Metraipolis › archive › dc_fc70773cc79b

AccelForge: Comprehensive Modeling and Co-Design Framework for AI Accelerators — arXiv:2609.11906

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11906
License (as archived)
CC0-1.0
Archived
2026-10-16T05:44:57.845Z
SHA-256 of the archived text
44c090251749a9fef142bcfe5f94f4b0e802637d06362027981782ee615a1c96
Stable URL of this page
https://metraipolis.com/documento/dc_fc70773cc79b

How to cite

AccelForge: Comprehensive Modeling and Co-Design Framework for AI Accelerators — arXiv:2609.11906 — arXiv (en), https://arxiv.org/abs/2609.11906 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc70773cc79b (Metraipolis archive dc_fc70773cc79b, sha256 44c090251749a9fef142bcfe5f94f4b0e802637d06362027981782ee615a1c96)
BibTeX
@misc{dcfc70773cc79b,
  title = {AccelForge: Comprehensive Modeling and Co-Design Framework for AI Accelerators — arXiv:2609.11906},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11906},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc70773cc79b; sha256 44c090251749a9fef142bcfe5f94f4b0e802637d06362027981782ee615a1c96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11906. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tensor algebra workloads, of which deep neural networks are prominent examples, are energy-intensive workloads in modern datacenter and edge deployments, making accelerators necessary to achieve energy efficiency and high throughput. To quickly evaluate and iterate on accelerator designs, we need an accelerator modeling framework that captures salient attributes of devices, circuits, architectures, workloads, as well as optimizing the mapping of the workload onto the hardware. In this paper, we introduce AccelForge, which improves upon existing accelerator modeling frameworks in capabilities, speed, and ease-of-use. AccelForge unifies and multiple works into one framework, and it includes (1) composable user-defined and user-modifiable models of devices, circuits, and architectures, (2) fast mappers that enable accurate evaluation in orders of magnitude less (computer and human) time, and (3) easy-to-use and easy-to-extend, yet still high performance, Python implementations of both the model and mapper to enable rapid research and extension to novel optimizations.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AR).
Categorie arXiv: Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2609.11906 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:26:59.343Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).