Intel® Integrated Performance Primitives
Production-ready building blocks for cross-platform performance. Develop high-performance vision, signal, security, and storage applications with this multithreaded software library.
Multimedia and Data Processing Performance
Intel® Integrated Performance Primitives (Intel® IPP) is an extensive library of ready-to-use, domain-specific functions that are highly optimized for diverse Intel architectures. Its royalty-free APIs help developers:
- Take advantage of Single Instruction, Multiple Data (SIMD) instructions
- Improve the performance of computation-intensive applications, including signal processing, data compression, image processing, video processing, and computer vision.
- Reduce cost and time to market for software development and maintenance
What's New
Image Processing, Signal Processing, and Data Compression
- Boost your image processing applications with the Intel IPP in-place MulC function, multiplying pixel values by a constant. It now supports image sizes up to 512 megapixels for high-performance, low-memory overhead image scaling.
- Manipulate and align 32-bit floating point images faster on Intel® CPUs with AVX-512, using Warp Perspective functions with Nearest Interpolation, or OpenCV.
- Phase function for 16-bit-integer image/signal data receive a considerable performance boost on AVX2 and AVX512 capable CPUs.
- Optimize your 5G signal processing with the Intel IPP–enhanced Discrete Fourier Transform (DFT), specifically tuned for the critical demands of cellular systems.
- Intel® Control-Flow Enforcement Technology (Intel® CET) protection safeguards your software against control-flow attacks and mitigates exploitation risks. Safeguard your software with cutting-edge hardware-enforced security measures.
Download as Part of the Toolkit
Intel IPP is included as part of the Intel® oneAPI Base Toolkit (Base Kit), which is a core set of tools and libraries for developing high-performance, data-centric applications across diverse architectures.
Download the Stand-Alone Version
A stand-alone download of Intel IPP is available. You can download binaries from Intel or choose your preferred repository.
Features
Optimized for Performance
These software building blocks are highly optimized using Intel® Streaming SIMD Extensions 2, Intel® Advanced Vector Extensions 2 (Intel® AVX2), and Intel® Advanced Vector Extensions 512 (Intel® AVX-512) instruction sets.
Plug In and Go
With these ready-to-use, royalty-free functions, you will:
- Gain more time to develop new application features
- Reduce development, debug, and maintenance time
- Ensure the code you write today will run optimally on future generations of Intel processors
A Comprehensive Set of Primitives
Access thousands of optimized functions covering frequently used fundamental algorithms, including those for creating:
- Digital media
- Enterprise data
- Embedded communications
- Scientific, technical, and security applications
The library includes more than 2,500 primitives for image processing, 1,300 for signal processing, and 500 for computer vision.
Optimize for great CPU performance in current and future Intel platforms. With each instruction set upgrade, a new implementation layer is added. Previous implementations work as before, but functions that can benefit from new hardware capabilities are updated and validated before new architecture is released.
Unlock increased performance that's delivered with new hardware. Start using new CPU capabilities right away instead of interrupting development cycles for additional optimizations. In most cases, the performance boost is automatic. For other cases, you only need to recompile.
For complete information, see the release notes.
Domains and Workloads
Signal Processing
Enable information generation, transformation, and interpretation. Pull meaning from broad sources of data, helping modern communications that include:
- Voice recognition
- Biotechnology
- Wearable technology
- Hearing aids
- Speech synthesis
Optimize commonly used signal-processing functions for a wide variety of Intel architectures, including:
- Discrete Fourier transform (DFT)
- Fast Fourier transforms (FFT)
- Convolution
- Filtering
- Statistics
These signal-processing applications use Intel IPP:
- Telecommunications
- Energy
- Ultrasound machines
- Medical scanning
- Record, enhance, and playback audio and non-audio signals
- Echo cancellation: filter, equalize, and emphasis
- Simulation of environment or acoustics
- Games with sophisticated audio content or effect
- Interfaces for voice-controlled personal assistants
Image Processing
Take visual information and convert it into manageable, usable data for further analysis and decision-making. These image-processing applications use Intel IPP:
- Healthcare (medical imaging)
- Computer vision
- E-commerce (visual search)
- Digital surveillance
- Biometric identification
- Factory machine vision
- Advanced driver assistance systems (ADAS) for autonomous driving
- Printing and printers
- Image recognition and enhancement
- Remote equipment operation
- Gesture recognition
- Illegal image recognition
- Optical correction
Data Compression
Reduce the number of bits needed to store or transmit data. Intel IPP highly optimizes these common compression standards:
- Lempel-Ziv-Storer-Szymanski (LZSS)
- LZ77 (zlib)
- Lempel-Ziv-Oberhumer (LZO)
- Bzip2
- LZ4
- ZFP
Achieve significant performance gains with plug and play functions on applications such as these:
- Internet portal data center
- Data storage centers
- Databases
- Enterprise data management
Benchmarks
These benchmarks illustrate the performance capabilities of Intel IPP.
Documentation
Other Development Environments
Code Samples
Demonstrations of important features in this release are located in [install-dir]/ipp/latest/share/doc/ipp. Refer to the Developer Guide topic Using Intel IPP Examples.
| Sample | Description |
|---|---|
| Multithread Image Resize | Learn how to use the ippiResize functionality in single and multithread modes. Use the parallel_for loop functionality for external multithreading. The multithreading mode works if the project is built with Intel® oneAPI Threading Building Blocks (oneTBB) support. |
| Image Linear Transform (ipp_fft) |
This example shows how to use two image linear transforms:
|
| External Threading Example (ipp_thread) | Learn about threading for an image harmonization filter. Since internal threading is deprecated, it is important to know how to externally thread a generic Intel IPP function. |
Training Resources
Image Processing
Signal Processing
Testimonials
Hisense* Adopts the Base Kit to Develop Its New Ultrasound Imaging Application
The Hisense* new ultrasound imaging platform consists of GPUs and CPUs in its computing architecture for ultrasound desktop and portable devices. They not only migrated key CUDA* kernel functions to SYCL* to run on current and future generations of Intel CPUs using the Intel® DPC++ Compatibility Tool, but also simplified programming for their cross-architecture systems. Using Intel® oneAPI Base Toolkit components including the Intel® oneAPI DPC++/C++ Compiler, Intel IPP, Intel® oneAPI Math Kernel Library (oneMKL), and oneTBB has helped in reducing the total post-processing time in the ultrasonic system for signals and images. Intel® toolkits help them simplify their development efforts and deliver better products to their end users.
Johns Hopkins University School of Medicine
Optimization of processing and analysis of fMRI data as shown will help not only with operational efficiency for clinical fMRI but for large-scale research projects, which would benefit significantly from such speed increases while potentially reducing cloud deployment cost by approximately 25%. These optimizations were achieved by using Intel® C++ Compiler Classic, oneMKL, Intel® Performance Primitives library, and Intel® VTune™ Profiler.
Meituan*
"Intel toolkits helped increase our end-to-end application processing performance on Intel® Xeon® platforms. By using oneAPI technology including Intel IPP, which is a set of high-performance software library combined with hardware deep optimization providing a large number of signal processing, image processing and other functions, we were able to significantly improve our image-processing code performance by 2.7x in image rotation, and 4x in image resize. This allows us to analyze larger image datasets, and builds the cutting-edge visual AI Inference solution for our end customers."
Specifications
Processors:
- Intel® Core™ processors
- Intel® Xeon® processors
- Intel Atom® processors
Languages:
- Built-in support for C and C++
Operating systems:
- Windows
- Linux
Development environments:
- Compatible with compilers from vendors that follow platform standards, such as Microsoft*, GNU Compiler Collection (GCC)*, and Intel
- Can be integrated with Microsoft Visual Studio*
License:
End User License Agreement (EULA)
Note Your installed software development products may use a prior version of the EULA.
Get Help
Your success is our success. Access these support resources when you need assistance.