Intel® Integrated Performance Primitives (Intel® IPP) Release Notes

Where to Find the Release 

Intel® Integrated Performance Primitives (Intel® IPP)  

Intel® IPP 2022.2.0

System Requirements

What's New 

• Optimized signal domain Phase functionality (ippsPhase API) with16-bit integer data types, which was accelerated for Intel® AVX2 and Intel® AVX512 hardware, allowing to accelerate image and signal processing pipelines.
• Introduced Intel® IPP optimization patch for GraphicsMagic version 1.3.38
• Optimized image processing domain warp perspective transformation functionality (ippiWarpPerspective API) with 32-bit floating point data and nearest interpolation

Bug fixes

• Fixed ipprResize bug in 3D resizing

Known Issues and Limitations

• The custom dispatcher example is unable to work with Intel® SSSE3 and Intel® Advanced Vector Extensions (Intel® AVX) targets, due to the elimination of specific hardware path in Intel® IPP

Deprecation Notices

• ippGetNumThreads and ippSetNumThreads are deprecated and will be removed in some future product release

Intel® IPP 2022.1.0

System Requirements

What's New 

• Added new inplace API for MulC functionality for images
• Optimized half-precision floating point(fp16) Discrete Fourier Transform (DFT) and Inverse Discrete Fourier Transform (IDFT) for the length of 1728, 1800, 2304, 2592, 2880 and 3072
• Improved the performance on Intel® Advanced Vector Extensions 512 (Intel® AVX512) processor systems for the APIs: ippiHog, ippiSet, ippsMagnitude_16sc32f, ippsAutoCorrNorm_64f, ippiConvert_32f8u/16s8u/16u8u

Bug fixes

• ippiFilterBilateral_8u (all mods) is fixed and works for L2 norm (ippDistNormL2) parameter instead of zero output.
• Fixed a correct suffix in "IPPConfig.cmake" file for Linux system
• Fixed a regression in norm functionality in OpenCV
• Added the description for ippsFIRMR32f_32fc function in documet FIRMR

Deprecation Notices

• Optimizations for architecture n8 (Intel® SSSE3) and e9 Intel® Advanced Vector Extensions (Intel® AVX)  code path are deprecated, Intel® SSE is instead.

Intel® IPP 2022.0.0

System Requirements

What's New 

• Extended optimizations in image colorspace conversion using Intel® Advanced Vector Extensions - Vector Neural Network Instruction (Intel® AVX-VNNI) for functions ippiRGBToYUV_8u_AC4R, ippiYUVToRGB_8u_AC4R, ippiRGBToYUV_8u_C3R, ippiRGBToYCbCr_8u_AC4R, ippiRGBToYCbCr_8u_C3R. Also new general optimizations for functions ippiYCbCr422_8u_P3C2R, ippiYCCToRGB_8u_AC4R, ippiRGBToYCC_8u_AC4R, ippiRGBToYCC_8u_C3R, ippiYCCToRGB_8u_C3R, ippiXYZToRGB_8u_AC4R, ippiXYZToRGB_8u_C3R, ippiRGBToXYZ_16s_C3R, ippiRGBToXYZ_16s_AC4R, ippiXYZToRGB_16u_AC4R, ippiXYZToRGB_16u_C3R, ippiXYZToRGB_16s_AC4R, ippiXYZToRGB_16s_C3R, ippiYCCToRGB_16s_AC4R, ippiYCCToRGB_16s_C3R, ippiRGBToYCC_16u_C3R. 
• Extended optimizations in signal processing targeting Intel® Xeon® Processors with efficiency cores (E-cores) for functions ippsNorm_L2_16s32f, ippsNorm_L2_16s32s_Sfs, ippsNorm_L2Sqr_16s64s_Sfs. 
• Fixed error in Intel® IPP Signal Processing Windowing function ippsWinKaiser_32f_I. 
• Enabled Intel® Control-flow Enforcement Technology (Intel® CET) 

Known Issues and Limitations 

• CMake config files doesn't work properly with shared libraries (when CMake variable IPP_SHARED is set to ON) on Linux in Intel® IPP 2022.0.0 release. As a temporary workaround, please, replace IPP_MAJOR_VERSION with IPP_INTERFACE_VERSION_MAJOR on the line 205 of the file $IPPROOT/lib/cmake/ipp/IPPConfig.cmake.

• This release of Intel® Integrated Performance Primitives has been built with the new secure and powerful Intel® oneAPI DPC++/C++ Compiler.  As a result, we’ve noted some performance regressions in our testing, which will be addressed in the subsequent releases.  If these regressions are thought to be impacting your application in a negative way or you have specific questions, please contact  Intel® oneAPI Products Support. 

Unsupported or Discontinued Features 

• Intel® IPP 32-bit binaries are dropped in this release  

• Intel® IPP char domain is dropped in this release. 

Release Number Mapping

The table presents the mapping of Intel® Integrated Performance Primitives and Intel® oneAPI Base Toolkit versions. 

Previous Releases

Find Previous Release Here

Technical Support 

If you did not register your Intel® software product during installation, please do so now at the Intel® Software Development Products Registration Center. Registration entitles you to free technical support, product updates and upgrades for the duration of the support term. 

For technical information about Intel® IPP, including FAQ's, tips and tricks, and other support information, please visit the Intel® IPP forum. 

For general information about Intel technical support, product updates, user forums, FAQs, tips and tricks and other support questions, please visit the support site. 

Note: If your distributor provides technical support for this product, please contact them rather than Intel. 

Notices and Disclaimers

Intel technologies may require enabled hardware, software or service activation.

No product or component can be absolutely secure.

Your costs and results may vary.

© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.

No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.

The products described may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata are available on request.

Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.