核函数是多种机器学习算法的重要组成部分，但通常会产生显著的内存和计算成本。我们提出了一种适用于混合信号模拟内存计算（AIMC）架构的机器学习算法中的核函数近似方法。模拟内存核函数近似通过直接在内存中执行近似核方法中的大部分操作，解决了传统基于核的方法的性能瓶颈。IBM HERMES项目芯片，一款基于相变内存的最先进的AIMC芯片，被用于核函数近似的硬件演示。实验结果表明，我们的方法保持了高精度，在基于核的岭回归分类基准测试中精度下降不到1%，在Transformer神经网络的核化注意力Long Range Arena基准测试中精度在1%以内。与传统数字加速器相比，我们的方法预计能提供更高的能效和更低的功耗。这些发现凸显了异构AIMC架构在提升机器学习应用效率和可扩展性方面的潜力。
英文摘要：
Kernel functions are vital ingredients of several machine learning algorithms, but often incur significant memory and computational costs. We introduce an approach to kernel approximation in machine learning algorithms suitable for mixed-signal Analog In-Memory Computing (AIMC) architectures. Analog In-Memory Kernel Approximation addresses the performance bottlenecks of conventional kernel-based methods by executing most operations in approximate kernel methods directly in memory. The IBM HERMES Project Chip, a state-of-the-art phase-change memory based AIMC chip, is utilized for the hardware demonstration of kernel approximation. Experimental results show that our method maintains high accuracy, with less than a 1% drop in kernel-based ridge classification benchmarks and within 1% accuracy on the Long Range Arena benchmark for kernelized attention in Transformer neural networks. Compared to traditional digital accelerators, our approach is estimated to deliver superior energy efficiency and lower power consumption. These findings highlight the potential of heterogeneous AIMC architectures to enhance the efficiency and scalability of machine learning applications.
vMCU: Coordinated Memory Management and Kernel Optimization for DNN Inference on MCUs
School of Computer Science, Peking University（北京大学计算机学院）；School of Computer Science & Engineering, University of Washington（华盛顿大学计算机科学与工程学院）；OctoAI（OctoAI公司）
Phase Kernel Lifts Capacity of Dense Associative Memory
Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China（电子科技大学基础与前沿研究院）；School of Physics, University of Electronic Science and Technology of China（电子科技大学物理学院）；Non-classical Information Science Basic Discipline Research Center of Sichuan Province, University of Electronic Science and Technology of China（电子科技大学四川省非经典信息科学基础学科研究中心）
PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；King’s College London（伦敦国王学院）；ETH Zürich（苏黎世联邦理工学院）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；NVIDIA（英伟达公司）
Kernel Neural Operators (KNOs) for Scalable, Memory-efficient, Geometrically-flexible Operator Learning
Kahlert School of Computing（卡勒特计算学院）；University of Utah（犹他大学）；Department of Mathematics（数学系）；Sandia National Laboratories（桑迪亚国家实验室）；Scientific Machine Learning（科学机器学习）；Scientific Computing and Imaging (SCI) Institute（科学计算与成像（SCI）研究所）
Quantum Kernel-Based Long Short-term Memory for Climate Time-Series Forecasting
National Center for High-Performance Computing, NARlabs（国家高性能计算中心（国家高速网络与计算中心））；Cross College Elite Program, National Cheng Kung University（成功大学跨学院精英计划）；National Synchrotron Radiation Research Center（国家同步辐射研究中心）；Imperial College London（伦敦帝国学院）
