English(EN) SLICE-CiM: Selective Layer-wise Inference Control Engine with Confidence-Based Early Exit for SRAM based Digital Compute-in-Memory

新的计算内存引擎提高了CNN推理效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 17:32

研究人员开发了SLICE-CiM，一种用于SRAM数字计算内存（CIM）宏的新型控制引擎，旨在提高CNN推理的能效。该系统包含四个外围模块，包括一个基于置信度的提前退出模块，以最小化功耗并优化性能。SLICE-CiM在TSMC 65-nm CMOS上实现，展示了显著的能效提升，在MobileNetV2上实现了高达454.91 TOPS/W的性能，且无需修改位单元或重新训练。 AI

影响这种新的计算内存架构显著提高了AI推理任务的能效，有可能在边缘设备上实现更强大的AI功能。

排序理由该项目是一篇研究论文，详细介绍了一种用于AI推理的新硬件架构。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.NE (Neural & Evolutionary) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 3 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇研究论文，详细介绍了一种用于AI推理的新硬件架构。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: infra, paper; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Santosh Kumar Vishvakarma · 2026-10-27 17:32

SLICE-CiM：基于置信度的SRAM数字计算内存的层级推理选择性控制引擎及早期退出机制

Digital SRAM compute-in-memory (CIM) macros enable energy-efficient CNN inference by eliminating off-chip weight transfers; however, peripheral control logic introduces three inefficiencies: bit- slice over-activation at reduced precision (L1), unnecessary accumula- tion depth (L…

本文如何被排名

报道来源 [1]

SLICE-CiM：基于置信度的SRAM数字计算内存的层级推理选择性控制引擎及早期退出机制

相关实体

相关话题