Intel® IPP 2018 Update 3 is now available

Intel® IPP 2018 Update 3 is now available

Intel® IPP 2018 Update 3 is now available. Intel(R) IPP 2018 Update 3 release improved LZ4 compression and decompression performance on data with high entropy.

Check Intel® IPP 2018 Update 3 release notes to learn more information.

What's New in Intel® IPP 2018 Update 3:

  • Improved LZ4 compression and decompression performance on data with high entropy.
  • Fixed a number of internal and external defects.

What's New in Intel® IPP 2018 Update 2:

  • Added the new APIs to computes the CRC24 and CRC16 checksum. The APIs support CRC24A, CRC24B, CRC24С and CRC16 polynomial functions, and are included in the Intel® IPP embedded domain within the Intel® System Studio package.
  • Added new APIs in the image processing domain for fixed point Resize functionality. The functionality provides faster resize operations with less accuracy.
  •  Extended optimization for Intel®AVX2 and Intel® AVX-512 instruction set in the following functions


    • Image processing: ippiSeparableFilter, ippiNorm, ipprFilterBorder_L

    • Signal processing: ippsAdd_32u

  • Extended optimization for Intel® SSE4.2 and Intel®AVX2 instruction set for LZ4 data compression functions.
  • Fixed the problem on the incorrect code dispatching for the Intel® AVX512 processor systems running with the OS that does not support AVX-512 instructions. The problem caused some Intel® IPP functions report "illegal instructions” errors

What's New in Intel® IPP 2018 Update 1:

  • Added new Platform-Aware APIs ipprFilterBorder for 3D data filtering, and ipprCopyBorder for 3D border data copying.

  • Extended optimization for Intel® AVX-512 instruction set in the image and signal processing domain.

  • Extended optimization for Intel® SSE4.2 instruction set in image processing and signal processing domain

What's New in Intel® IPP 2018:

  • Added new functions to support the LZ4 data compression and decompression.This release also introduces the patch files for LZ4 source to provide drop-in optimization with the Intel® IPP functions.

  • Introduced the standalone cryptography packages. The cryptography functions no longer depend on the main Intel® IPP packages, and can be used without the main Intel® IPP packages.

  • Introduced the optimization code for the GraphicsMagick source.The code can provide drop-in optimization on GraphicsMagick with the Intel® IPP functions:

    • The code supports GraphicsMagick version 1.3.25, and provides optimization for the following GraphicsMagick APIs: ResizeImage, ScaleImage, GaussianBlurImage, FlipImage, and FlopImage.

    • The optimization code can improve the APIs performance by up to 4x, depending on the functionality, input parameters, and processors.

  • Made the Integration Wrappers APIs part of the Intel® IPP packages.

  • Computer Vision:

    • Added the 64-bit data length support to Canny edge detection functions (ippiCanny_32f8u_C1R_L).

  • Color Conversion:

    • Added the ippiDemosaicVNG functions that support the demosaicing algorithm with VNG interpolation.

  • Cryptography

    • Added the Elliptic Curves key generation and Elliptic Curves based Diffie-Hellman shared secret functionality.

    • Added the Elliptic Curves sign generation and verification functionalities for the DSA, NR, and SM2 algorithms.

  • Performance

    • Extended optimization for the Intel® Advanced Vector Extensions 512 (Intel® AVX-512) and Intel® Advanced Vector Extensions 2 (Intel® AVX2) instruction sets.

    • Improved performance of LZO data compression functions on Intel® AVX2 and Intel® Streaming SIMD Extensions 4.2 (Intel® SSE4.2).

  • Other Changes:

    • Removed support for Intel® Pentium® III processor. The minimal supported instruction set is Intel® Streaming SIMD Extensions 2 (Intel® SSE2).

    • Removed support for the Intel® Xeon Phi™ x100 product family coprocessor (formerly code name Knights Corner) in this release: The Intel® Xeon Phi™ x100 product family coprocessor (formerly code named Knights Corner) was officially announced end of life in January 2017.  As part of the end of life process, the support for this family will only be available in the Intel® Parallel Studio XE 2017 version.  Intel® Parallel Studio XE 2017 will be supported for a period of 3 years ending in January 2020 for the Intel® Xeon Phi™ x100 product family.  Support will be provided for those customers with active support.

  • Threading Notes: To support the internal threading in the Intel® IPP functions, Intel® IPP provides the Threading Layer APIs in the platform-aware functions.  These APIs can support both 64-bit object sizes (for large size images and signal data) and internal threading in Intel® IPP functions.  Check the “Threading Layer Functions” pat in the Intel® IPP Developer Reference to get more information on these APIs. Your feedback on extending the new threading functions is welcome. The legacy Intel IPP threaded libraries are available by the custom installation, and the code written with these libraries will still work as before. However, the threaded library will not expand its threading functions, and the new threading will be developed only in the new Intel® IPP threading layer APIs.  User’s application is recommended to use the new Intel® IPP threading layer APIs or implement the external threading in their applications.

Intel® IPP packages are as part of Intel® Parallel Studio XEIntel® System Studio, and a free community licenses version:

  • Intel fully supported suites: Intel IPP is part of a suite of Intel Software Development Products which are available worldwide for purchase.  These products are backed by Intel, include Intel® Premier Support (which includes private direct support from Intel and support for past versions). Learn more at Intel® Parallel Studio XE, or Intel® System Studio  
  • Community Licenses for Intel Performance Libraries: Community licensing for Intel performance libraries comes with no access to Intel Premier Support, but (like the regular products) has no royalties, and no restrictions based on company or project size. Learn how to register for Community Licenses at
12 posts / 0 new
Last post
For more complete information about compiler optimizations, see our Optimization Notice.

We need many guides and examples of how utilize the function in Multi Threaded scenarios.

P. S.
The forum Cookies life span is really short (If you don't visit for 3 days you need to login again).
Could you please extend that to a month or something?
There is no reason for this short life span of the cookie.
The data isn't that sensitive.

It seems 2018 Update 1 is released.

Could you reconsider and bring back the Matrix Library (Optimized for small matrices)?
It was one of the most useful features of IPP.

Thank You.


Have you got chance to check Intel MKL libraries,  which is focusing on mathematical computation?  Matrix functions are now provided in that libraries now.  In the recent MKL releases, it also improves the performance on small matrix computation (for example, by direct_call APIs).



I haven't checked MKL specifically.
We would be happy to integrate only one library (Even one is too much trouble).

I really think a library optimized for small matrices should be included in IPP.
Even you won't optimize it to AVX 512 (Which is by itself not showing any improvement on CPU's).

By the way, does the DFT and FFT functions in IPP are still multi threaded?

Hi Royi,

It depends on domain: in ipps they are threaded only for cpus that have 2 cores on die (not more!) and shared cache. In ippi - 2d FFT is threaded for images > 256x256.

regards, Igor


it seems that IPP 2018 Update 3 (Windows) is not available in download area.





I cannot download 2018 Update 3.

Click "w_ipp_2018.3.210_online.exe" to download on page, occur page not found.

w_ipp_2018.3.210.exe file is too.

Please check.


Steffen, Han,
I checked here, and did not see the problem. I will send you an URL to see it works for you?


Wow.. Download completed.

Thank you.


Leave a Comment

Please sign in to add a comment. Not a member? Join today