arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.13852cs.LGcs.AIcs.DC
收藏

H2H:具有计算和通信感知的异构模型到异构系统的映射

H2H: Heterogeneous Model to Heterogeneous System Mapping with Computation and Communication Awareness

University of Pittsburgh(匹兹堡大学);Georgia Institute of Technology(佐治亚理工学院)

Xinyi Zhang, Cong Hao, Peipei Zhou, Alex Jones, Jingtong Hu

摘要:

现实世界问题的复杂性要求机器学习(ML)模型和硬件系统都具有异质性。ML模型中的异质性来自多传感器感知和多任务学习,即,多模态多任务(MMMT),导致不同的深度神经网络(DNN)层和计算模式。系统中的异构性来自不同的处理组件,因为它成为将多个专用加速器集成到一个系统中的流行方法。因此,一个新的问题出现了:异构模型到异构系统的映射(H2 H)。虽然以前的映射算法主要集中在有效的计算,在这项工作中,我们认为,它是必不可少的,以考虑计算和通信同时更好的系统效率。我们提出了一种新的H2 H映射算法的计算和通信意识,通过稍微交易的通信计算,系统的整体延迟和能量消耗可以大大降低。基于MAESTRO模型评估了我们工作的优越性能,与现有的计算优先映射算法相比,延迟减少了15%-74%,能量减少了23%-64%。

英文摘要:

The complex nature of real-world problems calls for heterogeneity in both machine learning (ML) models and hardware systems. The heterogeneity in ML models comes from multi-sensor perceiving and multi-task learning, i.e., multi-modality multi-task (MMMT), resulting in diverse deep neural network (DNN) layers and computation patterns. The heterogeneity in systems comes from diverse processing components, as it becomes the prevailing method to integrate multiple dedicated accelerators into one system. Therefore, a new problem emerges: heterogeneous model to heterogeneous system mapping (H2H). While previous mapping algorithms mostly focus on efficient computations, in this work, we argue that it is indispensable to consider computation and communication simultaneously for better system efficiency. We propose a novel H2H mapping algorithm with both computation and communication awareness; by slightly trading computation for communication, the system overall latency and energy consumption can be largely reduced. The superior performance of our work is evaluated based on MAESTRO modeling, demonstrating 15%-74% latency reduction and 23%-64% energy reduction compared with existing computation-prioritized mapping algorithms.

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。

↑