# Exploration of state-of-the-art AI-acceleration platforms for HEP use cases

- Institution: CERN
- Speaker: Grace Margaret Rossiter
- Year: 2026
- Language: English
- Subjects: Art, architecture and design
- Source: [CERN](https://videos.cern.ch/record/3026663)
- Licence: [CERN](https://copyright.web.cern)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

**Project Description**:

Exotic AI-accelerator hardware, such as the CEREBRAS Wafer Scale Engine, and the Tenstorrent Blackhole processing board offer compelling alternatives to the standard CPU+GPU offerings for AI training and inference. Within CERN openlab we would like to investigate these solutions and understand which. The student will work to port our existing AI models to one or several of these exotic platforms (depending on hardware availability), documenting the trials and tribulations of the process, and eventually resulting in fair benchmark comparisons between the different hardware approaches. This experience will then help to inform the wider community at CERN of the potential pros and cons of developing for these alternative AI platforms.

**Supervisor**: Thomas Owen James Elias Leutgeb

00:00:00 Slide 1

00:00:14 Slide 2

00:00:29 Slide 3

00:00:52 Slide 4

00:01:03 Slide 5

00:01:15 Slide 6

00:01:29 Slide 7

00:01:40 Slide 8

00:02:11 Slide 9

00:02:26 Slide 10

00:02:46 Slide 11

00:03:03 Slide 12

00:03:23 Slide 13

00:03:38 Slide 14

00:03:48 Slide 15

00:04:09 Slide 16

00:04:21 Slide 17

00:04:33 Slide 18

00:04:49 Slide 19

00:05:18 Slide 20

## Lectures

1. [Exploration of state-of-the-art AI-acceleration platforms for HEP use cases](https://invisiblenetwork.ai/learn/cern/3026663/bd2df8cda339), 6 min (CERN's player)