Windows Cuda SDK error fallback on OpenCL
#1
Hi,

Sorry for the noob question, i have the below messages while starting hashcat, this is working, but i belive on openCL, not on cuda sdk, am i mistaken?. I'm on Windows 11 with the last drivers of nvidia, do i need to install a specific driver?
in https://hashcat.net/wiki/doku.php?id=fre...hould_i_do
the recommended driver link just redirect to the hascat portal and i don't see any driver version number

Currently on opencl i'm at 360kH/s on a rar5 hash, should i expect much more on cuda sdk?

Thanks,




hashcat (v7.1.2) starting - session [1]

Kernel ./OpenCL/m13000-optimized.cl:
Optimized kernel requested, but not available or not required
Falling back to pure kernel

Successfully initialized the NVIDIA main driver CUDA runtime library.

Failed to initialize NVIDIA RTC library.

* Device #1: CUDA SDK Toolkit not installed or incorrectly installed.
            CUDA SDK Toolkit required for proper device support and utilization.
            For more information, see: https://hashcat.net/faq/wrongdriver
            Falling back to OpenCL runtime.

If you are using WSL2 you can use CUDA instead of OpenCL.
Users must not install any NVIDIA GPU Linux driver within WSL 2
For all details: https://docs.nvidia.com/cuda/wsl-user-guide/index.html

TLDR; go to https://developer.nvidia.com/cuda-downloads and follow this path:
  Linux -> Architecture -> Distribution -> Version -> deb (local)
Follow the installation Instructions on the website.

Failed to initialize the AMD main driver HIP runtime library. Please install the AMD HIP SDK.

Failed to initialize AMD HIP RTC library. Please install the AMD HIP SDK.

OpenCL API (OpenCL 3.0 CUDA 13.1.117) - Platform #1 [NVIDIA Corporation]
========================================================================
* Device #01: NVIDIA GeForce RTX 5090, 32606/32606 MB (8151 MB allocatable), 170MCU

OpenCL API (OpenCL 2.1 AMD-APP (3628.0)) - Platform #2 [Advanced Micro Devices, Inc.]
=====================================================================================
* Device #02: AMD Radeon(TM) Graphics, skipped

Kernel ./OpenCL/m13000-optimized.cl:
Optimized kernel requested, but not available or not required
Falling back to pure kernel

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: 66

Optimizers applied:
* Zero-Byte
* Single-Hash
* Single-Salt
* Slow-Hash-SIMD-LOOP
Reply


Messages In This Thread
Windows Cuda SDK error fallback on OpenCL - by Dag750 - 01-10-2026, 08:45 PM