# AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models

Source: [AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models](<https://www.sota2.com/research/paper/69ba31ac0636e5bf4afc09e3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-24T05:00:04.550Z

Authors: Martin Mayr, Sebastian Wind, Lukas Schr\\"oder, Mohammadmoein Moradi, Georg Hager, Harald K\\"ostler, Gerhard Wellein

Published: 2026-03-17T06:32:41.000Z

## Abstract

Artificial Intelligence (AI) workloads drive a rapid expansion of high-performance computing (HPC) infrastructures and increase their power and energy demands towards a critical level. AI benchmarks representing state-of-the-art workloads and their understanding in the context of performance-energy trade-offs are critical to deploy efficient infrastructures and can guide energy efficiency measures, such as power limiting. We introduce a benchmarking framework with popular deep learning applications from computer vision (image classification and generation) and large language models (continued pre-training and inference) implementing modern methods. Our performance analysis focuses on throughput rather than \`\`time to completion'', which is the standard metric in HPC. We analyse performance and energy efficiency under various power-limit settings on NVIDIA H100, NVIDIA H200, and AMD MI300X GPUs. Our results reveal that no universal optimal power limit exists, as the efficiency peak varies across application types and GPU architectures. Interestingly, the two NVIDIA GPUs which mainly differ in their high-bandwidth memory (HBM) configuration show qualitatively different performance-energy trade-offs. Code is available on Zenodo (https://zenodo.org/records/20083679) and GitHub (https://github.com/RRZE-HPC/hpc-ai-perf-bench).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.16164>)

[PDF](<https://arxiv.org/pdf/2603.16164.pdf>)
