oneAPI Data Analytics Library (oneDAL)

oneAPI Data Analytics Library (oneDAL) is a C++ library (powering the Extension for Scikit-learn in Python) which implements accelerated machine learning routines for tabular data (e.g. linear regression, K-means clustering, random forests, etc.) for CPUs, GPUs, and multi-node distributed setups.

It provides highly optimized algorithmic building blocks for all stages of data analytics (preprocessing, transformation, analysis, modeling, validation, and decision making) in batch, online, and distributed processing modes of computation. The library provides two different sets of C++ interfaces: oneAPI and DAAL.

For general information, refer to oneDAL GitHub* repository.

oneAPI vs. DAAL Interfaces

• oneAPI Interfaces are based on open oneDAL specification and are currently under an active development. They work on various hardware but only a limited set of algorithms is available at the moment.

• DAAL Interfaces are CPU-only interfaces that provide implementations for a wide range of algorithms.

Get Started

• Installation
• Quick Start
  • Before You Begin
  • End-to-end Example
  • Build and Run Examples
• oneAPI Examples
  • DPC++
  • C++

Developer Guide

• oneAPI Interfaces
  • Introduction
  • Algorithms Support
    • CPU and GPU Support
    • Build applications with oneDAL
    • Glossary
    • Mathematical Notations
  • Computational Modes
    • Batch
    • Online
    • Distributed
  • Data Management
    • Key concepts
    • Details
  • Algorithms
    • Clustering
    • Covariance
    • Decomposition
    • Ensembles
    • Graph
    • Kernel Functions
    • Logistic Regression
    • Linear Regression
    • Nearest Neighbors (kNN)
    • Objective function
    • Optimizers
    • Newton-CG Optimizer
    • Pairwise Distances
    • Statistics
    • Support Vector Machines
  • Single Program Multiple Data
    • Distributed computation using SPMD model
    • Supported Collective Operations
    • Backend-specific restrictions
  • Appendix
    • Decision Tree
    • k-d Tree
• DAAL Interfaces
  • CPU and GPU Support
  • Library Usage
    • Algorithms
    • Computation Modes
    • Training and Prediction
  • Data Management
  • Analysis
    • K-Means Clustering
    • Density-Based Spatial Clustering of Applications with Noise
    • Correlation and Variance-Covariance Matrices
    • Principal Component Analysis
    • Principal Components Analysis Transform
    • Singular Value Decomposition
    • Association Rules
    • Kernel Functions
    • Expectation-Maximization
    • Cholesky Decomposition
    • QR Decomposition
    • Outlier Detection
    • Distance Matrix
    • Distributions
    • Engines
    • Moments of Low Order
    • Quantile
    • Quality Metrics
    • Sorting
    • Normalization
    • Optimization Solvers
  • Training and Prediction
    • Decision Forest
    • Decision Trees
    • Gradient Boosted Trees
    • Stump
    • Linear and Ridge Regressions
    • LASSO and Elastic Net Regressions
    • k-Nearest Neighbors (kNN) Classifier
    • Implicit Alternating Least Squares
    • Logistic Regression
    • Naïve Bayes Classifier
    • Support Vector Machine Classifier
    • Multi-class Classifier
    • Boosting
    • Training Alternative
  • Services
    • Extracting Version Information
    • Handling Errors
    • Managing Memory
    • Managing the Computational Environment
    • Providing a Callback for the Host Application
  • Examples
• Bibliography
• Deprecation Notice
  • Java* Interfaces
  • Compression Functionality
  • ABI Compatibility
  • macOS* Support

Developer Reference

• C++ API
  • Data Management
    • Array
    • Accessors
    • Data Sources
    • Graphs
    • Graph Service
    • Tables
    • Backend Primitives
  • Algorithms
    • Clustering
    • Covariance
    • Decomposition
    • Ensembles
    • Graph
    • Kernel Functions
    • Logistic Regression
    • Linear Regression
    • Nearest Neighbors (kNN)
    • Optimizers
    • Objective function
    • Pairwise Distances
    • Statistics
    • Support Vector Machines
  • Distributed Model: Single Process Multiple Data
    • Distributed SPMD model
    • Communicators