See the blog announcing the release.

To install conda package, use conda install -c intel mkl-service, or conda install -c conda-forge mkl-service.

To install pypi package, use python -m pip install mkl-service.

Intel(R) Math Kernel Library support functions are subdivided into the following groups according to their purpose:

• Version Information
• Threading Control
• Timing
• Memory Management
• Conditional Numerical Reproducibility Control
• Miscellaneous

A short example, illustrating it use:

import tomopy
import mkl
mkl.domain_set_num_threads(1, domain='fft') # Intel(R) MKL FFT functions to run sequentially