Failing benchmark modes

[kevkss]

Code:

C:\Users\kev\Downloads\hashcat-6.2.3\hashcat-6.2.3>hashcat -m 2500 --benchmark

hashcat (v6.2.3) starting in benchmark mode

Benchmarking uses hand-optimized kernel code by default.
You can use it in your cracking session by setting the -O option.
Note: Using optimized kernel code limits the maximum supported password length.
To disable the optimized kernel code in benchmark mode, use the -w option.

ADL_Overdrive_Caps(): -8

ADL_Overdrive_Caps(): -8

ADL_Overdrive_Caps(): -8

ADL_Overdrive_Caps(): -8

nvmlDeviceGetFanSpeed(): Not Supported

CUDA API (CUDA 11.4)
====================
* Device #1: NVIDIA GeForce GTX 1660 Ti with Max-Q Design, 5163/6144 MB, 24MCU

OpenCL API (OpenCL 3.0 CUDA 11.4.94) - Platform #1 [NVIDIA Corporation]
=======================================================================
* Device #2: NVIDIA GeForce GTX 1660 Ti with Max-Q Design, skipped

OpenCL API (OpenCL 2.1 AMD-APP (2841.19)) - Platform #2 [Advanced Micro Devices, Inc.]
======================================================================================
* Device #3: AMD Radeon(TM) RX Vega 10 Graphics, 7143/7207 MB (4048 MB allocatable), 10MCU

Benchmark relevant options:
===========================
* --optimized-kernel-enable

Hashmode: 2500 - WPA-EAPOL-PBKDF2 (Iterations: 4095)


C:\Users\kev\Downloads\hashcat-6.2.3\hashcat-6.2.3>

Code:

C:\Users\kev\Downloads\hashcat-6.2.3\hashcat-6.2.3>hashcat --benchmark
hashcat (v6.2.3) starting in benchmark mode

Benchmarking uses hand-optimized kernel code by default.
You can use it in your cracking session by setting the -O option.
Note: Using optimized kernel code limits the maximum supported password length.
To disable the optimized kernel code in benchmark mode, use the -w option.

ADL_Overdrive_Caps(): -8

ADL_Overdrive_Caps(): -8

ADL_Overdrive_Caps(): -8

ADL_Overdrive_Caps(): -8

nvmlDeviceGetFanSpeed(): Not Supported

CUDA API (CUDA 11.4)
====================
* Device #1: NVIDIA GeForce GTX 1660 Ti with Max-Q Design, 5163/6144 MB, 24MCU

OpenCL API (OpenCL 3.0 CUDA 11.4.94) - Platform #1 [NVIDIA Corporation]
=======================================================================
* Device #2: NVIDIA GeForce GTX 1660 Ti with Max-Q Design, skipped

OpenCL API (OpenCL 2.1 AMD-APP (2841.19)) - Platform #2 [Advanced Micro Devices, Inc.]
======================================================================================
* Device #3: AMD Radeon(TM) RX Vega 10 Graphics, 7143/7207 MB (4048 MB allocatable), 10MCU

Benchmark relevant options:
===========================
* --optimized-kernel-enable

Hashmode: 0 - MD5

Speed.#1.........: 15934.0 MH/s (49.93ms) @ Accel:32 Loops:1024 Thr:1024 Vec:1
Speed.#3.........:  3595.8 MH/s (92.03ms) @ Accel:1024 Loops:512 Thr:64 Vec:1
Speed.#*.........: 19529.9 MH/s

Hashmode: 100 - SHA1

Speed.#1.........:  5297.6 MH/s (75.24ms) @ Accel:64 Loops:256 Thr:1024 Vec:1
Speed.#3.........:  1374.6 MH/s (59.66ms) @ Accel:128 Loops:1024 Thr:64 Vec:1
Speed.#*.........:  6672.2 MH/s

Hashmode: 1400 - SHA2-256

Speed.#1.........:  2284.6 MH/s (87.64ms) @ Accel:32 Loops:256 Thr:1024 Vec:1
Speed.#3.........:  560.2 MH/s (73.57ms) @ Accel:128 Loops:512 Thr:64 Vec:1
Speed.#*.........:  2844.8 MH/s

Hashmode: 1700 - SHA2-512

Speed.#1.........:  725.9 MH/s (68.54ms) @ Accel:8 Loops:256 Thr:1024 Vec:1
Speed.#3.........:  128.1 MH/s (80.29ms) @ Accel:64 Loops:256 Thr:64 Vec:1
Speed.#*.........:  854.0 MH/s

Hashmode: 22000 - WPA-PBKDF2-PMKID+EAPOL (Iterations: 4095)


C:\Users\kev\Downloads\hashcat-6.2.3\hashcat-6.2.3>

Seems to work for other hash modes. I just recently upgraded Adrenalin,  and Cuda. This problem began after upgrading to Cuda 11.4.

[Snoopy]

You can try to delete all used old kernels in the kernel directory to force hashcat to rebuild them on use

[kevkss]

You can try to delete all used old kernels in the kernel directory to force hashcat to rebuild them on use

I should note that this is in Windows 10. I did a fresh reformat, went straight to the latest drivers and software, and I am still having the same issue.

[kevkss]

Suppose i'll post an update. Still having this same issue with latest OEM drivers. Unsure of fix. Clearing out Kernel directory does not change output. This is with latest beta, and same result with the release versions.

Code:

C:\Users\kevin\Downloads\hashcat-6.2.5+55\hashcat-6.2.5>hashcat.exe -O -b -m 22000
hashcat (v6.2.5-55-gcb7f99ef7) starting in benchmark mode

Benchmarking uses hand-optimized kernel code by default.
You can use it in your cracking session by setting the -O option.
Note: Using optimized kernel code limits the maximum supported password length.
To disable the optimized kernel code in benchmark mode, use the -w option.

ADL2_Overdrive_Caps(): -8

ADL2_Overdrive_Caps(): -8

ADL2_Overdrive_Caps(): -8

ADL2_Overdrive_Caps(): -8

nvmlDeviceGetFanSpeed(): Not Supported

ADL_Overdrive5_FanSpeed_Get(): -100

ADL_Overdrive5_Temperature_Get(): -100

CUDA API (CUDA 11.5)
====================
* Device #1: NVIDIA GeForce GTX 1660 Ti with Max-Q Design, 5163/6143 MB, 24MCU

OpenCL API (OpenCL 3.0 CUDA 11.5.125) - Platform #1 [NVIDIA Corporation]
========================================================================
* Device #2: NVIDIA GeForce GTX 1660 Ti with Max-Q Design, skipped

OpenCL API (OpenCL 2.1 AMD-APP (2841.5)) - Platform #2 [Advanced Micro Devices, Inc.]
=====================================================================================
* Device #3: AMD Radeon(TM) RX Vega 10 Graphics, 3232/6567 MB (2024 MB allocatable), 10MCU

Benchmark relevant options:
===========================
* --optimized-kernel-enable

-------------------------------------------------------------
* Hash-Mode 22000 (WPA-PBKDF2-PMKID+EAPOL) [Iterations: 4095]
-------------------------------------------------------------


C:\Users\kevin\Downloads\hashcat-6.2.5+55\hashcat-6.2.5>