Metraipolis › archive › dc_ff8e956abeed
IMPACT: Constraint-Aware Search for Imperfectly Factorized Accelerator Mappings — arXiv:2610.39040
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39040
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:19:42.950Z
- SHA-256 of the archived text
7a9abbb80615c5b5e41ad07196f2b5be2636e159bd0e064bf61c3a654a3d021b- Stable URL of this page
https://metraipolis.com/documento/dc_ff8e956abeed
How to cite
IMPACT: Constraint-Aware Search for Imperfectly Factorized Accelerator Mappings — arXiv:2610.39040 — arXiv (en), https://arxiv.org/abs/2610.39040 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff8e956abeed (Metraipolis archive dc_ff8e956abeed, sha256 7a9abbb80615c5b5e41ad07196f2b5be2636e159bd0e064bf61c3a654a3d021b)
BibTeX
@misc{dcff8e956abeed,
title = {IMPACT: Constraint-Aware Search for Imperfectly Factorized Accelerator Mappings — arXiv:2610.39040},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39040},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff8e956abeed; sha256 7a9abbb80615c5b5e41ad07196f2b5be2636e159bd0e064bf61c3a654a3d021b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39040. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The efficiency of Deep Neural Network (DNN) accelerators depends on how each tensor operation is mapped onto the hardware. A mapping specifies how the computation is tiled across the memory hierarchy, ordered, and parallelized across the processing elements. These choices form a combinatorially large search space, where efficient mappings are hard to find. Most violate hardware constraints, and most remaining mappings underutilize the hardware. Existing mappers either search only part of this space to keep the search tractable, excluding the most efficient mappings, or sample the full space randomly, so most mappings they evaluate are infeasible. We present IMPACT, a mapper that searches the full space. IMPACT pairs a genetic algorithm with a constraint-aware repair operator that converts each infeasible mapping into a feasible one instead of discarding it. On a flexible accelerator, IMPACT outperforms state-of-the-art mappers in EDP, latency, and energy on every DeepBench workload. On a compute-in-memory (CIM) accelerator, whose constraints leave few mappings feasible, it reduces EDP by 66%, latency by 47%, and energy by 18% over the strongest prior mapper across five networks, and rivals hand-crafted expert mappings. Across flexible and highly constrained accelerators, IMPACT finds efficient mappings automatically. IMPACT will be released as open source. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno). Categorie arXiv: Hardware Architecture (cs.AR). Pagina del lavoro: https://arxiv.org/abs/2610.39040 — 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 2026-10-31T06:08:08.289Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).