Releases: SChernykh/RandomX_OpenCL
RandomX 1.1.0 optimized code for Vega/Polaris GPUs
Contains portable OpenCL code for all GPUs and optimized code for AMD Vega and Polaris GPUs (Windows only).
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,...
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).
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,...
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,...
RandomX 1.0.4 support for all GPUs on Windows
Contains portable OpenCL code for all GPUs and optimized code for AMD Vega GPUs (Windows only).
Update v1.0.4-3: you can use --dataset_host option to avoid allocating 2 GB dataset in GPU memory, but hashrate will be a bit lower because accessing system memory from GPU is slower.
Update v1.0.4-4: fixed invalid hashes on Vega FE with intensity > 2048
Update v1.0.4-5: fixed invalid hashes on AMD GPUs (portable code)
Update v1.0.4-6: fixed OpenCL compilation error in optimized Vega code
Recommended command line for all GPUs:
RandomX_OpenCL.exe --mine --validate --portable --workers 8 --bfactor 5 --fast_fp [--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, 768 or less for 4 GB GPUs.
Recommended command line for testing AMD Vega:
RandomX_OpenCL.exe --mine --validate [--dataset_host] --intensity 1984
NOTE: 0.01% - 0.012% 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 1984
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,...
RandomX 1.0.4 support for all GPUs on Windows
Contains portable OpenCL code for all GPUs and optimized code for AMD Vega GPUs (Windows only).
Update v1.0.4-3: you can use --dataset_host option to avoid allocating 2 GB dataset in GPU memory, but hashrate will be a bit lower because accessing system memory from GPU is slower.
Update v1.0.4-4: fixed invalid hashes on Vega FE with intensity > 2048
Update v1.0.4-5: fixed invalid hashes on AMD GPUs (portable code)
Recommended command line for all GPUs:
RandomX_OpenCL.exe --mine --validate --portable --workers 8 --bfactor 5 --fast_fp [--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, 768 or less for 4 GB GPUs.
Recommended command line for testing AMD Vega:
RandomX_OpenCL.exe --mine --validate [--dataset_host] --intensity 1984
NOTE: 0.01% - 0.012% 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 1984
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,...
RandomX 1.0.4 support for all GPUs on Windows
Contains portable OpenCL code for all GPUs and optimized code for AMD Vega GPUs (Windows only).
Update v1.0.4-3: you can use --dataset_host option to avoid allocating 2 GB dataset in GPU memory, but hashrate will be a bit lower because accessing system memory from GPU is slower.
Update v1.0.4-4: fixed invalid hashes on Vega FE with intensity > 2048
Recommended command line for all GPUs:
RandomX_OpenCL.exe --mine --validate --portable --workers 8 --bfactor 5 --fast_fp [--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, 768 or less for 4 GB GPUs.
Recommended command line for testing AMD Vega:
RandomX_OpenCL.exe --mine --validate [--dataset_host] --intensity 1984
NOTE: 0.01% - 0.012% 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 1984
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,...
RandomX 1.0.4 support for all GPUs on Windows
Contains portable OpenCL code for all GPUs and optimized code for AMD Vega GPUs (Windows only).
Update: you can use --dataset_host option to avoid allocating 2 GB dataset in GPU memory, but hashrate will be a bit lower because accessing system memory from GPU is slower.
Recommended command line for all GPUs:
RandomX_OpenCL.exe --mine --validate --portable --workers 8 --bfactor 5 --fast_fp [--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, 768 or less for 4 GB GPUs.
Recommended command line for testing AMD Vega:
RandomX_OpenCL.exe --mine --validate [--dataset_host] --intensity 1984
NOTE: 0.01% - 0.012% 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 1984
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,...
RandomX 1.0.4 support for all GPUs on Windows
Contains portable OpenCL code for all GPUs and optimized code for AMD Vega GPUs (Windows only).
Recommended command line for all GPUs:
RandomX_OpenCL.exe --mine --validate --portable --workers 8 --bfactor 5 --fast_fp --intensity N
Choose N depending on available GPU memory: 1984 or less for 8 GB GPUs, 1536 or less for 6 GB GPUs, 768 or less for 4 GB GPUs.
Recommended command line for testing AMD Vega:
RandomX_OpenCL.exe --mine --validate --intensity 1984
NOTE: 0.01% - 0.012% 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 --intensity 1984
or
RandomX_OpenCL.exe --mine --portable --workers 8 --bfactor 5 --fast_fp --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,...
RandomX 1.0.4 support for AMD Vega GPUs on Windows
Works only with AMD Vega GPUs on Windows.
Recommended comand line for testing:
RandomX_OpenCL.exe --mine --validate --intensity 1984
NOTE: 0.01% - 0.012% 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 --intensity 1984
Full RandomX 1.0.3 support for AMD Vega GPUs on Windows
This is the first release for testing/benchmarking. Works only with AMD Vega GPUs on Windows.
Recommended comand line for testing:
RandomX_OpenCL.exe --mine --validate --intensity 1984
NOTE: 0.01% - 0.012% 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 --intensity 1984