Content deleted Content added
Removed a graphic that was considered promotional. Added additional references. This content describes an open specification and is not vendor specific. It is meant to be descriptive and neutral. |
|||
Line 11:
== The oneAPI Specification ==
The oneAPI specification<ref>{{Cite web|url=https://spec.oneapi.com/oneAPI/|title=The oneAPI Specification|last=|first=|date=|website=oneAPI|url-status=live|archive-url=|archive-date=|access-date=}}</ref> extends existing developer programming models to enable a diverse set of hardware through a data-parallel language, a set of library APIs, and a low-level hardware interface to support cross-architecture programming. It builds upon industry standards and provides an open, cross-platform developer stack.
== The Language – Data Parallel C++ ==
Line 19 ⟶ 17:
== The oneAPI Libraries ==
The set of APIs<ref>{{Cite web|url=https://www.oneapi.com/spec/|title=oneAPI specification elements|last=|first=|date=|website=oneAPI|url-status=live|archive-url=|archive-date=|access-date=}}</ref> spans several domains that benefit from acceleration, including an interface for deep learning; general libraries for linear algebra math, video, and media processing; and others.
{|
!'''Library Name'''
!'''Short'''
Line 26 ⟶ 24:
|-
|oneAPI DPC++ Library
|
|Algorithms and functions to speed DPC++ kernel programming
|-
|oneAPI Math Kernel Library
|
|Math routines including matrix algebra, FFT, and vector math
|-
|oneAPI Data Analytics Library
|
|Machine learning and data analytics functions
|-
|oneAPI Deep Neural Network Library
|
|Neural networks functions for deep learning training and inference
|-
|oneAPI Collective Communications Library
|
|Communication patterns for distributed deep learning
|-
|oneAPI Threading Building Blocks
|
|Threading and memory management template library
|-
|oneAPI Video Processing Library
|
|Real-time video encode, decode, transcode, and processing
|}
Line 66 ⟶ 64:
* [https://www.apress.com/gp/data-parallel-c-advanced-chapters-just-released/17382670 Data Parallel C++: Mastering DPC++ for Programming of Heterogeneous Systems Using C++ and SYCL]
* [https://www.phoronix.com/scan.php?page=news_item&px=Intel-oneAPI-DPC-SYCL-NVIDIA-CU oneAPI / DPC++ / SYCL Will Run Atop NVIDIA GPUs]
*[https://www.codeplay.com/portal/12-16-19-bringing-nvidia-gpu-support-to-sycl-developers Bringing Nvidia GPU support to SYCL developers]
* [https://www.hpcwire.com/2019/11/17/intel-debuts-new-gpu-ponte-vecchio-and-outlines-aspirations-for-oneapi/ Intel Debuts New GPU – Ponte Vecchio – and Outlines Aspirations for oneAPI]
* [https://www.oneapi.com/ oneAPI Industry Specification]
* [https://software.intel.com/en-us/oneapi Intel oneAPI Product]
*[https://www.khronos.org/news/tags/tag/sycl Sycl tagged news]
==References==
| |||