提升 CPU-GPU 异构系统上单面矩阵分解的节能效果
Improving Energy Saving of One-sided Matrix Decompositions on CPU-GPU Heterogeneous Systems
AI总结：
针对 CPU-GPU 异构系统上的单面矩阵分解，本文提出结合 ABFT-OC 与 DVFS 的 BSR 框架，在保证性能和可靠性的同时显著降低能耗并支持帕累托权衡。
摘要：
单面稠密矩阵分解（例如 Cholesky、LU 和 QR）是众多不同领域科学计算中的关键组成部分。尽管其设计已针对现代处理器进行了高度优化，但仍会消耗大量能量。由于 CPU-GPU 异构系统通常用于矩阵分解，本文致力于进一步提升 CPU-GPU 异构系统上单面矩阵分解的节能效果。我们首先构建了一种基于算法的容错保护超频技术（Algorithm-Based Fault Tolerance protected overclocking technique，ABFT-OC），使我们能够为关键矩阵分解操作利用可靠的超频。随后，我们设计了一个节能矩阵分解框架——双向松弛回收（Bi-directional Slack Reclamation，BSR），该框架能够智能结合 ABFT-OC 与 DVFS 所提供的能力，在保持性能和可靠性的同时最大化节能效果。实验表明，与当前最佳且无性能下降的节能优化方法相比，BSR 能够多节省最高 11.7% 的能量，并实现最高 14.1% 的 Energy * Delay^2 降低。此外，BSR 支持帕累托高效的性能-能量权衡，能够在不消耗额外能量的情况下提供最高 1.43 倍的性能提升。
英文摘要：
One-sided dense matrix decompositions (e.g., Cholesky, LU, and QR) are the key components in scientific computing in many different fields. Although their design has been highly optimized for modern processors, they still consume a considerable amount of energy. As CPU-GPU heterogeneous systems are commonly used for matrix decompositions, in this work, we aim to further improve the energy saving of one-sided matrix decompositions on CPU-GPU heterogeneous systems. We first build an Algorithm-Based Fault Tolerance protected overclocking technique (ABFT-OC) to enable us to exploit reliable overclocking for key matrix decomposition operations. Then, we design an energy-saving matrix decomposition framework, Bi-directional Slack Reclamation(BSR), that can intelligently combine the capability provided by ABFT-OC and DVFS to maximize energy saving and maintain performance and reliability. Experiments show that BSR is able to save up to 11.7% more energy compared with the current best energy saving optimization approach with no performance degradation and up to 14.1% Energy * Delay^2 reduction. Also, BSR enables the Pareto efficient performance-energy trade-off, which is able to provide up to 1.43x performance improvement without costing extra energy.
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。
