Intel® oneAPI Data Analytics Library
Deploy High-Performance Data Science on CPUs and GPUs
Discontinuation Notice
Intel® Developer Cloud for oneAPI will be discontinued effective October 31, 2024. This includes all features and services associated with the platform.
Build High-Performance Data Science and Machine Learning Applications
Intel® oneAPI Data Analytics Library (oneDAL) accelerates big data analysis at all stages of the machine learning pipeline. This open source, cross-platform library provides implementations of classical machine learning algorithms that are optimized for Intel CPUs and GPUs.
Using this library, you can:
- Make better predictions faster.
- Optimize data ingestion and algorithmic compute simultaneously.
- Develop offline, streaming, and distributed use models.
- Split analytics workloads between edge devices and cloud to optimize overall application throughput.
oneDAL optimizes algorithms from popular machine learning Python* libraries such as XGBoost and Intel® Extension for Scikit-learn*, which are part of the end-to-end suite of Intel® AI and machine learning development tools and resources.
Download the Stand-Alone Version
A stand-alone download of oneDAL is available. You can download binaries from Intel or choose your preferred repository.
Help oneDAL Evolve
oneDAL is an implementation of the oneAPI specification, which is part of the Unified Acceleration (UXL) Foundation. We welcome you to participate.
Download as Part of the Toolkit
oneDAL is included as part of the Intel oneAPI Base Toolkit, which is a core set of tools and libraries for developing high-performance, data-centric applications across diverse architectures.
Features
Performance and Portability
- To ensure maximum calculation speed, each function is highly tuned to the instruction set, vector width, core count, and memory architecture of each target CPU or GPU.
- See performance benefits for a wide range of applications—from IoT gateways to back-end servers.
- Work in the language you are most familiar with and get maximum performance in your application with integrated Python, SYCL*, and C++ support.
Algorithm Support
oneDAL includes algorithms for analysis functions, math functions, and training and library prediction functions for C++, including:
- Apriori for Association Rules Mining
- Correlation and Variance-Covariance Matrices
- Decision Forest for Classification and Regression
- Expectation-Maximization Using a Gaussian Mixture Model (EM-GMM)
- Gradient Boosted Trees (GBT) for Classification and Regression
- Alternating Least Squares (ALS) for Collaborative Filtering
- Multinomial Naïve Bayes Classifier
- Multiclass Classification Using a One-Against-One Strategy
- Limited-Memory BFGS (L-BFGS) Optimization Solver
- Logistic Regression with L1 and L2 regularization support
- Linear Regression
- K-Means Clustering
- K-Nearest Neighbor (KNN)
- Support Vector Machines (SVM) with Linear and Radial Basis Function (RBF) Kernels
- Principal Components Analysis (PCA)
- Density-based Special Clustering of Applications with Noise (DBSCAN)
- Random Forest
Benchmarks
This library addresses all stages of the data analytics pipeline: preprocessing, transformation, analysis, modeling, validation, and decision-making.
Documentation & Code Samples
Documentation
Code Samples
Get Started
Intel Extension for Scikit-learn for Python
Learn how to use machine learning algorithms that are available with scikit-learn.
Learn how to train a model and save the information to a file using daal4py—a Python API for oneDAL.
Distributed daal4py CPU Computations
Distributed Linear Regression Training and Prediction
Use this sample to train and predict with a distributed linear regression model.
Distributed K-means Training and Prediction
See how to train and predict with a distributed K-means model.
Master oneAPI C++ and SYCL* Interfaces
Use this set of examples to learn about oneAPI interfaces without SYCL support.
DPC++ (a oneAPI Implementation of SYCL) Examples
Use this set of examples to learn about oneAPI interfaces with SYCL support.
How to work with code samples:
Training
Machine Learning Workflow Optimization
A Quick Walk-through of oneDAL [04:00]
Develop Efficient AI Solutions with Accelerated Machine Learning [02:25:47]
Enhance Data Analytics with oneDAL
Accelerate ML.NET Training with oneDAL
XGBoost Performance
Introduction to XGBoost and Intel Optimizations
AI Tools and XGBoost for Predictive Modeling [02:28:16]
Efficient Data Analysis with scikit-learn
Introduction to Intel Extension for Scikit-learn
Specifications
Processors:
- Intel® Core™ processors
- Intel® Xeon® processors
GPUs:
- Intel® Processor Graphics Gen9 and above
- Iris® graphics
- Intel® Data Center GPUs
- Intel® Arc™ A-series graphics
Operating systems:
- Linux
- Windows
- macOS* (CPU only)
For more information, see the system requirements.
Compilers:
- Intel® oneAPI DPC++/C++ Compiler
- Intel® C++ Compiler
- GNU Compiler Collection (GCC)* on Linux
- Microsoft Visual C++ Compiler* on Windows
- Clang on macOS
Languages:
- SYCL
Note Must have Intel oneAPI Base Toolkit installed
- C++
- Python
Get Help
Your success is our success. Access these support resources when you need assistance.
Stay Up to Date on AI Workload Optimizations
Sign up to receive hand-curated technical articles, tutorials, developer tools, training opportunities, and more to help you accelerate and optimize your end-to-end AI and data science workflows. Take a chance and subscribe. You can change your mind at any time.