Intel® oneAPI Data Analytics Library 2024.0.0

oneDAL 2024.0

oneDAL is happy to introduce 2024.0 release!

🚨 What's New

New oneDAL functionality:

• Online algorithms support: Covariance
• Structure of arrays (SOA) Tables

🚩 Removals and ABI Compatibility

• Starting with the 2024.0 release, the following functionality is deprecated in oneDAL:
  • Compression functionality
  • DAAL CPP SYCL Interfaces
  • Java* interfaces
• ABI compatibility is broken as part of the 2024.0 release of oneDAL. The library’s major version is incremented to two to enforce the relinking of existing applications.

🔨 Library Engineering

• Compressed sparse rows (CSR) accessor has been changed and moved from detail namespace. The support of USM memory was added into this class.
• Centralized parameters selection library has been introduced in the release.

❌ Deprecation Notice

• The following algorithms in DAAL Interfaces are deprecated and will not be supported starting with 2025.0 release:
  • k-Means
  • Covariance
  • PCA
  • Logistic Regression
  • Linear Regression
  • Random Forest
  • kNN
  • SVM
  • DBSCAN
  • Low-order moments
• ABI compatibility is to be broken as part of the 2025.0 release of oneDAL. The library’s major version is to be incremented to three to enforce the relinking of existing applications

Acknowledgements

Thanks to everyone who helped us make 2024.0 release possible!

@avolkov-intel, @Alexsandruss, @ahuber21, @Alexandr-Solovev, @Vika-F, @razdoburdin, @ethanglaser, @napetrov, @aepanchi, @amgrigoriev, @KulikovNikita, @Pahandrovich, @icfaust, @inteldimitrius, @maria-Petrova, @samir-nasibli, @md-shafiul-alam,
@keeranroth, @amgrigoriev

Intel® oneAPI Data Analytics Library 2023.2.1

The release of Intel® oneAPI Data Analytics Library 2023.2.1 introduces the following changes:

🚨 What's New

• sklearn 1.3 support fixes (1, 2, 3)
• Model builders API update

Intel® oneAPI Data Analytics Library 2023.2.0

The release Intel® oneAPI Data Analytics Library 2023.2.0 introduces the following changes:

❌ Deprecation Notice

• The compression functionality in the Intel® oneDAL library is deprecated. Starting with the 2024.0 release, oneDAL will not support the compression functionality
• The DAAL CPP SYCL Interfaces in the Intel® oneDAL library are deprecated. Starting with the 2024.0 release, oneDAL will not support the DAAL CPP SYCL Interfaces
• The Java* interfaces in the Intel® oneDAL library are marked as deprecated. The future releases of the oneDAL library may no longer include support for these Java* interfaces
• ABI compatibility is to be broken as part of the 2024.0 release of Intel® oneDAL. The library’s major version is to be incremented to two to enforce the relinking of existing applications
• macOS* support is deprecated for oneDAL. The 2023.x releases are the last to provide it

🛠️ Library Engineering

• CSR tables interface has been changed and moved from detail namespace

🚨 What's New

• Introduced new Intel® oneDAL functionality:
  • Distributed KMeans++ algorithm
  • Logistic Loss objective algorithm
• Introduced new functionality for Intel® Extension for Scikit-learn:
  • NaN(missing values) support was added to Model Builders
• Improved performance for the following Intel® Extension for Scikit-learn algorithms:
  • Model Builders performance has been improved up to 2x

Intel® oneAPI Data Analytics Library 2023.1.1

The release Intel® oneAPI Data Analytics Library 2023.1.1 introduces the following changes:

🚨 What's New

• Introduced new oneDAL functionality:
  • oneAPI interfaces for Logistic Loss: 98fc59c
  • Random splitting strategy in Decision Forest algorithm: 5e080cf
• Performance fix for features sampling in Decision Forest algorithm: af225ad

Intel® oneAPI Data Analytics Library 2023.1.0

The release Intel® oneAPI Data Analytics Library 2023.1 introduces the following changes:

📚Support Materials

• Accelerating Barnes-Hut t-SNE Algorithm by Efficient Parallelization on Multi-Core CPUs

🛠️ Library Engineering

• Reduced the size of Intel® oneDAL library by approximately ~30%
• Enabled NuGet distribution channel for Intel® oneDAL on Linux and MacOS

🚨 What's New

• Introduced new Intel® oneDAL functionality:
  • Distributed Linear Regression, kNN, PCA algorithms
• Introduced new functionality for Intel® Extension for Scikit-learn:
  • Enabled PCA, Linear Regression, Random Forest algorithms and SPMD policy as preview
  • Scikit-learn 1.2 support
  • sklearn_is_patched() function added to validate status of algorithms patching
• Improved performance for the following Intel® Extension for Scikit-learn algorithms:
  • t-SNE for “Burnes-Hut” algorithm
  • SVM algorithm for single row inference

❗ Known Issues

• In certain conditions DAAL SYCL interface might hang with L0 backend – please use oneDAL DPC interfaces instead. If older interfaces are required OpenCL backend can be used as workaround.

Intel® oneAPI Data Analytics Library 2023.0.1

The release Intel® oneAPI Data Analytics Library 2023.0.1 introduces the following changes:

🚨 What's New

• Performance improvements for tSNE algorithm: b8fb329
• Fixes in DBSCAN algorithm: f3cbe18
• Fix for dynamic library versions on Linux and macOS: 10caf82

Intel® oneAPI Data Analytics Library 2023.0.0

The release Intel® oneAPI Data Analytics Library 2023.0 introduces the following changes:

🚨 What's New

• Introduced new Intel® oneDAL functionality:
  • DPC++ interface for Linear Regression algorithm

❗ Known Issues

• Intel® Extension for Scikit-learn SVC.fit and KNN.fit do not support GPU
• Most Intel® Extension for Scikit-learn sycl examples fail when using GPU context
• Running the Random Forest algorithm with versions 2021.7.1 and 2023.0 of scikit-learn-intelex on the 2nd Generation Intel® Xeon® Scalable Processors, formerly Cascade Lake may result in an 'Illegal instruction' error.
  • No workaround is currently available for this issue.
  • Recommendation: Use an older version of scikit-learn-intelex until the issue is fixed in a future release.

Intel® oneAPI Data Analytics Library 2021.7.1

The release Intel® oneAPI Data Analytics Library 2021.7.1 introduces the following changes:

📚 Support Materials

• [Tabular Playground Series - Sep 2022] Tuning of ElasticNet hyperparameters
• Accelerated Random Forest for Rent Prediction

🚨 What's New

• zlib and bzip2 methods of compression were deprecated. They are dispatched to the lzo method starting this version
• Optional results (eigenvectors, eigenvalues, variances and means) and precomputed method for PCA algorithm.

Intel® oneAPI Data Analytics Library 2021.6

The release Intel® oneAPI Data Analytics Library 2021.6 introduces the following changes:

📚 Support Materials:

Kaggle kernels for Intel® Extension for Scikit-learn:

• Fast Feature Importance using scikit-learn-intelex
• [Tabular Playground Series - December 2021] Fast Feature Importance with sklearnex
• [Tabular Playground Series - December 2021] SVC with sklearnex 20x speedup
• [Tabular Playground Series - January 2022] Fast PyCaret with Scikit-learn-Intelex
• [Tabular Playground Series - February 2022] KNN with sklearnex 13x speedup
• Fast SVM for Sparse Data from NLP Problem
• Introduction to scikit-learn-intelex
• [Datasets] Fast Feature Importance using sklearnex
• [Tabular Playground Series - March 2022] Fast workflow using scikit-learn-intelex

🛠️ Library Engineering

• Reduced the size of oneDAL python run-time package by approximately 8%
• Added Python 3.10 support for daal4py and Intel(R) Extension for Scikit-learn packages

🚨 What's New

• Improved performance of oneDAL algorithms:
  • Optimized data conversion for tables with column-major layout in host memory to tables with row-major layout in device memory
  • Optimized the computation of Minkowski distances in brute-force kNN on CPU
  • Optimized Covariance algorithm
  • Added DPC++ column-wise atomic reduction
• Introduced new oneDAL functionality:
  • KMeans distributed random dense initialization
  • Distributed PcaCov
  • sendrecv_replace communicator method
• Added new parameters to oneDAL algorithms:
  • Weights in Decision Forest for CPU
  • Cosine and Chebyshev distances for KNN on GPU

Intel® oneAPI Data Analytics Library 2021.5

The release introduces the following changes:

📚 Support Materials

The following additional materials were created:

• oneDAL samples:

  • oneCCL-based distributed K-means, Covariance and DBSCAN samples
  • MPI samples for Basic Statistics and Decision Forest

• Intel® Extension for Scikit-learn samples:

  • Demo samples of the Intel® Extension for Scikit-learn usage with the performance comparison to original Scikit-learn for ElasticNet, K-means, Lasso Regression, Linear regression, and Ridge Regression
  • Demo samples of the Modin usage

• daal4py samples:

  • An example of Catboost converter usage

• Kaggle kernels for Intel® Extension for Scikit-learn:

  • [Tabular Playground Series - Sep 2021] Ridge with sklearn-intelex 2x speedup
  • [Tabular Playground Series - Oct 2021] Fast AutoML with Intel Extension for Scikit-learn
  • [Titanic – Machine Learning from Disaster] AutoML with Intel Extension for Sklearn
  • [Tabular Playground Series - Nov 2021] AutoML with Intel® Extension
  • [Tabular Playground Series - Nov 2021] Log Regression with sklearnex 17x speedup
  • [Tabular Playground Series - Dec 2021] SVC with sklearnex 20x speedup
  • [Tabular Playground Series - Dec 2021] Fast Feature Importance with sklearnex

🛠️ Library Engineering

• Reduced the size of oneDAL library by approximately ~15%.

🚨 What's New

• Introduced new oneDAL functionality:
  • Distributed algorithms for Covariance, DBSCAN, Decision Forest, Low Order Moments
  • oneAPI interfaces for Linear Regression, DBSCAN, KNN
• Improved error handling for distributed algorithms in oneDAL in case of compute nodes failures
• Improved performance for the following oneDAL algorithms:
  • Louvain algorithm
  • KNN and SVM algorithms on GPU
• Introduced new functionality for Intel® Extension for Scikit-learn:
  • Scikit-learn 1.0 support
• Fixed the following issues:
  • Stabilized the results of Linear Regression in oneDAL and Intel® Extension for Scikit-learn
  • Fixed an issue with RPATH on MacOS