Metraipolis › archive › dc_094239a72096
SMART-AIMC: Sensitivity-Aware Mixed ADC Resolution with Fine-Grained Tunability for Analog In-Memory Computing — arXiv:2611.01707
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01707
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:57:20.754Z
- SHA-256 of the archived text
25c43aa62ab29c19434e87d017be124ab0214522c650288e25c8f9a9db5a41d4- Stable URL of this page
https://metraipolis.com/documento/dc_094239a72096
How to cite
SMART-AIMC: Sensitivity-Aware Mixed ADC Resolution with Fine-Grained Tunability for Analog In-Memory Computing — arXiv:2611.01707 — arXiv (en), https://arxiv.org/abs/2611.01707 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_094239a72096 (Metraipolis archive dc_094239a72096, sha256 25c43aa62ab29c19434e87d017be124ab0214522c650288e25c8f9a9db5a41d4)
BibTeX
@misc{dc094239a72096,
title = {SMART-AIMC: Sensitivity-Aware Mixed ADC Resolution with Fine-Grained Tunability for Analog In-Memory Computing — arXiv:2611.01707},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01707},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_094239a72096; sha256 25c43aa62ab29c19434e87d017be124ab0214522c650288e25c8f9a9db5a41d4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01707. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Analog In-Memory Computing (IMC) is a promising paradigm for accelerating GEMM-based AI workloads by executing computations directly within the memory array in the analog domain. While IMC delivers substantial energy and throughput improvements, it can suffer from significant task accuracy degradation due to analog-to-digital converter (ADC) quantization noise, which occurs at the GEMM output and is thus different from weight/activation quantization, which occurs at the GEMM input. Mixed ADC resolution allows IMC modules to choose between high- and low-resolution ADC modes with different energy costs, offering a compelling accuracy-energy trade-off. However, selecting ADC resolutions across IMC units while respecting hardware granularity constraints remains challenging. In this paper, we propose SMART-AIMC, a Sensitivity-aware Mixed ADC Resolution framework with fine-grained Tunability for Analog In-Memory Computing. SMART-AIMC correlates the algorithmic task loss to hardware ADC quantization noise in the form of an ADC Channel Sensitivity (ACS) metric. Using this metric, SMART-AIMC systematically, and in a disciplined manner, allocates ADC resources to critical computations. Furthermore, we introduce a sensitivity-based channel reordering scheme that overcomes the hardware granularity constraints with no runtime overhead and approaches the optimal ADC quantization possible for the model. Evaluated across diverse workloads, SMART-AIMC unlocks a superior accuracy-energy Pareto frontier, providing (1) higher task accuracy at matched energy budgets and (2) fine-grained tuning across efficiency targets, from aggressive energy savings to near-digital inference accuracy. At the latter operating point, SMART-AIMC achieves $6.99\times$ higher modeled system-level energy efficiency for linear projections than the INT8 digital baseline with negligible accuracy degradation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Hardware Architecture (cs.AR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.01707 — 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 2026-11-03T10:49:38.586Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).