TensorFlow defaults to Intel oneDNN AI optimizations

TensorFlow defaults to Intel oneDNN AI optimizations

Following Google and Intel’s partnership, the open-source TensorFlow has announced that their machine learning library is being updated.

Intel’s open-source oneAPI Deep Neural Network Library (oneDNN) is now enabled by default in Tensor Flow, a Google-led effort. OneDNN is an open-source cross-platform performance collection of deep learning building blocks aimed at deep learning application and framework developers, such as TensorFlow.

According to Intel, oneDNN will provide the organizations with a considerable speed boost of up to 3 times for AI operations using TensorFlow.

Read More: https://venturebeat.com/2022/05/31/tensorflow-now-defaults-to-intel-onednn-ai-optimizations/

Previous articleMicrosoft Unveils New ‘Family’ Of Identity and Access Management Tools
Next articleGitHub Adds More Automation Features to Enterprise Server