WHYPE：一种支持无线空中多数的可扩展内存中多维计算的横向扩展架构
WHYPE: A Scale-Out Architecture with Wireless Over-the-Air Majority for Scalable In-memory Hyperdimensional Computing
摘要：
超维计算（HDC）是一种新兴的计算范式，它使用称为超向量的长随机向量来表示、操作和通信数据。在能够执行HDC算法的不同硬件平台中，存内计算（IMC）已经显示出前景，因为它在执行矩阵-向量乘法中非常有效，这在HDC代数中是常见的。尽管基于IMC的HDC架构已经存在，但由于这些架构需要集体通信模式，而传统芯片级网络并非为之设计，因此如何扩展它们仍然是一个关键挑战。为了应对这一困难，我们提出了一个横向扩展的HDC架构称为WHYPE，它使用无线封装内通信技术来互连大量的物理分布式IMC核心，无论是编码超向量或并行执行多个相似性搜索。在这种情况下，WHYPE的关键推动者是机会主义地使用无线网络作为空中计算的媒介。WHYPE实现了优化的信源编码，允许接收器计算通过无线信道同时传输的多个超向量的按位多数（HDC中的有用操作）。通过这样做，我们实现了一个联合广播分布和计算的性能和效率无法达到有线互连，这反过来又使大规模并行化的架构。通过在片上网络和完整架构级别的评估，我们证明了WHYPE可以比假设的有线实现更快，更有效地捆绑和分发超向量，并且它可以很好地扩展到数十个接收器。我们表明，大多数计算的平均出错率是低的，这样它对HDC分类任务的准确性的影响可以忽略不计。
英文摘要：
Hyperdimensional computing (HDC) is an emerging computing paradigm that represents, manipulates, and communicates data using long random vectors known as hypervectors. Among different hardware platforms capable of executing HDC algorithms, in-memory computing (IMC) has shown promise as it is very efficient in performing matrix-vector multiplications, which are common in the HDC algebra. Although HDC architectures based on IMC already exist, how to scale them remains a key challenge due to collective communication patterns that these architectures required and that traditional chip-scale networks were not designed for. To cope with this difficulty, we propose a scale-out HDC architecture called WHYPE, which uses wireless in-package communication technology to interconnect a large number of physically distributed IMC cores that either encode hypervectors or perform multiple similarity searches in parallel. In this context, the key enabler of WHYPE is the opportunistic use of the wireless network as a medium for over-the-air computation. WHYPE implements an optimized source coding that allows receivers to calculate the bit-wise majority of multiple hypervectors (a useful operation in HDC) being transmitted concurrently over the wireless channel. By doing so, we achieve a joint broadcast distribution and computation with a performance and efficiency unattainable with wired interconnects, which in turn enables massive parallelization of the architecture. Through evaluations at the on-chip network and complete architecture levels, we demonstrate that WHYPE can bundle and distribute hypervectors faster and more efficiently than a hypothetical wired implementation, and that it scales well to tens of receivers. We show that the average error rate of the majority computation is low, such that it has negligible impact on the accuracy of HDC classification tasks.
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。
