Intel Iris Xe-LP as a platform for scientific computing

In the present article, we describe the implementation of the finite element numerical integration algorithm for the Intel Iris Xe-LP Graphics Processing Unit. This GPU is a direct successor of a Xeon Phi accelerator architecture. Although it is used in integrated circuits and does not offer substantial performance, its test should be treated as a preview of the estimated performance for the Intel HPG Graphics Cards that are announced to be released in 2022. In the article, we use our previously developed auto-tuning Finite Element numerical integration OpenCL code on the Intel Iris Xe-LP GPU integrated into the Intel i7 11370H CPU and compare the results with the Nvidia GeForce RTX 3060 GPU. This article brings the answer to the question of whether the new Intel architecture can be a direct competitor to the more classic GPU architecture. It also allows showing if the new architecture can be used for the computation of complex engineering tasks.

---

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).