Thanks to the emerging 3D integration technology, The multiprocessor system on chips （MPSoCs） can now integrate more IP cores on chip with improved energy efficiency. However, several severe challenges also rise up ...Thanks to the emerging 3D integration technology, The multiprocessor system on chips （MPSoCs） can now integrate more IP cores on chip with improved energy efficiency. However, several severe challenges also rise up for 3D ICs due to the die-stacking architecture. Among them, power supply noise becomes a big concern. In the paper, we investigate power supply noise （PSN） interactions among different cores and tiers and show that PSN variations largely depend on task assignments. On the other hand, high integration density incurs a severe thermal issue on 3D ICs. In the paper, we propose a novel task scheduling framework considering both the PSN and the thermal issue. It mainly consists of three parts. First, we extract current stimuli of running tasks by analyzing their power traces derived from architecture level simulations. Second, we develop an efficient power delivery network （PDN） solver to evaluate PSN magnitudes efficiently. Third, we propose a heuristic algorithm to solve the formulated task scheduling problem. Compared with the state-of-the-art task assignment algorithm, the proposed method can reduce PSN by 12% on a 2 × 2 × 2 3D MPSoCs and by 14% on a 3 × 3 × 3 3D MPSoCs. The end-to-end task execution time also improves as much as 5.5% and 7.8% respectively due to the suppressed PSN.展开更多
The implementation of Countermeasure Techniques(CTs)in the context of Network-On-Chip(NoC)based Multiprocessor System-On-Chip(MPSoC)routers against the Flooding Denial-of-Service Attack(F-DoSA)falls under Multi-Criter...The implementation of Countermeasure Techniques(CTs)in the context of Network-On-Chip(NoC)based Multiprocessor System-On-Chip(MPSoC)routers against the Flooding Denial-of-Service Attack(F-DoSA)falls under Multi-Criteria Decision-Making(MCDM)due to the three main concerns,called:traffic variations,multiple evaluation criteria-based traffic features,and prioritization NoC routers as an alternative.In this study,we propose a comprehensive evaluation of various NoC traffic features to identify the most efficient routers under the F-DoSA scenarios.Consequently,an MCDM approach is essential to address these emerging challenges.While the recent MCDM approach has some issues,such as uncertainty,this study utilizes Fuzzy-Weighted Zero-Inconsistency(FWZIC)to estimate the criteria weight values and Fuzzy Decision by Opinion Score Method(FDOSM)for ranking the routers with fuzzy Single-valued Neutrosophic under names(SvN-FWZIC and SvN-FDOSM)to overcome the ambiguity.The results obtained by using the SvN-FWZIC method indicate that the Max packet count has the highest importance among the evaluated criteria,with a weighted score of 0.1946.In contrast,the Hop count is identified as the least significant criterion,with a weighted score of 0.1090.The remaining criteria fall within a range of intermediate importance,with enqueue time scoring 0.1845,packet count decremented and traversal index scoring 0.1262,packet count incremented scoring 0.1124,and packet count index scoring 0.1472.In terms of ranking,SvN-FDOSM has two approaches:individual and group.Both the individual and group ranking processes show that(Router 4)is the most effective router,while(Router 3)is the lowest router under F-DoSA.The sensitivity analysis provides a high stability in ranking among all 10 scenarios.This approach offers essential feedback in making proper decisions in the design of countermeasure techniques in the domain of NoC-based MPSoC.展开更多
随着以太网技术和集成电路技术的发展,以太网物理层(Physical Layer,PHY)芯片的速率和性能都得到了极大提升,电路复杂度更是几何级增长,以至于常规的自动测试设备(Automatic Test Equipment,ATE)测试很难充分验证其功能,所以亟需开展相...随着以太网技术和集成电路技术的发展,以太网物理层(Physical Layer,PHY)芯片的速率和性能都得到了极大提升,电路复杂度更是几何级增长,以至于常规的自动测试设备(Automatic Test Equipment,ATE)测试很难充分验证其功能,所以亟需开展相应测试方法研究。提出了一种高效的基于ZYNQ MPSOC的以太网PHY芯片功能测试方法。该方法以ZYNQ MPSOC为核心,设计了一种直达应用层面的系统级测试装置,从而减少了与物理层直接交互的行为,有效降低了测试装置及程序开发难度。经试验验证,提出的基于ZYNQ MPSOC的以太网PHY芯片功能测试方法能够用于以太网PHY芯片测试。展开更多
随着集成技术的快速发展,使得单个芯片上集成IP核数目越来越多。然而,晶体管密度和处理器工作频率的不断提升,使得功耗密度持续增加,导致芯片热量的不断上升。因此,MPSoCs面临不可避免的散热问题。提出了一种基于处理器核区域均温(Regio...随着集成技术的快速发展,使得单个芯片上集成IP核数目越来越多。然而,晶体管密度和处理器工作频率的不断提升,使得功耗密度持续增加,导致芯片热量的不断上升。因此,MPSoCs面临不可避免的散热问题。提出了一种基于处理器核区域均温(Regional Mean Temperature,RMT)的初始任务分配策略,该方法充分考虑到处理器核区域温度。通过向量距离计算处理器核温度梯度,使用遗传算法进行初始任务分配。实验结果表明,该策略相比于随机任务分配策略,峰值温度降低率、热点降低率和温度梯度降低率最高分别达到4.69%、42.31%和77.49%。展开更多
随着深亚微米工艺的迅速发展,现代网络处理器芯片广泛采用MPSoC(Multi-Processor System on Chip)体系结构实现,继而需要一种新的设计方法指导网络处理器体系结构设计.本文研究了网络处理器的设计方法,提出了一种基于遗传算法的网络应...随着深亚微米工艺的迅速发展,现代网络处理器芯片广泛采用MPSoC(Multi-Processor System on Chip)体系结构实现,继而需要一种新的设计方法指导网络处理器体系结构设计.本文研究了网络处理器的设计方法,提出了一种基于遗传算法的网络应用到网络处理器异构硬件资源映射方法.该方法首先对网络处理器设计的问题空间进行分析,采用加权数据流进程网络描述网络应用,并参数化各种硬件资源,最后构建遗传算法来完成网络应用到异构硬件资源的映射,形成网络处理器体系结构设计方案.展开更多
基金This work was supported by the National Natural Science Foundation of China under Grant Nos. 61401008 and 61602022, and the State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, under Grant No. CARCH201602.
文摘Thanks to the emerging 3D integration technology, The multiprocessor system on chips （MPSoCs） can now integrate more IP cores on chip with improved energy efficiency. However, several severe challenges also rise up for 3D ICs due to the die-stacking architecture. Among them, power supply noise becomes a big concern. In the paper, we investigate power supply noise （PSN） interactions among different cores and tiers and show that PSN variations largely depend on task assignments. On the other hand, high integration density incurs a severe thermal issue on 3D ICs. In the paper, we propose a novel task scheduling framework considering both the PSN and the thermal issue. It mainly consists of three parts. First, we extract current stimuli of running tasks by analyzing their power traces derived from architecture level simulations. Second, we develop an efficient power delivery network （PDN） solver to evaluate PSN magnitudes efficiently. Third, we propose a heuristic algorithm to solve the formulated task scheduling problem. Compared with the state-of-the-art task assignment algorithm, the proposed method can reduce PSN by 12% on a 2 × 2 × 2 3D MPSoCs and by 14% on a 3 × 3 × 3 3D MPSoCs. The end-to-end task execution time also improves as much as 5.5% and 7.8% respectively due to the suppressed PSN.
文摘The implementation of Countermeasure Techniques(CTs)in the context of Network-On-Chip(NoC)based Multiprocessor System-On-Chip(MPSoC)routers against the Flooding Denial-of-Service Attack(F-DoSA)falls under Multi-Criteria Decision-Making(MCDM)due to the three main concerns,called:traffic variations,multiple evaluation criteria-based traffic features,and prioritization NoC routers as an alternative.In this study,we propose a comprehensive evaluation of various NoC traffic features to identify the most efficient routers under the F-DoSA scenarios.Consequently,an MCDM approach is essential to address these emerging challenges.While the recent MCDM approach has some issues,such as uncertainty,this study utilizes Fuzzy-Weighted Zero-Inconsistency(FWZIC)to estimate the criteria weight values and Fuzzy Decision by Opinion Score Method(FDOSM)for ranking the routers with fuzzy Single-valued Neutrosophic under names(SvN-FWZIC and SvN-FDOSM)to overcome the ambiguity.The results obtained by using the SvN-FWZIC method indicate that the Max packet count has the highest importance among the evaluated criteria,with a weighted score of 0.1946.In contrast,the Hop count is identified as the least significant criterion,with a weighted score of 0.1090.The remaining criteria fall within a range of intermediate importance,with enqueue time scoring 0.1845,packet count decremented and traversal index scoring 0.1262,packet count incremented scoring 0.1124,and packet count index scoring 0.1472.In terms of ranking,SvN-FDOSM has two approaches:individual and group.Both the individual and group ranking processes show that(Router 4)is the most effective router,while(Router 3)is the lowest router under F-DoSA.The sensitivity analysis provides a high stability in ranking among all 10 scenarios.This approach offers essential feedback in making proper decisions in the design of countermeasure techniques in the domain of NoC-based MPSoC.
文摘随着集成技术的快速发展,使得单个芯片上集成IP核数目越来越多。然而,晶体管密度和处理器工作频率的不断提升,使得功耗密度持续增加,导致芯片热量的不断上升。因此,MPSoCs面临不可避免的散热问题。提出了一种基于处理器核区域均温(Regional Mean Temperature,RMT)的初始任务分配策略,该方法充分考虑到处理器核区域温度。通过向量距离计算处理器核温度梯度,使用遗传算法进行初始任务分配。实验结果表明,该策略相比于随机任务分配策略,峰值温度降低率、热点降低率和温度梯度降低率最高分别达到4.69%、42.31%和77.49%。
文摘随着深亚微米工艺的迅速发展,现代网络处理器芯片广泛采用MPSoC(Multi-Processor System on Chip)体系结构实现,继而需要一种新的设计方法指导网络处理器体系结构设计.本文研究了网络处理器的设计方法,提出了一种基于遗传算法的网络应用到网络处理器异构硬件资源映射方法.该方法首先对网络处理器设计的问题空间进行分析,采用加权数据流进程网络描述网络应用,并参数化各种硬件资源,最后构建遗传算法来完成网络应用到异构硬件资源的映射,形成网络处理器体系结构设计方案.
