发表机构
Georgia Institute of Technology; University of Texas Dallas; University of California San Diego; Samsung Electronics Co., Ltd.（佐治亚理工学院; 德克萨斯大学达拉斯分校; 加州大学圣地亚哥分校; 三星电子有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大规模数据库搜索中冯·诺依曼架构的瓶颈，本文提出基于多位铁电NAND的存储内计算平台，实验验证多级单元点积与汉明相似度计算，在TB级蛋白质组学任务中实现近千倍加速和万倍能效提升。
AI 中文摘要
从蛋白质组学到自主系统等数据密集型应用对大规模数据库搜索的需求日益增长，由于内存带宽和能量限制，冯·诺依曼架构暴露了根本性局限。超维（HD）计算为这类任务提供了鲁棒且可并行化的框架，但其实际实现仍受高内存需求挑战。超高密度、节能的铁电NAND（FE-NAND）存储器通过支持原位计算提供了潜在解决方案。我们制造了具有宽存储窗口、抗干扰能力和稳健保持特性的四电平FE-NAND串。以这些平面FE-NAND串为构建模块，我们在单单元层面实验演示了原位多级单元（MLC）点积运算，并使用实验校准的基于物理的模拟，演示了参考超向量与查询超向量（HV）之间的汉明相似度计算。该平台利用HD计算固有的容错性，即使在高逻辑电平（TLC、QLC）下也能实现超过90%的搜索准确率。在蛋白质组学中TB级数据集的开放修改搜索（OMS）任务上进行基准测试时，与现有解决方案相比，我们的系统显示出近1000倍的加速和超过10000倍的能效提升。这些结果确立了FE-NAND作为大规模高维数据处理中可行的存储内计算架构。
英文摘要
The growing demand for large-scale database search in data-intensive applications, ranging from proteomics to autonomous systems, has exposed fundamental limitations in von Neumann architectures due to memory bandwidth and energy constraints. Hyperdimensional (HD) computing offers a robust and parallelizable framework for such tasks, but its practical implementation remains challenged by high memory demands. Ultra-high-density, energy-efficient ferroelectric NAND (FE-NAND) memory provides a potential solution by enabling in-situ computation. We fabricate quad-level FE-NAND strings with wide memory windows, disturb resilience, and robust retention. Using these planar FE-NAND strings as building blocks, we experimentally demonstrate in-situ multi-level cell (MLC) dot product operations at the single-cell level and, using experimentally calibrated physics-based simulations, demonstrate Hamming similarity calculations between reference and query hypervectors (HV). This platform leverages the inherent error tolerance of HD computing to achieve >90% search accuracy even at high logic levels (TLC, QLC). When benchmarked on Open Modification Search (OMS) tasks in proteomics with TB-scale datasets, our system shows nearly 1,000x speedup and over 10,000x energy efficiency improvement compared to incumbent solutions. These results establish FE-NAND as a viable in-storage compute architecture for large-scale, high-dimensional data processing.
