With the continuous development of deep learning,Deep Convolutional Neural Network(DCNN)has attracted wide attention in the industry due to its high accuracy in image classification.Compared with other DCNN hard-ware ...With the continuous development of deep learning,Deep Convolutional Neural Network(DCNN)has attracted wide attention in the industry due to its high accuracy in image classification.Compared with other DCNN hard-ware deployment platforms,Field Programmable Gate Array(FPGA)has the advantages of being programmable,low power consumption,parallelism,and low cost.However,the enormous amount of calculation of DCNN and the limited logic capacity of FPGA restrict the energy efficiency of the DCNN accelerator.The traditional sequential sliding window method can improve the throughput of the DCNN accelerator by data multiplexing,but this method’s data multiplexing rate is low because it repeatedly reads the data between rows.This paper proposes a fast data readout strategy via the circular sliding window data reading method,it can improve the multiplexing rate of data between rows by optimizing the memory access order of input data.In addition,the multiplication bit width of the DCNN accelerator is much smaller than that of the Digital Signal Processing(DSP)on the FPGA,which means that there will be a waste of resources if a multiplication uses a single DSP.A multiplier sharing strategy is proposed,the multiplier of the accelerator is customized so that a single DSP block can complete multiple groups of 4,6,and 8-bit signed multiplication in parallel.Finally,based on two strategies of appeal,an FPGA optimized accelerator is proposed.The accelerator is customized by Verilog language and deployed on Xilinx VCU118.When the accelerator recognizes the CIRFAR-10 dataset,its energy efficiency is 39.98 GOPS/W,which provides 1.73×speedup energy efficiency over previous DCNN FPGA accelerators.When the accelerator recognizes the IMAGENET dataset,its energy efficiency is 41.12 GOPS/W,which shows 1.28×−3.14×energy efficiency compared with others.展开更多
为了使插电式混合动力汽车(plug-in hybrid electric vehicle,PHEV)能够获得更好的燃油经济性,本文提出了一种基于多目标优化的加速意图识别能量管理策略,在基于规则型能量管理策略的基础上采用模糊控制器构建起加速意图识别模块,通过...为了使插电式混合动力汽车(plug-in hybrid electric vehicle,PHEV)能够获得更好的燃油经济性,本文提出了一种基于多目标优化的加速意图识别能量管理策略,在基于规则型能量管理策略的基础上采用模糊控制器构建起加速意图识别模块,通过引入修正系数对整车需求转矩进行实时修正,实现更符合驾驶员意图的转矩输出,同时利用多目标粒子群算法对整车的传动比进行优化以提升整车燃油经济性,利用CRUISE软件搭建整车模型与MATLAB/Simulink进行联合仿真验证策略的有效性。仿真结果表明:在世界轻型车辆测试循环(world light vehicle test cycle,WLTC)工况下,当起始动力电池荷电状态(state of charge,SOC)为70%时,对比基于多目标优化的加速意图识别策略与单一的加速意图识别策略,前者的燃油经济性提升了0.48%;当起始SOC为35%时,前者的燃油经济性提升了2.22%,由此得出基于多目标优化的加速意图识别策略对于提升整车燃油经济性具有较好的效果。展开更多
Withthe rapiddevelopment of deep learning,the size of data sets anddeepneuralnetworks(DNNs)models are also booming.As a result,the intolerable long time for models’training or inference with conventional strategies c...Withthe rapiddevelopment of deep learning,the size of data sets anddeepneuralnetworks(DNNs)models are also booming.As a result,the intolerable long time for models’training or inference with conventional strategies can not meet the satisfaction of modern tasks gradually.Moreover,devices stay idle in the scenario of edge computing(EC),which presents a waste of resources since they can share the pressure of the busy devices but they do not.To address the problem,the strategy leveraging distributed processing has been applied to load computation tasks from a single processor to a group of devices,which results in the acceleration of training or inference of DNN models and promotes the high utilization of devices in edge computing.Compared with existing papers,this paper presents an enlightening and novel review of applying distributed processing with data and model parallelism to improve deep learning tasks in edge computing.Considering the practicalities,commonly used lightweight models in a distributed system are introduced as well.As the key technique,the parallel strategy will be described in detail.Then some typical applications of distributed processing will be analyzed.Finally,the challenges of distributed processing with edge computing will be described.展开更多
The Philippines was in the 1960s a model of development in Asia and second to Japan,but occupies presently only the 11th position under South-East and East Asian countries in terms of GDP-per capita.The article explor...The Philippines was in the 1960s a model of development in Asia and second to Japan,but occupies presently only the 11th position under South-East and East Asian countries in terms of GDP-per capita.The article explores why this important Asian country with a long colonial past and enormous economic potential still ranks under lower-income countries and has in the last decades let pass by many other Asian countries.In answering this question,the approach of external triggers for accelerated development is being applied.In stark contrast to the success stories of the strongly outward-looking Asian countries like the four Tigers,later of Thailand and Vietnam the Philippines never developed a vision of an open economy connecting pro-actively to the world markets.Trade is hampered by a non-competitive and highly protected national economy.The existing FDI is more oriented to the profitable local markets.Foreign debts were never effectively used and international tourism was never well promoted.Linking these failures to the existing power structures in the country,it seems very much that the backward forces like the big landowners,the local producers and industrialists never wanted and continue not to want to open up the economy to international competition and governments are complacent with these groups.Various indicators demonstrate the long-term decline of the Philippines:Among them the slow growth of the GDP and the continuously high poverty rates.As the alliance of big business and policy holds firm no change in the failing nationalistic economic model can be detected leaving the bleak outlook that the economic decline will continue.展开更多
基金supported in part by the Major Program of the Ministry of Science and Technology of China under Grant 2019YFB2205102in part by the National Natural Science Foundation of China under Grant 61974164,62074166,61804181,62004219,62004220,62104256.
文摘With the continuous development of deep learning,Deep Convolutional Neural Network(DCNN)has attracted wide attention in the industry due to its high accuracy in image classification.Compared with other DCNN hard-ware deployment platforms,Field Programmable Gate Array(FPGA)has the advantages of being programmable,low power consumption,parallelism,and low cost.However,the enormous amount of calculation of DCNN and the limited logic capacity of FPGA restrict the energy efficiency of the DCNN accelerator.The traditional sequential sliding window method can improve the throughput of the DCNN accelerator by data multiplexing,but this method’s data multiplexing rate is low because it repeatedly reads the data between rows.This paper proposes a fast data readout strategy via the circular sliding window data reading method,it can improve the multiplexing rate of data between rows by optimizing the memory access order of input data.In addition,the multiplication bit width of the DCNN accelerator is much smaller than that of the Digital Signal Processing(DSP)on the FPGA,which means that there will be a waste of resources if a multiplication uses a single DSP.A multiplier sharing strategy is proposed,the multiplier of the accelerator is customized so that a single DSP block can complete multiple groups of 4,6,and 8-bit signed multiplication in parallel.Finally,based on two strategies of appeal,an FPGA optimized accelerator is proposed.The accelerator is customized by Verilog language and deployed on Xilinx VCU118.When the accelerator recognizes the CIRFAR-10 dataset,its energy efficiency is 39.98 GOPS/W,which provides 1.73×speedup energy efficiency over previous DCNN FPGA accelerators.When the accelerator recognizes the IMAGENET dataset,its energy efficiency is 41.12 GOPS/W,which shows 1.28×−3.14×energy efficiency compared with others.
文摘为了使插电式混合动力汽车(plug-in hybrid electric vehicle,PHEV)能够获得更好的燃油经济性,本文提出了一种基于多目标优化的加速意图识别能量管理策略,在基于规则型能量管理策略的基础上采用模糊控制器构建起加速意图识别模块,通过引入修正系数对整车需求转矩进行实时修正,实现更符合驾驶员意图的转矩输出,同时利用多目标粒子群算法对整车的传动比进行优化以提升整车燃油经济性,利用CRUISE软件搭建整车模型与MATLAB/Simulink进行联合仿真验证策略的有效性。仿真结果表明:在世界轻型车辆测试循环(world light vehicle test cycle,WLTC)工况下,当起始动力电池荷电状态(state of charge,SOC)为70%时,对比基于多目标优化的加速意图识别策略与单一的加速意图识别策略,前者的燃油经济性提升了0.48%;当起始SOC为35%时,前者的燃油经济性提升了2.22%,由此得出基于多目标优化的加速意图识别策略对于提升整车燃油经济性具有较好的效果。
基金supported by the Natural Science Foundation of Jiangsu Province of China under Grant No.BK20211284the Financial and Science Technology Plan Project of Xinjiang Production,Construction Corps under Grant No.2020DB005the National Natural Science Foundation of China under Grant Nos.61872219,62002276 and 62177014。
文摘Withthe rapiddevelopment of deep learning,the size of data sets anddeepneuralnetworks(DNNs)models are also booming.As a result,the intolerable long time for models’training or inference with conventional strategies can not meet the satisfaction of modern tasks gradually.Moreover,devices stay idle in the scenario of edge computing(EC),which presents a waste of resources since they can share the pressure of the busy devices but they do not.To address the problem,the strategy leveraging distributed processing has been applied to load computation tasks from a single processor to a group of devices,which results in the acceleration of training or inference of DNN models and promotes the high utilization of devices in edge computing.Compared with existing papers,this paper presents an enlightening and novel review of applying distributed processing with data and model parallelism to improve deep learning tasks in edge computing.Considering the practicalities,commonly used lightweight models in a distributed system are introduced as well.As the key technique,the parallel strategy will be described in detail.Then some typical applications of distributed processing will be analyzed.Finally,the challenges of distributed processing with edge computing will be described.
文摘The Philippines was in the 1960s a model of development in Asia and second to Japan,but occupies presently only the 11th position under South-East and East Asian countries in terms of GDP-per capita.The article explores why this important Asian country with a long colonial past and enormous economic potential still ranks under lower-income countries and has in the last decades let pass by many other Asian countries.In answering this question,the approach of external triggers for accelerated development is being applied.In stark contrast to the success stories of the strongly outward-looking Asian countries like the four Tigers,later of Thailand and Vietnam the Philippines never developed a vision of an open economy connecting pro-actively to the world markets.Trade is hampered by a non-competitive and highly protected national economy.The existing FDI is more oriented to the profitable local markets.Foreign debts were never effectively used and international tourism was never well promoted.Linking these failures to the existing power structures in the country,it seems very much that the backward forces like the big landowners,the local producers and industrialists never wanted and continue not to want to open up the economy to international competition and governments are complacent with these groups.Various indicators demonstrate the long-term decline of the Philippines:Among them the slow growth of the GDP and the continuously high poverty rates.As the alliance of big business and policy holds firm no change in the failing nationalistic economic model can be detected leaving the bleak outlook that the economic decline will continue.
