Collaboration Encouraged

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

Spec 1.3

Spec Elements

This Spec is made of 8 core elements.

DPC++

oneAPI Data
Parallel C++ (SYCL)

oneDPL

oneAPI Data
Parallel C++ Library

oneDNN

oneAPI Deep Neural
Network Library

oneCCL

oneAPI Collective
Communications Library

Level Zero

oneAPI
Level Zero

oneDAL

oneAPI Data
Analytics Library

oneTBB

oneAPI Threading
Building Blocks

oneMKL

oneAPI Math
Kernel Library

Component Releases

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

About the Specification

The specification includes 8 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
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 1.3

oneAPI 1.3 Provisional Specification was released on September 14, 2023, and is available online.

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.

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 Special Interest Groups (SIGs)

The Special Interest Groups are open to anyone and bring together industry experts to help guide the oneAPI specification and open source projects.

Information about these groups is available on the GitHub repository where you can find out when meetings are being held and read the meeting notes and minutes.

Language SIGDPC++ & oneDPL

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

Math SIGoneMKL

High-performance math routines for science, and financial applications

AI SIGOneDNN & OneDAL

Artificial Intelligence allows machines to work efficiently and solve problems

Hardware SIGLevel Zero

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

Image SIGoneIPL

Ready-to-use, highly optimized, image processing Library (under development).