用CORDIC动态调节精度，实现低功耗高效深度学习推理。
CARMEN: CORDIC-Accelerated Resource-Efficient Multi-Precision Inference Engine for Deep Learning
- 通过可调迭代深度的CORDIC单元实现精度与功耗动态平衡。
- 28nm芯片实测：单MAC减少33%计算周期，功耗降21%，能效达11.67 TOPS/W。
- 适合嵌入式设备部署，支持实时目标检测，延迟仅154.6毫秒。
本文提出CARMEN，一种面向资源高效深度学习推理的运行时自适应、CORDIC加速多精度向量引擎。核心思想是CORDIC迭代深度直接决定计算精度，从而可在不修改硬件的前提下动态切换近似与精确执行模式。架构集成低资源迭代式CORDIC乘加单元与时间复用的多激活函数模块，支持灵活的8/16位精度配置，实现高硬件利用率。在28纳米CMOS工艺下的ASIC实现中，单个乘加单元计算周期最多减少33%，功耗降低21%；256核配置下达到4.83 TOPS/mm²的计算密度和11.67 TOPS/W的能效。基于PynqZ2的FPGA部署验证了实时目标检测任务中0.43 W功耗下154.6毫秒的延迟。
原文摘要 · Abstract (English)
This paper presents CARMEN, a runtime-adaptive, CORDIC-accelerated multi-precision vector engine for resource-efficient deep learning inference. The key insight is that CORDIC iteration depth directly governs computational accuracy, enabling dynamic switching between approximate and accurate execution modes without hardware modification. The architecture integrates a low-resource iterative CORDIC-based MAC unit with a time-multiplexed multi-activation function block, supporting flexible 8/16-bit precision and high hardware utilization. ASIC implementation in 28 nm CMOS achieves up to 33% reduction in computation cycles and 21% power savings per MAC stage; a 256-PE configuration delivers 4.83 TOPS/mm2 compute density and 11.67 TOPS/W energy efficiency. FPGA deployment on PynqZ2 validates 154.6 ms latency at 0.43 W for real-time object detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。