Edit on wiki

Benchmarks

Run go infinite from start position and abort after depth 26 and report NPS output.

I put some sample ones from memory. Please put your own bench scores here in sorted NPS order if you can. If you don’t know what engine type, gpu is opencl and cpu is openblas

Google docs of bench results here. Easier to maintain/prettier? https://docs.google.com/spreadsheets/d/1lGFf6PLGmBUSMan-YP7Vul4DpRNfn6K8oeCjBILe6uA/edit#gid=0

GPU

GPU @ stock or OC frequencyEngine version/typeNeural Net sizeUsernameSpeed
GTX 1060 @ stock -t 3v7 Linux openCL10x1282650 nps
1080 ti @ 2ghz -t 3v7 Windows openCL10x1282500 nps
GTX 1050 Ti @ stockv7 Windows openCL20x256go infinite2300 nps
GTX 1050 Ti @ stockv7 Windows openCL20x256benchmark1690 nps
GTX 470 @ stock -t 2v7 Windows openCL10x128600 nps

CPU

CPU @ stock or OC frequencyEngine version/typeNeural Net sizeUsernameSpeed
i7-6800K @ 3.6GHz -t 12v7 Linux openblas10x1281010 nps
i7-8700 stock -t 12v7 Windows openblas10x128818 nps
i6700 stock -t 4v7 Windows intel_mkl10x128500 nps
i6700 stock -t 4v7 Windows openblas10x128320 nps
Ryzen 3 1200 stock -t 4v7 Windows openblas10x128300 nps
Last Updated: 2023-08-18