Intel® Integrated Performance Primitives

Your Feedback Matters

Thank you for using Intel® software development tools. We are committed to making the best possible software and platforms to meet your development needs. Your personal experience with our products is extremely valuable to us and we want to know how we can do better.

Announcing Intel IPP 2017 release

Intel® IPP 2017 is now available. This release added new Platform-Aware APIs to support 64-bit parameters for image dimensions and vector length, significantly improved performance of zlib compression functions, and extended optimization for different platforms.

What's New in Intel® IPP 2017:

  • Added Intel® IPP Platform-Aware APIs to support 64-bit parameters for image dimensions and vector length on 64-bit platforms and 64-bit operating systems:

Missing ippm and ipp_z libraries in v2017

I just installed IPP 2017 and it seems to be missing a few libraries we're using from v7.0.25 (yeah, it's a big jump). 

From vector math, I'm missing what was and .a, and from data-compression I'm missing what was and .a. Actually, I'm missing the entire interfaces/data-compression directory. To check to make sure it wasn't my install that's broken, I unpacked all of the rpm files, and I don't see these libs anywhere. I'm aware that the _l and _t suffixes were dropped, but these libraries are just straight up missing. What gives?


Compare the quaility of image result of ippiResizeCenter and ippiSqrResizePixel

Hi every one,

I am writing project in IPP 7.0. I need to resize and shift image. I found two functions that can respond my requirement, they are:

- ippiResizeCenter function

- ippiResizeSqrPixel function

After trying to use these functions, the output result between these two functions are different.

I wonder, which function can give the better quality for resizing image ? Which function should I use to resize and shift image ?

And I also would like to know the reason for selecting

Hope you can help me answer these questions. 

substitute for ippiResizeSqrPixel ippiResizeGetBufSize

My project is using the ippiResizeSqrPixel_16u_C1R to resize image with IPPI_INTER_CUBIC mode, and using ippiResizeGetBufSize to initialize the buffer in advance.

But unfortunately ipp9.0 doesn't support both apis, and the "Substitution or Workaround" for both are N/A.

Could you give me a work around solution?

Thanks and regards,

Yang Qi Xin

IPP 9.0 - ippiWarpAffineLinear - Aligned Vs non-Aligned inputs


I have an implementation for Image Warp using the ippiWarpAffineLinear and related set up functions. The implementation works great and gives the right results.
But, I get a difference in results between when-

  1.  input is aligned to 64.
  2.  unaligned input.

This is *not* seen with the ippiWarpAffineNearest symbol.
I have attached the warped image and the diff'ed warped image between aligned and unaligned input.

Here are the questions that I have-

IPP 9.0 : image rotation - different results AVX2 Vs SSE4


I have a implementation of image rotation in IPP 9.0 using ippiWarpAffineNearest symbol. This implementation works great except for the following case where the results on AVX2 and SSE4 machines do not match-

Image Size - Multiples of 256

Rotation angle  - 45, 135 degrees

Data Type - uint8

Destination image size = Source image size

Image resizing

I am new to C++. I am using Intel's IPP for resizing an image in VS2015. I am trying to use ippiResizeLanczos_8u_C3R function to resize the image.

I do not know how to see/view the resized image or get the pixel values of the resized image(image after applying the above mentioned function), as I intend to use the resized image for further processing. The function perhaps returns only the "IppStatus". But I want to get the resized image or the data information(pixel values) of the resized image as return value.

Any help in this regard would be highly appreciated?

Min / Max Filters vs. Erosion / Dlation Filters

I'm using Intel IPP 8 (On the latest 2015 Edition of Composer).

Intel IPP offers Min / Max Filters and Erode / Dilate Filters.
One could use Erode (With all 1 Mask) for Min and Dilate (With all 1 Mask) for Max.

Yet, what I'm curious about is how come Min / Max aren't faster than Erode / Dilate?
Since they are "Private" cases I would assume they can be much farther be optimized.

Could anyone comment on that?
Does any of them benefit from using the Multi Threaded library?

Thank You.

Web download of IPP libraries keeps getting interrupted


I am trying to narrow down an annoying problem related to download of IPP libraries.

I am trying to download the IPP for Windows (community edition) library installer over the web. However, the download keeps getting interrupted every 30 seconds and the download rate keeps going to zero. It starts after sometime and continues for a while, but then stops again. This continues for quite some time until the download fully stops before completing.

Подписаться на Intel® Integrated Performance Primitives