超维计算的硬件感知静态优化
Hardware-Aware Static Optimization of Hyperdimensional Computations
AI总结：
本文提出硬件感知静态优化框架 Heim，通过解析推导最小超向量大小，在满足目标精度并容忍硬件错误的同时减少资源使用，实验表明其精度和优化速度均显著优于动态调优方法。
摘要：
基于二进制散点码（BSC）的超维计算（HDC）是一种高度容错的近似计算范式，适用于易出错的新兴硬件平台。在 BSC HDC 中，基本数据类型是超向量，即通常较大的二进制向量，其中超向量的大小对计算的保真度和资源使用有显著影响。通常，超向量大小会被动态调整以提供所需精度；这一过程耗时较长，并且常常产生缺乏精度保证的超向量大小，在复用于非常相似的工作负载时结果不佳。我们提出 Heim，一个面向 BSC HD 计算的硬件感知静态分析与优化框架。Heim 以解析方式推导出最小超向量大小，从而最小化资源使用并满足目标精度要求。Heim 保证优化后的计算在期望上收敛到用户提供的精度目标，即使在存在硬件错误的情况下也是如此。Heim 采用了一种新颖的静态分析过程，该过程统一了神经科学界的理论结果，以系统化地优化 HD 计算。我们在 25 个基准数据结构上将 Heim 与基于动态调优的优化进行了评估。在 99% 精度要求下，Heim 优化后的计算实现了 99.2%–100.0% 的中位精度，比基于动态调优的优化高出最多 49.5%，同时与实现可比查询精度的 HD 计算相比，超向量大小减少了 1.15 倍–7.14 倍，并且找到参数化的速度比基于动态调优的方法快 30.0 倍–100167.4 倍。我们还使用 Heim 系统化地评估了在保持等精度的情况下，使用模拟 CAM 和每单元多比特 ReRAM 相对于传统硬件的性能收益——对于这两种新兴技术，我们都发现了新兴硬件带来显著收益的使用场景。
英文摘要：
Binary spatter code (BSC)-based hyperdimensional computing (HDC) is a highly error-resilient approximate computational paradigm suited for error-prone, emerging hardware platforms. In BSC HDC, the basic datatype is a hypervector, a typically large binary vector, where the size of the hypervector has a significant impact on the fidelity and resource usage of the computation. Typically, the hypervector size is dynamically tuned to deliver the desired accuracy; this process is time-consuming and often produces hypervector sizes that lack accuracy guarantees and produce poor results when reused for very similar workloads. We present Heim, a hardware-aware static analysis and optimization framework for BSC HD computations. Heim analytically derives the minimum hypervector size that minimizes resource usage and meets the target accuracy requirement. Heim guarantees the optimized computation converges to the user-provided accuracy target on expectation, even in the presence of hardware error. Heim deploys a novel static analysis procedure that unifies theoretical results from the neuroscience community to systematically optimize HD computations. We evaluate Heim against dynamic tuning-based optimization on 25 benchmark data structures. Given a 99% accuracy requirement, Heim-optimized computations achieve a 99.2%-100.0% median accuracy, up to 49.5% higher than dynamic tuning-based optimization, while achieving 1.15x-7.14x reductions in hypervector size compared to HD computations that achieve comparable query accuracy and finding parametrizations 30.0x-100167.4x faster than dynamic tuning-based approaches. We also use Heim to systematically evaluate the performance benefits of using analog CAMs and multiple-bit-per-cell ReRAM over conventional hardware, while maintaining iso-accuracy -- for both emerging technologies, we find usages where the emerging hardware imparts significant benefits.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
