MemPool Flavors: Between Versatility and Specialization in a RISC-V Manycore Cluster
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909566549098496 |
|---|---|
| author | Mazzola, Sergio Zhang, Yichao Bertuletti, Marco Shen, Diyou Benini, Luca |
| author_facet | Mazzola, Sergio Zhang, Yichao Bertuletti, Marco Shen, Diyou Benini, Luca |
| contents | As computational paradigms evolve, applications such as attention-based models, wireless telecommunications, and computer vision impose increasingly challenging requirements on computer architectures: significant memory footprints and computing resources are demanded while maintaining flexibility and programmability at a low power budget. Thanks to their advantageous trade-offs, shared-L1-memory clusters have become a common building block of massively parallel computing architectures tackling these issues. MemPool is an open-source, RISC-V-based manycore cluster scaling up to 1024 processing elements (PEs). MemPool offers a scalable, extensible, and programmable solution to the challenges of shared-L1 clusters, establishing itself as an open-source research platform for architectural variants covering a wide trade-off space between versatility and performance. As a demonstration, this paper compares the three main MemPool flavors, Baseline MemPool, Systolic MemPool, and Vectorial MemPool, detailing their architecture, targets, and achieved trade-offs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03675 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MemPool Flavors: Between Versatility and Specialization in a RISC-V Manycore Cluster Mazzola, Sergio Zhang, Yichao Bertuletti, Marco Shen, Diyou Benini, Luca Hardware Architecture Distributed, Parallel, and Cluster Computing As computational paradigms evolve, applications such as attention-based models, wireless telecommunications, and computer vision impose increasingly challenging requirements on computer architectures: significant memory footprints and computing resources are demanded while maintaining flexibility and programmability at a low power budget. Thanks to their advantageous trade-offs, shared-L1-memory clusters have become a common building block of massively parallel computing architectures tackling these issues. MemPool is an open-source, RISC-V-based manycore cluster scaling up to 1024 processing elements (PEs). MemPool offers a scalable, extensible, and programmable solution to the challenges of shared-L1 clusters, establishing itself as an open-source research platform for architectural variants covering a wide trade-off space between versatility and performance. As a demonstration, this paper compares the three main MemPool flavors, Baseline MemPool, Systolic MemPool, and Vectorial MemPool, detailing their architecture, targets, and achieved trade-offs. |
| title | MemPool Flavors: Between Versatility and Specialization in a RISC-V Manycore Cluster |
| topic | Hardware Architecture Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2504.03675 |