Intel® Integrated Performance Primitives

Watershed Function


I'm trying to work with the Intel IPP Watershed Segmentation function.

I'm not sure what should I send as pMarker image.

I have an Image I want to segment using The Watershed.
I want to get back the segmented image and use the Gradient Norm as reference.

Now I calculate the image gradient norm, send it as source image and pMarker is all zero.

I want to get back segmented image but all I get is an image all zeroed.

UMC libraries for AAC Encoder and support for Constant Bit Rate Mode


I have question regarding the Bit rate Mode for AAC Encoder. I am trying to encode the audio file using UMC::AAC_Encoder and I am looking for a way to encoder it in a Constant Bit Rate mode.Currently, it is encoding in a Variable Bit Rate Mode as default, but I looked around UMC manual and there is no parameter declared in AAC encoder that can control the bit rate mode to constant or variable. So my question is does Intel libraries support Constant Bit Rate mode for AAC encoding ? If it does then how to do it.

IPP 6.1 Crypto Libraries

Our product uses IPP 6.1 and i'm trying to get the matching cryptography libraries for 6.1.6.

They dont appear in the legacy download list at the registrationcenter, only version 7 and 8 appear.

I downloaded the 32bit version for 6.1.4 back in 2010, so I'm sure we did the registration stuff ok.

Any help much appreciated, thanks..

Non existing ipps Random 64f variants as ippsRandGauss_64f

Hi all,

I am currently facing a problem:

ipp 8.2.2 ipps documentation refers that ippsRandGauss_Direct_64f is marked as deprecated, and that the replacement would be ippsRandGauss_64f Nevertheless, the same document only presents up to the 32f variant, and in ipps.h we can not also find the 64f variant. This situation also happens for uniform random.

Does intel have a solution?

Kind regards,


IPP Huffman encoding/decoding functions deprecated, substituation?

I'am wondering why all the Huffman encoding/decoding functions are deprecated. What functions should I use instead, or will Huffman encoding/decoding no longer be supported in future releases of IPP?

Regards Torsten

Spelling mistake in topic, correct is substitution.



Is it still possible to purchase Intel IPP 6.1


My company purchased a software where we have become resposible of development, maintenance and sale. IPP 6.1 was used for developing the SW using C++ under windows.

Correct me if I am wrong, but as per other posts I have concluded the following:

1- IPP is no longer available as a standalone product. This means we have to buy one of the suites. From what I saw, the most cost efficient would be Intel® Parallel Studio XE with a price of around $700

2- With a new license, it is possible to download older product versions.

Effect of disable FTZ mode.

In this link :

The effect describe as this sentence: "This bit doesn't affect correctness of IPP functions, in some rare cases it can affect performance only."


1. Correctness of calculation

When program disables FTZ mode, this mode doesn't affect correctness of IPP functions.
However, is correctness of other functions of Intel affected? (Ex: SIMD)

Filter with single diagonal kernel


 I've been filtering with 8 single width directional kernels.(0, 45, 90,..., 270 and 315 degrees)

 For horizontal and vertical kernels I use FilterRow and FilterColumn.
 But for diagonal directions there's no filter for single width kernel like FilterRow and FilterColumn. 

 So, I've been using kernels like below for diagonal directions.

 0 0 0 0 k4
 0 0 0 k3 0
 0 0 k2 0 0
 0 k1 0 0 0
 k0 0 0 0 0

 Filtering with these kernels is much slower than single row or column filtering.

how can i get ipp example.

I purchased Intel Integrated Native Developer Experience (Intel INDE) Ultimate Edition,and got a setup file(w_inde_2015.2.027.exe).
In the installation directory where the IPP file is very small, only:

do not know where to get IPP sample ?

Iscriversi a Intel® Integrated Performance Primitives