RandomX 1.0.4 optimized code for Vega/Polaris GPUs

Contains portable OpenCL code for all GPUs and optimized code for AMD Vega and Polaris GPUs (Windows only).

Code for Polaris GPUs works only on Baffin GPUs with newer drivers (19.4.1, 19.5.2, 19.7.5 were tested). Fixed version for older drivers and Ellesmere/Lexa GPUs will be released soon.

Recommended command line for testing AMD Vega and Polaris GPUs:

RandomX_OpenCL.exe --mine --validate [--dataset_host] --intensity N

Recommended command line for all other GPUs:

RandomX_OpenCL.exe --mine --validate --portable --workers 8 --bfactor 5 [--dataset_host] --intensity N

Choose N depending on available GPU memory: 1984 or less for 8 GB GPUs, 1536 or less for 6 GB GPUs, 896 or less for 4 GB and 2 GB GPUs. You must add --dataset_host for 2 GB GPUs!

NOTE: 0.01% - 0.02% of failed hashes is normal and expected. The code for FDIV/FSQRT doesn't always produce correct results, but it's much faster than "always correct" version.

To test power usage properly, turn off CPU validation:

RandomX_OpenCL.exe --mine [--dataset_host] --intensity N
or
RandomX_OpenCL.exe --mine --portable --workers 8 --bfactor 5 --fast_fp [--dataset_host] --intensity N

The benchmark tests only 1 GPU at a time. If you have more than 1 GPU, you can select GPU to test by adding --device_id N to the command line where N=0,1,2,...