Why is Numpy with Ryzen Threadripper so much slower than Xeon?

As of 2021, Intel unfortunately removed the MKL_DEBUG_CPU_TYPE to prevent people on AMD use the workaround presented in the accepted answer. This means that the workaround no longer works, and AMD users have to either switch to OpenBLAS or keep using MKL.

To use the workaround, follow this method:

1. Create a conda environment with conda‘s and NumPy’s MKL=2019.
2. Activate the environment
3. Set MKL_DEBUG_CPU_TYPE = 5

The commands for the above steps:

1. conda create -n my_env -c anaconda python numpy mkl=2019.* blas=*=*mkl
2. conda activate my_env
3. conda env config vars set MKL_DEBUG_CPU_TYPE=5

And thats it!