some strange craqcking perfomance mode 6,7 , MD5

[blaster666]

I am using 300k string wordlist + ?a?a?a?a mask, and for this set , I usually get 13 mins estimated time, but sometines it runs like this 

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
* Device #3: 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 #4: 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 12.2)
====================
* Device #1: NVIDIA GeForce RTX 4090, 23008/24563 MB, 128MCU
* Device #2: NVIDIA GeForce RTX 4090, 23008/24563 MB, 128MCU

OpenCL API (OpenCL 3.0 CUDA 12.2.138) - Platform #1 [NVIDIA Corporation]
========================================================================
* Device #3: NVIDIA GeForce RTX 4090, skipped
* Device #4: NVIDIA GeForce RTX 4090, skipped

Minimum password length supported by kernel: 0
Maximum password length supported by kernel: 31

Hashes: 38 digests; 38 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates

Optimizers applied:
* Optimized-Kernel
* Zero-Byte
* Precompute-Init
* Meet-In-The-Middle
* Early-Skip
* Not-Salted
* Not-Iterated
* Single-Salt
* Raw-Hash

Watchdog: Temperature abort trigger set to 90c

INFO: Removed 7 hashes found as potfile entries.

Host memory required for this attack: 2950 MB

The spped is :

Session..........: hashcat
Status...........: Running
Hash.Mode........: 0 (MD5)
Hash.Target......: md5_2508.hash
Time.Started.....: Thu Sep 14 12:52:18 2023 (2 mins, 1 sec)
Time.Estimated...: Thu Sep 14 13:35:13 2023 (40 mins, 54 secs)
Kernel.Feature...: Optimized Kernel
Guess.Base.......: Mask (?a?a?a?a) [4], Left Side
Guess.Mod........: File (D:\Master_master_MASTER.txt), Right Side
Guess.Charset....: -1 ?d?s, -2 ?l?u, -3 Undefined, -4 Undefined
Speed.#1.........: 14146.2 MH/s (0.78ms) @ Accel:1024 Loops:1024 Thr:32 Vec:1
Speed.#2.........: 15114.5 MH/s (0.74ms) @ Accel:1024 Loops:1024 Thr:32 Vec:1
Speed.#*.........: 29260.8 MH/s
Recovered........: 7/38 (18.42%) Digests (total), 0/38 (0.00%) Digests (new)
Progress.........: 3548673744120/75375711585000 (4.71%)
Rejected.........: 0/3548673744120 (0.00%)
Restore.Point....: 14460/925416 (1.56%)
Restore.Sub.#1...: Salt:0 Amplifier:37222400-37223424 Iteration:0-1024
Restore.Sub.#2...: Salt:0 Amplifier:45287424-45288448 Iteration:0-1024
Candidate.Engine.: Device Generator
Candidates.#1....: _7MVChaumer -> G5A5Councilor
Candidates.#2....: -QBluffable -> KU#yChaulmugras
Hardware.Mon.#1..: Temp: 53c Fan: 31% Util: 82% Core:2805MHz Mem:10501MHz Bus:8
Hardware.Mon.#2..: Temp: 50c Fan: 31% Util: 82% Core:2745MHz Mem:10251MHz Bus:8

After that, i just close hashcat window, and RESTART it , and voilà, the spped it 100gH\s

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
* Device #3: 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 #4: 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 12.2)
====================
* Device #1: NVIDIA GeForce RTX 4090, 23008/24563 MB, 128MCU
* Device #2: NVIDIA GeForce RTX 4090, 23008/24563 MB, 128MCU

OpenCL API (OpenCL 3.0 CUDA 12.2.138) - Platform #1 [NVIDIA Corporation]
========================================================================
* Device #3: NVIDIA GeForce RTX 4090, skipped
* Device #4: NVIDIA GeForce RTX 4090, skipped

Minimum password length supported by kernel: 0
Maximum password length supported by kernel: 31

Hashes: 38 digests; 38 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates

Optimizers applied:
* Optimized-Kernel
* Zero-Byte
* Precompute-Init
* Meet-In-The-Middle
* Early-Skip
* Not-Salted
* Not-Iterated
* Single-Salt
* Raw-Hash

Watchdog: Temperature abort trigger set to 90c

INFO: Removed 7 hashes found as potfile entries.

Host memory required for this attack: 2950 MB

Dictionary cache hit:
* Filename..: D:\PASSCREATION\allwords\Master_master_MASTER.txt
* Passwords.: 925416
* Bytes.....: 9409539
* Keyspace..: 75375711585000




The wordlist or mask that you are using is too small.    Finished autotune
This means that hashcat cannot use the full parallel power of your device(s).
Unless you supply more work, your cracking speed will drop.
For tips on supplying more work, see: https://hashcat.net/faq/morework

Approaching final keyspace - workload adjusted.

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

Session..........: hashcat
Status...........: Running
Hash.Mode........: 0 (MD5)
Hash.Target......: md5_2508.hash
Time.Started.....: Thu Sep 14 12:55:47 2023 (2 secs)
Time.Estimated...: Thu Sep 14 13:07:15 2023 (11 mins, 26 secs)
Kernel.Feature...: Optimized Kernel
Guess.Base.......: Mask (?a?a?a?a) [4], Left Side
Guess.Mod........: File (D:\Master_master_MASTER.txt), Right Side
Guess.Charset....: -1 ?d?s, -2 ?l?u, -3 Undefined, -4 Undefined
Speed.#1.........: 54562.8 MH/s (7.65ms) @ Accel:32 Loops:1024 Thr:1024 Vec:1
Speed.#2.........: 54986.5 MH/s (7.57ms) @ Accel:32 Loops:1024 Thr:1024 Vec:1
Speed.#*.........:  109.6 GH/s
Recovered........: 7/38 (18.42%) Digests (total), 0/38 (0.00%) Digests (new)
Progress.........: 176258433024/75375711585000 (0.23%)
Rejected.........: 0/176258433024 (0.00%)
Restore.Point....: 0/925416 (0.00%)
Restore.Sub.#1...: Salt:0 Amplifier:189440-190464 Iteration:0-1024
Restore.Sub.#2...: Salt:0 Amplifier:191488-192512 Iteration:0-1024
Candidate.Engine.: Device Generator
Candidates.#1....: d}  lycras -> %axyZZZS
Candidates.#2....: QPinA -> u7nilycra
Hardware.Mon.#1..: Temp: 63c Fan: 31% Util: 96% Core:2775MHz Mem:10501MHz Bus:8
Hardware.Mon.#2..: Temp: 57c Fan: 31% Util: 95% Core:2715MHz Mem:10251MHz Bus:8

|I understand that time started on the log with 100gh\s speed it only 2 seconds, but believe me, it keeps 100gh\s for full bruteforce time, while when it started like that with 3 times lower speed, it also keeps only 30GH\s speed.

P.s literraly nothing changes between those two work starts! Cuda drivers also ok, GPUs not overheating, and just usuall hashcat restart helps, BUT THAT IS NOT CHNCE WORKING FOR ME, AS IS AM BRUTEFORCING: [b]Wordlist + MASK FOLDER .  I can not restart it evey time, when it happens. And waiting while it is bruteforcing 3 times longer , the wordlist it could actually bruteforce much more easier, is also very disgisting
Please help guys ![/b]

[blaster666]

Btw, this error comes on 100gh\s sucessfull job start also :
The wordlist or mask that you are using is too small. Finished autotune
This means that hashcat cannot use the full parallel power of your device(s).
Unless you supply more work, your cracking speed will drop.
For tips on supplying more work, see: https://hashcat.net/faq/morework

So that means nothing, it should keep 100ghs, not 30