Achieve Fast CPU Inference with New Optimization Features

If you’re running deep learning inference on CPUs that support low-precision math, balancing model accuracy with energy-efficient performance is important for accelerating inference while reducing memory bandwidth and improving operations per cycle..

In this webinar, Intel Senior Software Engineer Andrey Malyshev will show you how to achieve these benefits using the latest release of the Intel® Distribution of OpenVINO™ toolkit. Topics covered include:

  • Introduction to a post-training quantization process with support for INT8 model inference on Intel® processors
  • Best practices for leveraging model precision to improve inference throughput
  • Parallelization techniques to boost CPU performance in multicore systems

Get the software
Be sure to download the latest release of Intel Distribution of OpenVINO. It’s free.

Additional resources

OpenVINO is a trademark of Intel Corporation or its subsidiaries in the U.S. and/or other countries.

Andrey Malyshev, Senior Software Engineer, Intel Corporation

Andrey Malyshev a senior software engineer and an architect of the Intel® OpenVINO™ toolkit Inference Engine. He is responsible for designing ease-of-use solutions for inference on the diverse array of Intel hardware platforms—a focus that suits him well given his 20 years’ experience plus an interest in deep learning post-training and model optimization. Prior to Inference Engine development, Andrey developed binary analysis tools for profiling memory usage and threading application behavior, helping customers address and correct performance issues.

Andrey has been with Intel since 2000 and holds a Master’s in Mathematics from Nizhny Novgorod State University.

Performance varies by use, configuration, and other factors. Learn more at