OneAPI (compute acceleration): Difference between revisions

Revision as of 06:40, 6 December 2019

Revision as of 22:21, 6 December 2019

Line 50:

oneAPI Level Zero, the low-level hardware interface, defines a set of capabilities and services that a hardware accelerator needs to interface with the broad set of languages in support of consumer to Deep/Machine Learning and HPC class solutions.

== Implementations ==

== Intel Reference Implementation ==

Intel has released a oneAPI Beta Product<ref>{{Cite web|url=https://software.intel.com/en-us/oneapi|title=Intel oneAPI Product|last=|first=|date=|website=Intel oneAPI Toolkits|url-status=live|archive-url=|archive-date=|access-date=}}</ref> that serves as a reference implementation ofimplements the specification and adds migration, analysis, and debug tools.

COdeplay is working on a to-be-open-source layer<ref>{{Cite web|url=https://www.phoronix.com/scan.php?page=news_item&px=Intel-oneAPI-DPC-SYCL-NVIDIA-CU|title=Intel's oneAPI / DPC++ / SYCL Will Run Atop NVIDIA GPUs With Open-Source Layer - Phoronix|website=www.phoronix.com|access-date=2019-12-06}}</ref> to allow oneAPI and SYCL / Data Parallel C++ to run atop NVIDIA GPUs via CUDA.

== External links ==