Based on LLVM, DPC++ is the language of oneAPI. It provides the features needed to define data parallel functions and to launch them on devices.

oneAPI DPC++ Library (oneDPL) provides functionality specified in the C++ standard, with extensions to support data parallelism and offloading to devices.

oneAPI Deep Neural Network Library (oneDNN) is for deep learning applications. It includes optimized basic building blocks for neural networks.

oneAPI Collective Communications Library (oneCCL) provides an efficient implementation of communication patterns used in deep learning.

Level Zero provides low-level direct-to-metal interfaces tailored to the devices in a oneAPI platform. It provides fine-grain explicit controls needed by higher-level runtime APIs.

oneAPI Data Analytics Library (oneDAL) provides highly optimized algorithmic building blocks for all stages of data analytics: pre-processing, transformation, analysis, modeling, validation, and decision making.

oneAPI Threading Building Blocks (oneTBB) lets you easily write parallel C++ programs that take full advantage of multicore performance, that are scalable, portable, composable.

The oneAPI Video Processing Library (oneVPL) provides a single video processing API for encode, decode, and video processing that works across a wide range of accelerators.

Interface layer for providing runtime or compile-time dispatching to device-specific implementations of oneMKL APIs.

Embree is a collection of high-performance ray tracing kernels.

Open Volume Kernel Library (Open VKL) is a collection of high-performance volume computation kernels.

Open Image Denoise is an open, high-quality, efficient, and easy-to-use denoising library that allows one to significantly reduce rendering times in ray tracing based rendering applications.

OSPRay is a scalable, and portable ray tracing engine for high-performance, high-fidelity visualization.