Communication Characterization of AI Workloads for Large-scale Multi-chiplet Accelerators
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_ | 1866916608653393920 |
|---|---|
| author | Musavi, Mariam Irabor, Emmanuel Das, Abhijit Alarcon, Eduard Abadal, Sergi |
| author_facet | Musavi, Mariam Irabor, Emmanuel Das, Abhijit Alarcon, Eduard Abadal, Sergi |
| contents | Next-generation artificial intelligence (AI) workloads are posing challenges of scalability and robustness in terms of execution time due to their intrinsic evolving data-intensive characteristics. In this paper, we aim to analyse the potential bottlenecks caused due to data movement characteristics of AI workloads on scale-out accelerator architectures composed of multiple chiplets. Our methodology captures the unicast and multicast communication traffic of a set of AI workloads and assesses aspects such as the time spent in such communications and the amount of multicast messages as a function of the number of employed chiplets. Our studies reveal that some AI workloads are potentially vulnerable to the dominant effects of communication, especially multicast traffic, which can become a performance bottleneck and limit their scalability. Workload profiling insights suggest to architect a flexible interconnect solution at chiplet level in order to improve the performance, efficiency and scalability of next-generation AI accelerators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22262 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Communication Characterization of AI Workloads for Large-scale Multi-chiplet Accelerators Musavi, Mariam Irabor, Emmanuel Das, Abhijit Alarcon, Eduard Abadal, Sergi Hardware Architecture Next-generation artificial intelligence (AI) workloads are posing challenges of scalability and robustness in terms of execution time due to their intrinsic evolving data-intensive characteristics. In this paper, we aim to analyse the potential bottlenecks caused due to data movement characteristics of AI workloads on scale-out accelerator architectures composed of multiple chiplets. Our methodology captures the unicast and multicast communication traffic of a set of AI workloads and assesses aspects such as the time spent in such communications and the amount of multicast messages as a function of the number of employed chiplets. Our studies reveal that some AI workloads are potentially vulnerable to the dominant effects of communication, especially multicast traffic, which can become a performance bottleneck and limit their scalability. Workload profiling insights suggest to architect a flexible interconnect solution at chiplet level in order to improve the performance, efficiency and scalability of next-generation AI accelerators. |
| title | Communication Characterization of AI Workloads for Large-scale Multi-chiplet Accelerators |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2410.22262 |