基于张量核单元的相似性搜索
Similarity Search with Tensor Core Units
摘要:
张量核心单元(TCU)是为深度神经网络开发的硬件加速器,它有效地支持两个密集$\sqrt{m}\times \sqrt{m}$矩阵的乘法,其中$m$是给定的硬件参数。在本文中,我们表明,TCU可以加快相似性搜索问题。我们提出了算法的Johnson-Lindenstrauss降维和相似性连接,通过利用TCU,实现了$\sqrt{m}$加速相对于传统的方法。
英文摘要:
Tensor Core Units (TCUs) are hardware accelerators developed for deep neural networks, which efficiently support the multiplication of two dense $\sqrt{m}\times \sqrt{m}$ matrices, where $m$ is a given hardware parameter. In this paper, we show that TCUs can speed up similarity search problems as well. We propose algorithms for the Johnson-Lindenstrauss dimensionality reduction and for similarity join that, by leveraging TCUs, achieve a $\sqrt{m}$ speedup up with respect to traditional approaches.
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。