MonoSparse-CAM:利用CAM中的单调性与稀疏性实现高效树模型处理
MonoSparse-CAM: Efficient Tree Model Processing via Monotonicity and Sparsity in CAMs
AI总结:
本文提出MonoSparse-CAM技术,通过利用树模型稀疏性与单调性优化CAM电路,实现能耗降低最高28.56倍、计算效率提升至少1.68倍。
摘要:
尽管基于树的机器学习(TBML)模型在表格数据上表现出优于神经网络的性能,并有望利用aCAM阵列实现高能效加速,但在硬件上理想地部署TBML结构并显式利用aCAM电路仍然是一项具有挑战性的任务。在本工作中,我们提出了MonoSparse-CAM,这是一种新的基于CAM的优化技术,利用CAM电路中的TBML稀疏性和单调性来进一步提升处理性能。我们的结果表明,与原始处理相比,MonoSparse-CAM将能耗降低了高达28.56倍,与最先进的技术相比降低了18.51倍,同时将计算效率提高了至少1.68倍。
英文摘要:
While the tree-based machine learning (TBML) models exhibit superior performance compared to neural networks on tabular data and hold promise for energy-efficient acceleration using aCAM arrays, their ideal deployment on hardware with explicit exploitation of TBML structure and aCAM circuitry remains a challenging task. In this work, we present MonoSparse-CAM, a new CAM-based optimization technique that exploits TBML sparsity and monotonicity in CAM circuitry to further advance processing performance. Our results indicate that MonoSparse-CAM reduces energy consumption by upto to 28.56x compared to raw processing and by 18.51x compared to state-of-the-art techniques, while improving the efficiency of computation by at least 1.68x.
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。