# HEPScore Suite Enhancements: Power Metrics and GPU Integration

- Institution: CERN
- Taught by: Natalia Diana Szczepanek, Robin Hofsaess
- Year: 2026
- Language: English
- Source: [CERN](https://videos.cern.ch/record/3021022)
- Licence: [CERN](https://copyright.web.cern)
- Who can watch: Teens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

The HEPiX Benchmarking Working Group develops and maintains benchmarking tools to quantify computing resources across the Worldwide LHC Computing Grid (WLCG). Since the adoption of HEPScore23 as the official WLCG benchmark in April 2023, the WG has been actively enhancing the benchmark suite based on community feedback and emerging requirements.

Currently, the WG is advancing two key initiatives.

First, the development of instrumentation modules that capture comprehensive server utilization metrics during HEPScore execution, including CPU load, frequency scaling, I/O patterns, and power consumption. These metrics enable detailed analysis of power efficiency and performance characteristics across different hardware configurations.

Second, the integration of GPU workloads into the benchmark catalog, expanding HEPScore's applicability to heterogeneous computing environments and modern accelerator-based systems.

In this report, we provide an overview of the WG's technical progress, implementation challenges, and preliminary results from these developments.

0:00:00 Slide 1

0:00:08 Slide 2

0:00:25 Slide 3

0:00:48 Slide 4

0:01:11 Slide 5

0:01:53 Slide 6

0:03:03 Slide 7

0:04:13 Slide 8

0:05:44 Slide 9

0:06:50 Slide 10

0:07:38 Slide 11

0:09:28 Slide 12

0:11:40 Slide 13

0:11:50 Slide 14

0:12:31 Slide 15

0:13:05 Slide 16

0:13:57 Slide 17

0:14:31 Slide 18

0:14:59 Slide 19

0:15:24 Slide 20

0:15:55 Slide 21

0:16:29 Slide 22

0:17:04 Slide 23

0:17:35 Slide 24

0:17:47 Slide 25

0:18:28 Slide 26

0:19:30 Slide 27r>

## Lectures

1. [HEPScore Suite Enhancements: Power Metrics and GPU Integration](https://invisiblenetwork.ai/learn/cern/3021022/9b5da12a06b7), 20 min (CERN's player)