Is using CUDA runtime always prefer over OpenCL ??

[Gyfer]

[quote="aikiuslik" pid='58485' dateline='1687726001']
Also you don't have latest hastcat and cuda.

According to the changes.txt file in the Hashcat Documentation in GitHub on GitHub, there doesn't appear to be any improvements or additional benefits in upgrading to version 6.2.6 if my primarily use algorithm is 22000. As a result, there doesn't seem to be a reason or necessity to switch to 6.2.6 if version 6.2.5 is functioning well for me.

Regarding the NVIDIA Cuda documentation, and the NVIDIA Driver Archive for Unix , considering that I have an Nvidia GT 730 graphics card in my PC (for backward compatibility reason), the latest Nvidia driver available for Linux is version 470.xx. For this driver version (470.xx), the latest compatible CUDA version that can be installed is CUDA 11.4. It's worth noting that newer CUDA versions require newer driver versions.

Based on the above, I believe I have the latest "compatible" versions of Hashcat and CUDA for my setup. :-)

Now, I have trouble to get RX580 to compute in Hashcat. I won't be trying ROCm since AMD drop the support in ROCm 4.0,  any pointers to get it run in OpenCL with Ubuntu 20.04 Focal Fossa ?

Over here,  NVIDIA GTX 1060 still goes around ( forex rate : 4.66) USD75 , and RX580 4GB can get around USD 43. 
GTX 1060 have approx. 22000 speed rate of 186kH/s running in CUDA 11.x  (ref )
For RX580, I believe I can get around 220kH/s running in Windows OpenCL. 
Getting two RX580 for less than USD100 and hashrate of above 400++kH/s is not bad, I think. 

AMD driver tried (or trying) :
1. https://github.com/RadeonOpenCompute/ROCm
2. https://github.com/RadeonOpenCompute/ROC...CL-Runtime
1. https://github.com/xuhuisheng/rocm-gfx803
2. https://www.videogames.ai/Install-ROCM-M...ng-AMD-GPU
5. https://github.com/ptitjes/opencl-amd
Even result in cmake build:
1. CMake 3.20-custom
2. OpenCL in Linux

It has been 4 days to get AMD to hash! *meow*