Collaboration Encouraged

The oneAPI initiative encourages collaboration on the specification and compatible oneAPI implementations across the ecosystem.

Spec 1.2


Component Releases

Individual components of oneAPI may also release specifications. See Releases for detailed information about all releases.

About the Specification

The specification includes 10 core elements of oneAPI. This includes:

  • DPC++: oneAPI’s core language for programming accelerators and multiprocessors. DPC++ allows developers to reuse code across hardware targets (CPUs and accelerators such as GPUs and FPGAs) and tune for a specific architecture
  • oneDPL: A companion to the DPC++ Compiler for programming oneAPI devices with APIs from C++ standard library, Parallel STL, and extensions
  • oneDNN: High-performance implementations of primitives for deep learning frameworks
  • oneCCL: Communication primitives for scaling deep learning frameworks across multiple devices
  • Level Zero: A system interface for oneAPI languages and libraries
  • oneDAL: Algorithms for accelerated data science
  • oneTBB: A library for adding thread-based parallelism to complex applications on multiprocessors
  • oneVPL: Algorithms for accelerated video processing
  • oneMKL: High-performance math routines for science, engineering, and financial applications

Each element is developed by a core team with feedback from the community. This is described in more detail in our governance doc. The sources for the document are in GitHub, and we also publish a road map. If you want to be involved in the development of the specification, submit a GitHub issue or pull request.

oneAPI 1.2

oneAPI 1.2 was released on November 10, 2022, and is available online.

  • oneAPI Deep Neural Network Library (oneDNN): A graph API has been added to oneDNN, which compiles and executes a deep learning computation graph, identifying opportunities for fusing operators and other target-specific optimizations, working closely with industry partners who develop the major frameworks.READ MORE

oneAPI 1.1

oneAPI 1.1 was released on November 11, 2021, and is available online.

  • Advanced Ray Tracing: Software developers across the industry will have the ability to code for high-fidelity raytraced computations across multiple vendors’ systems and accelerators. The functionality is subdivided into several domains including geometric ray tracing computations, volumetric computation and rendering, image denoising, and scalable rendering and visualization infrastructure.READ MORE
  • oneAPI Video Processing Library: (oneVPL) is a programming interface for video decoding, encoding, and processing to build portable media pipelines on CPU, GPU, and other accelerators. Included in the latest oneVPL release is a preview implementation of Hyper Encode, which provides the ability to split workloads across oneAPI components for media and enabled special encoding mode.READ MORE
  • Level Zero: Level Zero serves as a foundational layer for supporting oneAPI as it provides a direct-to-metal interface to offload accelerator devices. Level Zero 1.1 provides several new extensions as well as spec clarifications.READ MORE

oneAPI Technical Advisory Board

The oneAPI technical advisory boards are an invitation-only forum of industry experts that help guide the oneAPI parallel programming ecosystem and give input to the oneAPI specification.

The general community is invited to join the conversation by reviewing the oneAPI specification, as well as the notes/slides in the GitHub repo, and then post comments or questions as Github issues. Meeting notes and presentations can be found below.

oneAPI Technical Advisory Board

DPC++ & oneDPL

DPC++ is oneAPI’s core language for programming accelerators and multiple processors. oneDPL is a companion to the DPC++ compiler.


High-performance math routines for science, and financial applications


Artificial Intelligence allows machines to work efficiently and solve problems


DPC++ image processing library for xPU

Level Zero

Foundational layer for supporting oneAPI as it provides a direct-to-metal interface to offload accelerator devices