Gaia: Hybrid Hardware Acceleration for Serverless AI in the 3D Compute Continuum
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918206577311744 |
|---|---|
| author | Reisecker, Maximilian Marcelino, Cynthia Pusztai, Thomas Nastic, Stefan |
| author_facet | Reisecker, Maximilian Marcelino, Cynthia Pusztai, Thomas Nastic, Stefan |
| contents | Serverless computing offers elastic scaling and pay-per-use execution, making it well-suited for AI workloads. As these workloads run in heterogeneous environments such as the Edge-Cloud-Space 3D Continuum, they often require intensive parallel computation, which GPUs can perform far more efficiently than CPUs. However, current platforms struggle to manage hardware acceleration effectively, as static user-device assignments fail to ensure SLO compliance under varying loads or placements, and one-time dynamic selections often lead to suboptimal or cost-inefficient configurations. To address these issues, we present Gaia, a GPU-as-a-service model and architecture that makes hardware acceleration a platform concern. Gaia combines (i) a lightweight Execution Mode Identifier that inspects function code at deploy time to emit one of four execution modes, and a Dynamic Function Runtime that continuously reevaluates user-defined SLOs to promote or demote between CPU- and GPU backends. Our evaluation shows that it seamlessly selects the best hardware acceleration for the workload, reducing end-to-end latency by up to 95%. These results indicate that Gaia enables SLO-aware, cost-efficient acceleration for serverless AI across heterogeneous environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_13728 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gaia: Hybrid Hardware Acceleration for Serverless AI in the 3D Compute Continuum Reisecker, Maximilian Marcelino, Cynthia Pusztai, Thomas Nastic, Stefan Distributed, Parallel, and Cluster Computing Serverless computing offers elastic scaling and pay-per-use execution, making it well-suited for AI workloads. As these workloads run in heterogeneous environments such as the Edge-Cloud-Space 3D Continuum, they often require intensive parallel computation, which GPUs can perform far more efficiently than CPUs. However, current platforms struggle to manage hardware acceleration effectively, as static user-device assignments fail to ensure SLO compliance under varying loads or placements, and one-time dynamic selections often lead to suboptimal or cost-inefficient configurations. To address these issues, we present Gaia, a GPU-as-a-service model and architecture that makes hardware acceleration a platform concern. Gaia combines (i) a lightweight Execution Mode Identifier that inspects function code at deploy time to emit one of four execution modes, and a Dynamic Function Runtime that continuously reevaluates user-defined SLOs to promote or demote between CPU- and GPU backends. Our evaluation shows that it seamlessly selects the best hardware acceleration for the workload, reducing end-to-end latency by up to 95%. These results indicate that Gaia enables SLO-aware, cost-efficient acceleration for serverless AI across heterogeneous environments. |
| title | Gaia: Hybrid Hardware Acceleration for Serverless AI in the 3D Compute Continuum |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2511.13728 |