Brain-inspired hyperdimensional (HD) computing emulates cognition by computing with long-size vectors. HD computing consists of two main modules: encoder and associative search. The encoder module maps inputs into high dimensional vectors, called hypervectors. The associative search finds the closest match between the trained model (set of hypervectors) and a query hypervector by calculating a similarity metric. To perform the reasoning task for practical classification problems, HD needs to store a non-binary model and uses costly similarity metrics as cosine. In this article we propose an FPGA-based acceleration of HD exploiting Computational Reuse ($\mathtt {HD}$HD-$\mathtt {Core}$Core) which significantly improves the computation efficiency of both encoding and associative search modules. $\mathtt {HD}$HD-$\mathtt {Core}$Core enables computation reuse in both encoding and associative search modules. We observed that consecutive inputs have high similarity which can be used to reduce the complexity of the encoding step. The previously encoded hypervector is reused to eliminate the redundant operations in encoding the current input. $\mathtt {HD}$HD-$\mathtt {Core}$Core, additionally eliminates the majority of multiplication operations by clustering the class hypervector values, and sharing the values among all the class hypervectors. Our evaluations on several classification problems show that $\mathtt {HD}$HD-$\mathtt {Core}$Core can provide $4.4\times$4.4× energy efficiency improvement and $4.8\times$4.8× speedup over the optimized GPU implementation while ensuring the same quality of classification. $\mathtt {HD}$HD-$\mathtt {Core}$Core provides $2.4\times$2.4× more throughput than the state-of-the-art FPGA implementation; on average, 40 percent of this improvement comes directly from enabling computation reuse in the encoding module and the rest comes from the computation reuse in the associative search module.

中文翻译：

---

通过利用计算重用加速 FPGA 上的超维计算

受大脑启发的超维 (HD) 计算通过使用长尺寸向量进行计算来模拟认知。高清计算由两个主要模块组成：编码器和关联搜索。编码器模块将输入映射到高维向量，称为超向量。关联搜索找到最接近的匹配训练模型 （一组超向量）和一个 询问超向量通过计算相似性度量。为了执行实际分类问题的推理任务，HD 需要存储一个非二元模型并使用代价高昂的相似性度量作为余弦. 在本文中，我们提出了一种基于 FPGA 的加速高清 剥削 公司计算的 关于用 （$\mathtt {HD}$高清——$\mathtt {核心}$核) 显着提高了编码和关联搜索模块的计算效率。 $\mathtt {HD}$高清——$\mathtt {核心}$核在编码和关联搜索模块中启用计算重用。我们观察到连续输入具有高相似性，可用于降低编码步骤的复杂性。重复使用先前编码的超向量以消除编码当前输入时的冗余操作。$\mathtt {HD}$高清——$\mathtt {核心}$核，通过聚类类超向量值并在所有类超向量之间共享值，另外消除了大多数乘法运算。我们对几个分类问题的评估表明，$\mathtt {HD}$高清——$\mathtt {核心}$核 可以提供 $4.4\times$4.4× 提高能源效率和 $4.8\times$4.8× 加速优化的 GPU 实现，同时确保相同的分类质量。 $\mathtt {HD}$高清——$\mathtt {核心}$核 提供 $2.4\times$2.4×比最先进的 FPGA 实现更高的吞吐量；平均而言，这种改进的 40% 直接来自启用编码模块中的计算重用，其余来自关联搜索模块中的计算重用。