Intel® Integrated Performance Primitives

Intel® IPP integration wrappers, the easy-to-use APIs for Intel IPP functions

Dear Users,

Intel® IPP Introduced the new integration wrappers, which provides the easy-to-use APIs to add Intel® IPP functions into your applications. 

Intel® IPP integration wrappers provides both the C and C++ interfaces:

alternative for IPP 6.1 method ippsNthMaxElement() in IPP 9.0

I am porting my code from IPP 6.1 to IPP 9.0.
I need to calculate nth max value from a 32F image.
As ippsNthMaxElement() from IPP 6.1 is deprecated, I tried writing my own method to get this functionality, but it hampers speed of the code.

Is there any better alternative available in IPP 9.0 OR MKL?
I want to avoid sorting the elements completely, so is there any method that can allow me to partially sort the elements and get the Nth max element ?

The example of FFT in IPP9.0 (2016XE)

hi ,

I want to use FFT on the Xeon Phi ,but the MKL-FFT performance is not good.I want to try IPP ,but I can not find the FFT API in IPP guide .

And the path which the guide mentioned :<install_dir>/ipp/components  not exist .

What is more, I found the oldversion sample for IPP8.0 named ipp-examples/ipp_fft but the compile said these function has been removed .

So please help me to find the FFT example for IPP9.0 ,thank you very much!

Known problems in Intel® Integrated Performance Primitives Cryptography XTS-AES, GFp, and HMAC functions

The following issues were identified in the Intel® Integrated Performance Primitives (Intel® IPP) Cryptography XTS-AES, GFp, and HMAC functions. The problems affect the Intel® IPP 2017 Update 2 and earlier releases.

These issues will be fixed in the future versions of Intel® IPP. If your code is affected, use the following workaround to fix the problem, and improve the code security

  • ОС Android*
  • Linux*
  • Microsoft Windows* 10
  • Microsoft Windows* 8.x
  • Intel® Integrated Performance Primitives
  • Cryptography
  • IPP Cryptography Library
  • Intel IPP & Xeon PHi Coprocessor Multi-threading


    How can I use multi threaded mode for Intel Integrated Performance Primitives 2017 Update 1 on Intel Xeon Phi Coprocessor? I use native mode program (not offload) and I compile project from command line on Windows host with string like this: icl source\block_filter.cpp source\convert.cpp main.cpp -Qmic -parallel -IPP_PARALLEL_DYNAMIC -qopenmp -g -O2 -lscif -ipp -lipps -lippcore -lippvm -o -link -MT . Where are my mistakes, because program don't use many cores?

    Подписаться на Intel® Integrated Performance Primitives