Metraipolis › archive › dc_dcca53e798ba

FieldRT: Reconfigurable Architecture from Geometric Sensitivity to Streaming Acceleration — arXiv:2611.00476

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00476
License (as archived)
CC0-1.0
Archived
2026-11-03T18:27:53.858Z
SHA-256 of the archived text
214b29791dadf7ac1fcea885a9ea1437b49bd7e2b6a435a5d8158d58d506a59e
Stable URL of this page
https://metraipolis.com/documento/dc_dcca53e798ba

How to cite

FieldRT: Reconfigurable Architecture from Geometric Sensitivity to Streaming Acceleration — arXiv:2611.00476 — arXiv (en), https://arxiv.org/abs/2611.00476 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcca53e798ba (Metraipolis archive dc_dcca53e798ba, sha256 214b29791dadf7ac1fcea885a9ea1437b49bd7e2b6a435a5d8158d58d506a59e)
BibTeX
@misc{dcdcca53e798ba,
  title = {FieldRT: Reconfigurable Architecture from Geometric Sensitivity to Streaming Acceleration — arXiv:2611.00476},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00476},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcca53e798ba; sha256 214b29791dadf7ac1fcea885a9ea1437b49bd7e2b6a435a5d8158d58d506a59e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00476. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Geometric perception on edge must simultaneously achieve two goals that are rarely addressed together: preserve accurate spatial understanding for object localization and operate within stringent latency, memory, energy, and precision constraints. This coupling is particularly evident in oriented bird's-eye-view (BEV) detection, where global context, multi-scale interactions, and geometric fusion affect both prediction quality and hardware dataflow. Conventional deployment flows first compress a model using aggregate quality or complexity proxies and then map the compressed operations to a fixed accelerator interface. This separation risks removing geometric structures that appear redundant under coarse metrics but are critical for precise localization, while leaving hardware-level efficiencies in the retained geometry unexploited. We present FieldRT, an algorithm-hardware co-design methodology that uses a common analysis of geometric sensitivity and data lifetime to derive both the deployment profile and its spatial realization. We deploy FieldRT with Axis-Fusion Network (AFN), a sub-million-parameter oriented-BEV detector, and construct controlled profiles that vary the capacity and organization of its geometric processing. The experiments show that redundancy is task-dependent rather than uniform across metrics. Dense prediction can improve while real instance detection deteriorates; coarse localization may remain stable while strict-IoU precision degrades. Moreover, transformations that are individually safe can become detrimental when combined. FieldRT translates the retained geometric structure into a parameterized streaming architecture that shares field access and storage across spatial operators. The resulting custom-PL primitives achieve production-scale numerical closure on an AMD Kria KV260 and make otherwise infeasible multi-dilation execution realizable.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno).
Categorie arXiv: Hardware Architecture (cs.AR) ; Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2611.00476 — 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 2026-11-03T18:10:37.653Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).