OneAPI (compute acceleration): Difference between revisions

Revision as of 11:53, 22 March 2021

Revision as of 11:56, 22 March 2021

Line 45:

|}

The [[source code]] of the above libraries are available on GitHub. Note that some libraries are just [[glue code]] between the oneAPI DPC++ interface and some other library. For example, the open-source "oneAPI Math Kernel Library" relies on actual BLAS implementations to work, one of which is the confusingly named, closed-source "Intel oneAPI Math Kernel Library" better known as Inter MKL.<ref>{{cite web |title=oneapi-src/oneMKL |url=https://github.com/oneapi-src/oneMKL |publisher=oneAPI-SRC |date=19 March 2021 |quote=oneMKL interfaces are an open-source implementation of the oneMKL Data Parallel C++ (DPC++) interface according to the oneMKL specification. It works with multiple devices (backends) using device-specific libraries underneath.}}</ref>

The [[source code]] of some of the above libraries are available on GitHub.

== Hardware abstraction layer ==