A 21.5M-Query-Vectors/s 3.37nJ/Vector Reconfigurable k-Nearest-Neighbor Accelerator with Adaptive Precision in 14nm Tri-Gate CMOS

📋 论文概要

该论文提出了一种在14nm工艺上实现的可重构k近邻加速器，通过自适应精度技术消除大部分向量的全精度计算，显著提升能效。实现了21.5M查询向量/秒的吞吐率和3.37nJ/向量的能耗。

💡 主要创新点

• 采用自适应精度策略，根据匹配程度逐步增加计算精度，避免不必要的全精度运算，降低能耗。
• 支持可重构架构，可灵活配置以适应不同k近邻计算需求。
• 在14nm先进工艺节点下实现了高吞吐量和高能效的专用加速器。

🏷 关键词

📄 原文摘要

Sudhir K. Satpathy, Steven K. Hsu, Amit Agarwal, Ram K. Krishnamurthy Intel, Hillsboro, OR Energy-efficient k-nearest-neighbor (kNN) computations are key building blocks for computer vision, classification, and machine-learning workloads [1-3]. Determining distances to high-dimensional vectors within a large vector database results in high compute cost. Adaptive precision improves energy efficiency by eliminating a majority of vectors without costly full-precision computation, with as-needed precision refinement to guarantee kNN accuracy of closely matched vectors. A special-purpose on-die kNN accelerator with 128-dimensions by 128 parallel reference vectors, targeted across mobile SoCs to multi-core microprocessors, and reconfigurable for either Manhattan or Euclidean distance, is fabricated in 14nm tri-gate CMOS [6]. Partial distance compute circuits, 2b window-based sort, MSB-to-LSB-based selective distance refinement, robust

👥 作者与机构

Himanshu Kaul, Mark A. Anders, Sanu K. Mathew, Gregory Chen,