Announcing new open source project Intel® Math Kernel Library for Deep Neural Networks (Intel® MKL-DNN)


Intel® Math Kernel Library for Deep Neural Networks (Intel® MKL-DNN) is now available on the Github ( as an open source performance library for Deep Learning (DL) applications intended for acceleration of DL frameworks on Intel® architecture. Intel® MKL-DNN includes highly vectorized and threaded building blocks to implement convolutional neural networks (CNN) with C and C++ interfaces.

[v3.2 defect] init script always disables openh264


After running v3.2 init script, the openh264 will always be disabled. This is a product defect and will be fixed in next patch release.

There are 3 ways to address this issue temporarily as following,

1. Modify the openh264Enabled flag in Release-v3.2/video_agent/agent.toml after running init script.

2. Set openh264Enabled flag again in Release-v3.2/video_agent/agent.toml if that's changed before running init script.

3. Apply the patch in attachment to replace the init script file at Release-v3.2/video_agent/

Intel® Collaboration Suite for WebRTC v3.2 Release Announcement


I am pleased to announce the release of the Intel® Collaboration Suite for WebRTC Version 3.2.  The release and user documentation are freely available to download from the Intel® Developer Zone site at

The following is a list of the complete features (refer to the Release Notes for details):

a. Added support to obtain real-time network statistics of the conference mode connection in the Client SDK APIs

b. Added Firefox* support in the P2P mode Client SDK for JavaScript

Intel® MKL 11.3.3 patch

There are two listed below limitations with Intel® Math Kernel Library (Intel® MKL) 11.3 Update 3 which were discovered recently. The official fix of these issues will be available the nearest update Intel MKL 11.3.4.

If you require an immediate Intel MKL update to address these issues, please submit a ticket at Intel Premier Support ( for the Intel MKL product.

Known Limitations: 

Intel® SDK for OpenCL™ Applications 2016 R2 for Windows with OpenCL 2.1 and SPIR-V support released



I am glad to announce the availability of Intel® SDK for OpenCL™ Applications 2016 R2 for Windows*. Please visit to download the version for your platform. For details check out Release Notes.


New Features


 OpenCL 2.1 and SPIR-V support

o OpenCL 2.1 development environment with the experimental CPU-only runtime for OpenCL 2.1

login and build issues- Versions 2893 and older no longer supported-


We have stopped supporting Intel XDK versions 2893 and older as of June 13, 2016 as communicated earlier (see the note below). If you are using these older versions please upgrade to the latest version of XDK. Typical signs of having older versions are - not able to login, build not working, and messages like - "check if you are connect to the internet" or "you are not logged in, log in as a valid user" or a spinner goes on for a long time without logging you in.  You need to upgrade to versions 3088 or above, we recommend you upgrade to the latest version.



Subscribe to Intel® Software RSS