512crypt $6$, SHA512 (Unix))
Hash.Target......: $6$rounds=10000$87$s7eRJvRffP/tMSxP8JfH8xHXN459xOC9...YGvBM1
Time.Started.....: Thu Aug 28 14:52:09 2025 (1 sec)
Time.Estimated...: Tue Jul 31 07:29:28 2029 (3 years, 336 days)
Kernel.Feature...: Optimized Kernel
Guess.Mask.......: ?a?a?a?a?a?a?a [7]
Guess.Queue......: 1/1 (100.00%)
Speed.#1.........:   564.2 kH/s (91.80ms) @ Accel:2048 Loops:1024 Thr:256 Vec:1
Recovered........: 0/1 (0.00%) Digests (total), 0/1 (0.00%) Digests (new)
Progress.........: 524288/69833729609375 (0.00%)
Rejected.........: 0/524288 (0.00%)
Restore.Point....: 0/735091890625 (0.00%)
Restore.Sub.#1...: Salt:0 Amplifier:1-2 Iteration:0-1024
Candidate.Engine.: Device Generator
Candidates.#1....: marieri -> m;iBONA
Hardware.Mon.#1..: Temp: 58c Fan: 30% Util: 99% Core:2625MHz Mem:10251MHz Bus:16
Website Find
Reply
atom Offline
Administrator
*******
Posts: 5,233
Threads: 233
Joined: Apr 2010
#10
08-28-2025, 08:15 PM
I think I found the issue and fixed it. Please try with hashcat.net/beta binary if is fast again and let me know.
Website Find
Reply