hashcat Forum

TBH, I am new to these stuff, so if I made any dumb thing, please point it directly.

After I complete all the prepare works to run the command

Code:
"E:\Program Files\hashcat-6.2.6\hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --increment-max=16

The hashcat just exited without any warn or error like the image above.

Then I run

Code:
"E:\Program Files\hashcat-6.2.6\hashcat.exe" -b -d 1,2

and find this out

Code:
E:\Program Files\hashcat-6.2.6>"E:\Program Files\hashcat-6.2.6\hashcat.exe" -b -d 1,2

hashcat (v6.2.6) 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.

The device #2 specifically listed was skipped because it is an alias of device #1

nvmlDeviceGetFanSpeed(): Not Supported

CUDA API (CUDA 12.9)

====================

* Device #1: NVIDIA GeForce RTX 4080 Laptop GPU, 11047/12281 MB, 58MCU

OpenCL API (OpenCL 3.0 CUDA 12.9.40) - Platform #1 [NVIDIA Corporation]

=======================================================================

* Device #2: NVIDIA GeForce RTX 4080 Laptop GPU, skipped

OpenCL API (OpenCL 3.0 D3D12 Implementation) - Platform #2 [Microsoft]

======================================================================

* Device #3: NVIDIA GeForce RTX 4080 Laptop GPU, skipped

* Device #4: Microsoft Basic Render Driver, skipped

OpenCL API (OpenCL 3.0 WINDOWS) - Platform #3 [Intel(R) Corporation]

====================================================================

* Device #5: 13th Gen Intel(R) Core(TM) i9-13980HX, skipped

Benchmark relevant options:

===========================

* --backend-devices=1,2

* --optimized-kernel-enable

-------------------

* Hash-Mode 0 (MD5)

-------------------

nvrtcCompileProgram(): NVRTC_ERROR_INVALID_OPTION

nvrtc: error: invalid value for --gpu-architecture (-arch)

* Device #1: Kernel ./OpenCL/shared.cl build failed.

* Device #1: Kernel ./OpenCL/shared.cl build failed.

...

* Device #1: Kernel ./OpenCL/shared.cl build failed.

Started: Mon Jun 02 02:01:47 2025

Stopped: Mon Jun 02 02:02:06 2025

What's the problem with my OpenCL or CUDA runtime?
Someone please help me, thanks.

Yeah, it's a really common (and currently unfixable) OpenCL issue. The current only real "fix" is to just do --backend-ignore-opencl

It may be fixed. Please try the latest beta from here:
https://hashcat.net/beta/

Please do let me know if it solves your problem, without having to use --backend-ignore-opencl

(06-01-2025, 11:34 PM)penguinkeeper Wrote: [ -> ]It may be fixed. Please try the latest beta from here:
https://hashcat.net/beta/

Please do let me know if it solves your problem, without having to use --backend-ignore-opencl

Unfortunately, argument --backend-ignore-opencl do not fix any problem of OpenCL compiling, even in the beta version of hashcat.
Instead, it gives me response like this

Code:
C:\Users\melon_444>cd /d "E:\Program Files\beta-hashcat\hashcat-6.2.6"

E:\Program Files\beta-hashcat\hashcat-6.2.6>"hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --increment-max=16

hashcat (v6.2.6-936-g73d817e74+) starting

nvmlDeviceGetFanSpeed(): Not Supported

CUDA API (CUDA 12.9)

====================

* Device #01: NVIDIA GeForce RTX 4080 Laptop GPU, 11047/12281 MB, 58MCU

OpenCL API (OpenCL 3.0 CUDA 12.9.40) - Platform #1 [NVIDIA Corporation]

=======================================================================

* Device #02: NVIDIA GeForce RTX 4080 Laptop GPU, skipped

OpenCL API (OpenCL 3.0 D3D12 Implementation) - Platform #2 [Microsoft]

======================================================================

* Device #03: NVIDIA GeForce RTX 4080 Laptop GPU, 11933/11997 MB (1024 MB allocatable), 1MCU

* Device #04: Microsoft Basic Render Driver, skipped

OpenCL API (OpenCL 3.0 WINDOWS) - Platform #3 [Intel(R) Corporation]

====================================================================

* Device #05: 13th Gen Intel(R) Core(TM) i9-13980HX, 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

Optimizers applied:

* Zero-Byte

* Early-Skip

* Not-Salted

* Not-Iterated

* Single-Hash

* Single-Salt

* Brute-Force

* Raw-Hash

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

nvrtcCompileProgram(): NVRTC_ERROR_INVALID_OPTION

nvrtc: error: invalid value for --gpu-architecture (-arch)

* Device #1: Kernel ./OpenCL/shared.cl build failed.

* Device #1: Kernel ./OpenCL/shared.cl build failed.

Started: Mon Jun 02 18:50:17 2025

Stopped: Mon Jun 02 18:50:21 2025

E:\Program Files\beta-hashcat\hashcat-6.2.6>"hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --incr -Ont-max=16

hashcat (v6.2.6-936-g73d817e74+) starting

nvmlDeviceGetFanSpeed(): Not Supported

CUDA API (CUDA 12.9)

====================

* Device #01: NVIDIA GeForce RTX 4080 Laptop GPU, 11047/12281 MB, 58MCU

OpenCL API (OpenCL 3.0 CUDA 12.9.40) - Platform #1 [NVIDIA Corporation]

=======================================================================

* Device #02: NVIDIA GeForce RTX 4080 Laptop GPU, skipped

OpenCL API (OpenCL 3.0 D3D12 Implementation) - Platform #2 [Microsoft]

======================================================================

* Device #03: NVIDIA GeForce RTX 4080 Laptop GPU, 11933/11997 MB (1024 MB allocatable), 1MCU

* Device #04: Microsoft Basic Render Driver, skipped

OpenCL API (OpenCL 3.0 WINDOWS) - Platform #3 [Intel(R) Corporation]

====================================================================

* Device #05: 13th Gen Intel(R) Core(TM) i9-13980HX, skipped

Minimum password length supported by kernel: 0

Maximum password length supported by kernel: 55

Hashes: 1 digests; 1 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-Hash

* Single-Salt

* Brute-Force

* Raw-Hash

Watchdog: Temperature abort trigger set to 90c

nvrtcCompileProgram(): NVRTC_ERROR_INVALID_OPTION

nvrtc: error: invalid value for --gpu-architecture (-arch)

* Device #1: Kernel ./OpenCL/shared.cl build failed.

* Device #1: Kernel ./OpenCL/shared.cl build failed.

Started: Mon Jun 02 18:50:37 2025

Stopped: Mon Jun 02 18:50:39 2025

E:\Program Files\beta-hashcat\hashcat-6.2.6>"hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --incre --backend-ignore-opencl

hashcat (v6.2.6-936-g73d817e74+) starting

nvmlDeviceGetFanSpeed(): Not Supported

CUDA API (CUDA 12.9)

====================

* Device #01: NVIDIA GeForce RTX 4080 Laptop GPU, 11047/12281 MB, 58MCU

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

Optimizers applied:

* Zero-Byte

* Early-Skip

* Not-Salted

* Not-Iterated

* Single-Hash

* Single-Salt

* Brute-Force

* Raw-Hash

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

nvrtcCompileProgram(): NVRTC_ERROR_INVALID_OPTION

nvrtc: error: invalid value for --gpu-architecture (-arch)

* Device #1: Kernel ./OpenCL/shared.cl build failed.

* Device #1: Kernel ./OpenCL/shared.cl build failed.

Started: Mon Jun 02 18:51:11 2025

Stopped: Mon Jun 02 18:51:15 2025

E:\Program Files\beta-hashcat\hashcat-6.2.6>"hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --increment-max=16  --backend-i -Ore-opencl

hashcat (v6.2.6-936-g73d817e74+) starting

nvmlDeviceGetFanSpeed(): Not Supported

CUDA API (CUDA 12.9)

====================

* Device #01: NVIDIA GeForce RTX 4080 Laptop GPU, 11047/12281 MB, 58MCU

Minimum password length supported by kernel: 0

Maximum password length supported by kernel: 55

Hashes: 1 digests; 1 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-Hash

* Single-Salt

* Brute-Force

* Raw-Hash

Watchdog: Temperature abort trigger set to 90c

nvrtcCompileProgram(): NVRTC_ERROR_INVALID_OPTION

nvrtc: error: invalid value for --gpu-architecture (-arch)

* Device #1: Kernel ./OpenCL/shared.cl build failed.

* Device #1: Kernel ./OpenCL/shared.cl build failed.

Started: Mon Jun 02 18:51:25 2025

Stopped: Mon Jun 02 18:51:27 2025

E:\Program Files\beta-hashcat\hashcat-6.2.6>

(I tried to follow the instruction of hashcat but it's useless)

Because of display glich of windows, I actually typed these commands:

Code:
E:\Program Files\beta-hashcat\hashcat-6.2.6>cd /d "E:\Program Files\beta-hashcat\hashcat-6.2.6"

E:\Program Files\beta-hashcat\hashcat-6.2.6>"hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --increment-max=16

E:\Program Files\beta-hashcat\hashcat-6.2.6>"hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --increment-max=16 -O

E:\Program Files\beta-hashcat\hashcat-6.2.6>"hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --increment-max=16  --backend-ignore-opencl

E:\Program Files\beta-hashcat\hashcat-6.2.6>"hashcat.exe" -m 0 -a 3 hash.txt ?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d?d --increment --increment-min=6 --increment-max=16  --backend-ignore-opencl -O

Is there any problems on the version of CUDA?

Ah! The beta did get further. That error you're seeing is very common, it's just because your driver and CUDA version are mis-matched. Double check and make sure that both are the latest versions and it should be okay. You may have to restart

(06-02-2025, 01:02 PM)penguinkeeper Wrote: [ -> ]Ah! The beta did get further. That error you're seeing is very common, it's just because your driver and CUDA version are mis-matched. Double check and make sure that both are the latest versions and it should be okay. You may have to restart

Thank for your assistant, I figured out that I mis-configured the environment varable, so now it can work correctly Smile

howdy_my_friend

penguinkeeper

penguinkeeper

howdy_my_friend

penguinkeeper

howdy_my_friend