.png){kind=icon}
返回
Mobile Application Processors: Techniques for Software Power-Performance Optimization
.png){kind=icon}
PRE
AI
DOI：10.1109/MCE.2020.2969171.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The latest and upcoming mobile application processors, embedded in a myriad of consumer devices, are typically implemented as heterogeneous multiprocessor system-on-chips, comprised of various processing engines such as general-purpose cores with differing characteristics, GPUs, DSPs, nonprogrammable accelerators, and reconfigurable computing devices. The heterogeneity allows application kernels with specific requirements to be executed on processing core(s) ideally suited to perform that computation, resulting in a significantly improved performance and energy-efficiency. However, while heterogeneous computing is an attractive proposition in theory, considerable software support at all levels is essential to fully realize its promises. The system software needs to orchestrate the different on-chip compute resources in a synergistic manner with minimal engagement from the application developers, as well as fulfill the stringent power-thermal constraint in mobile computing. In this article, we present compiler time and runtime techniques to unleash the full potential of heterogeneous multiprocessors toward high-performance energy-efficient computing on consumer devices.
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.1
论文数:
1.3K
被引数:
1.8K
机构
引用论文
Live Data Analytics With Collaborative Edge and Cloud Processing in Wireless IoT Networks.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏 没有更多内容
没有更多内容