Profiling and Modeling of Power Characteristics of Leadership-Scale HPC System Workloads
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914663440056320 |
|---|---|
| author | Karimi, Ahmad Maroof Sattar, Naw Safrin Shin, Woong Wang, Feiyi |
| author_facet | Karimi, Ahmad Maroof Sattar, Naw Safrin Shin, Woong Wang, Feiyi |
| contents | In the exascale era in which application behavior has large power & energy footprints, per-application job-level awareness of such impression is crucial in taking steps towards achieving efficiency goals beyond performance, such as energy efficiency, and sustainability.
To achieve these goals, we have developed a novel low-latency job power profiling machine learning pipeline that can group job-level power profiles based on their shapes as they complete. This pipeline leverages a comprehensive feature extraction and clustering pipeline powered by a generative adversarial network (GAN) model to handle the feature-rich time series of job-level power measurements. The output is then used to train a classification model that can predict whether an incoming job power profile is similar to a known group of profiles or is completely new. With extensive evaluations, we demonstrate the effectiveness of each component in our pipeline. Also, we provide a preliminary analysis of the resulting clusters that depict the power profile landscape of the Summit supercomputer from more than 60K jobs sampled from the year 2021. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_00729 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Profiling and Modeling of Power Characteristics of Leadership-Scale HPC System Workloads Karimi, Ahmad Maroof Sattar, Naw Safrin Shin, Woong Wang, Feiyi Distributed, Parallel, and Cluster Computing In the exascale era in which application behavior has large power & energy footprints, per-application job-level awareness of such impression is crucial in taking steps towards achieving efficiency goals beyond performance, such as energy efficiency, and sustainability. To achieve these goals, we have developed a novel low-latency job power profiling machine learning pipeline that can group job-level power profiles based on their shapes as they complete. This pipeline leverages a comprehensive feature extraction and clustering pipeline powered by a generative adversarial network (GAN) model to handle the feature-rich time series of job-level power measurements. The output is then used to train a classification model that can predict whether an incoming job power profile is similar to a known group of profiles or is completely new. With extensive evaluations, we demonstrate the effectiveness of each component in our pipeline. Also, we provide a preliminary analysis of the resulting clusters that depict the power profile landscape of the Summit supercomputer from more than 60K jobs sampled from the year 2021. |
| title | Profiling and Modeling of Power Characteristics of Leadership-Scale HPC System Workloads |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2402.00729 |