With the continuous increasing of circuit scale, the problem of power consumption is paid much more attention than before, especially in large designs. In this paper, an experience of optimizing the power consumption ...With the continuous increasing of circuit scale, the problem of power consumption is paid much more attention than before, especially in large designs. In this paper, an experience of optimizing the power consumption of the 16-bit datapath in a 32-bit reconfigurable pipelined Digital Signal Processor (DSP) is introduced. By keeping the old input values and preventing the useless switching of the logic blocks on the datapath, the power consumption is much lowered. At the same time, by relocating some logic blocks between different pipeline stages and employing some data forward logics, a better balanced pipeline is achieved to lower the power consumption for conditional computation instructions at very low timing and area costs. The effectivity of these power optimization technologies are proved by the experimental results. Finally, some ideas about how to reduce the power consumption of circuits are proposed, which are very effective and useful in practice designs, especially in pipelined ones.展开更多
Fortran语言在科学与工程计算领域具有广泛应用。然而,通用数字信号处理器(General-Purpose Digital Signal Processor,GPDSP)目前主要使用C语言或汇编语言进行编程,尚不支持Fortran语言。针对这一现状,面向CPU-DSP异构处理器的Fortran...Fortran语言在科学与工程计算领域具有广泛应用。然而,通用数字信号处理器(General-Purpose Digital Signal Processor,GPDSP)目前主要使用C语言或汇编语言进行编程,尚不支持Fortran语言。针对这一现状,面向CPU-DSP异构处理器的Fortran编译器实现技术,基于LLVM Flang编译器框架设计并实现了Fortran编译器原型mtFortran,完成了Flang前端移植,并重点解决了Fortran程序在异构架构上的编译和运行支持,包括加载执行、语法支持、内建函数实现及输入输出(I/O)系统适配问题。实验结果表明,该Fortran编译器成功支持Fortran语言商用测试集U_F90_TS_LITE中GUIDE F90测试集的语法特性,在176个测试程序中运行时库已完全支持的测试程序(102道)全部通过异构编译与加载执行验证,主要类别内建函数的实现率达79.38%,并可支持典型高性能计算程序的运行(如NPB-EP测试程序),实现了Fortran程序在CPU-DSP异构处理器架构上的基础运行能力,为后续完善标准支持、性能优化及并行化扩展奠定了基础。展开更多
针对高频信道非高斯脉冲噪声致解调失效问题,提出一种基于浮点数字信号处理器(Digital Signal Processor,DSP)的实时抑制方法。该方法采用“粗筛—精剥—固化加速”3阶段递进架构:首先基于α模型和分数阶自适应门限粗筛强脉冲噪声;其次...针对高频信道非高斯脉冲噪声致解调失效问题,提出一种基于浮点数字信号处理器(Digital Signal Processor,DSP)的实时抑制方法。该方法采用“粗筛—精剥—固化加速”3阶段递进架构:首先基于α模型和分数阶自适应门限粗筛强脉冲噪声;其次通过时频空三域联合稀疏贝叶斯学习(Sparse Bayesian Learning,SBL)与零吸引算法精剥残留多径拖尾与人为干扰;最后在TMS320C6748上实施二级流水线与混合量化加速。测试结果表明,该方法端到端时延低于5 ms,可提供11.23 dB的信噪比增益并显著降低误码率。展开更多
针对视频信号处理需求,设计一种基于数字信号处理器(Digital Signal Processor,DSP)的高清远程视频通信监控系统。首先从系统架构、DSP选择与配置、视频信号采集与预处理等方面进行详细设计,其次介绍DSP的编程与实现及系统集成与调试过...针对视频信号处理需求,设计一种基于数字信号处理器(Digital Signal Processor,DSP)的高清远程视频通信监控系统。首先从系统架构、DSP选择与配置、视频信号采集与预处理等方面进行详细设计,其次介绍DSP的编程与实现及系统集成与调试过程,最后结合仿真与性能分析,验证了系统在实际应用中的可行性与优越性。展开更多
The automation process is a very important pillar for Industry 4.0.One of the first steps is the control of motors to improve production efficiency and generate energy savings.In mass production industries,techniques ...The automation process is a very important pillar for Industry 4.0.One of the first steps is the control of motors to improve production efficiency and generate energy savings.In mass production industries,techniques such as digital signal processing(DSP)systems are implemented to control motors.These systems are efficient but very expensive for certain applications.From this arises the need for a controller capable of handling AC and DC motors that improves efficiency and maintains low energy consumption.This project presents the design of an adaptive control system for brushless AC induction and DC motors,which is functional to any type of plant in the industry.The design was possible by implementing Matlab software and tools such as digital signal processor(DSP)and Simulink.Through an extensive investigation of the state of the art,three models needed to represent the control system have been specified.The first model for the AC motor,the second for the DC motor and the third for the DSP control;this is done in this way so that the probability of failure is lower.Subsequently,these models have been programmed in Simulink,integrating the three main models into one.In this way,the design of a controller for use in AC induction motors,specifically squirrel cage and brushless DC motors,has been achieved.The final model represents a response time of 0.25 seconds,which is optimal for this type of application,where response times of 2e-3 to 3 seconds are expected.展开更多
随着电子设备功率密度的不断提升,其散热系统产生的气动噪声问题日益突出。研究一种基于数字信号处理器(Digital Signal Processor,DSP)的主动噪声控制系统,采用声学超材料被动抑制与自适应主动控制相结合的混合架构。通过压电致动器与...随着电子设备功率密度的不断提升,其散热系统产生的气动噪声问题日益突出。研究一种基于数字信号处理器(Digital Signal Processor,DSP)的主动噪声控制系统,采用声学超材料被动抑制与自适应主动控制相结合的混合架构。通过压电致动器与改进型滤波型最小均方误差(Filtered-x Least Mean Square,FxLMS)算法,实现对复杂工况下低频湍流噪声的有效抑制。实验结果表明,所提系统具有良好的实时性与健壮性。展开更多
为了避免放射源检测烟支重量过程中对环境和人体造成伤害,设计了一种通过金属谐振腔作为密度传感器的烟支密度检测系统。该系统主要由微波信号源发送接收模块、微波谐振腔、数据处理模块组成。微波谐振腔是用于检测烟支密度的中心开通...为了避免放射源检测烟支重量过程中对环境和人体造成伤害,设计了一种通过金属谐振腔作为密度传感器的烟支密度检测系统。该系统主要由微波信号源发送接收模块、微波谐振腔、数据处理模块组成。微波谐振腔是用于检测烟支密度的中心开通孔的金属谐振腔,当烟支通过微波谐振腔的通孔时,烟支密度使谐振腔的谐振频率产生偏移和功率衰减,数据处理模块中的核心部件高速数字信号处理器DSP(D igital Signal Processor)根据数值变化计算出烟支密度,从而实现烟支密度的在线检测功能。现场调试表明,微波检测系统和放射源检测系统在平均重量控制效果上无明显差异,标准偏差控制方面微波系统略优于放射源系统,其标准偏差在25 mg以下。微波检测系统实现了烟支密度的连续在线测量,满足了生产精度要求,减少了环境污染和对人体的不良影响。展开更多
摘要With the continuous increasing of circuit scale, the problem of power consumption is paid much more attention than before, especially in large designs. In this paper, an experience of optimizing the power consumption of the 16-bit datapath in a 32-bit reconfigurable pipelined Digital Signal Processor (DSP) is introduced. By keeping the old input values and preventing the useless switching of the logic blocks on the datapath, the power consumption is much lowered. At the same time, by relocating some logic blocks between different pipeline stages and employing some data forward logics, a better balanced pipeline is achieved to lower the power consumption for conditional computation instructions at very low timing and area costs. The effectivity of these power optimization technologies are proved by the experimental results. Finally, some ideas about how to reduce the power consumption of circuits are proposed, which are very effective and useful in practice designs, especially in pipelined ones.
摘要Fortran语言在科学与工程计算领域具有广泛应用。然而,通用数字信号处理器(General-Purpose Digital Signal Processor,GPDSP)目前主要使用C语言或汇编语言进行编程,尚不支持Fortran语言。针对这一现状,面向CPU-DSP异构处理器的Fortran编译器实现技术,基于LLVM Flang编译器框架设计并实现了Fortran编译器原型mtFortran,完成了Flang前端移植,并重点解决了Fortran程序在异构架构上的编译和运行支持,包括加载执行、语法支持、内建函数实现及输入输出(I/O)系统适配问题。实验结果表明,该Fortran编译器成功支持Fortran语言商用测试集U_F90_TS_LITE中GUIDE F90测试集的语法特性,在176个测试程序中运行时库已完全支持的测试程序(102道)全部通过异构编译与加载执行验证,主要类别内建函数的实现率达79.38%,并可支持典型高性能计算程序的运行(如NPB-EP测试程序),实现了Fortran程序在CPU-DSP异构处理器架构上的基础运行能力,为后续完善标准支持、性能优化及并行化扩展奠定了基础。
摘要针对视频信号处理需求,设计一种基于数字信号处理器(Digital Signal Processor,DSP)的高清远程视频通信监控系统。首先从系统架构、DSP选择与配置、视频信号采集与预处理等方面进行详细设计,其次介绍DSP的编程与实现及系统集成与调试过程,最后结合仿真与性能分析,验证了系统在实际应用中的可行性与优越性。
摘要The automation process is a very important pillar for Industry 4.0.One of the first steps is the control of motors to improve production efficiency and generate energy savings.In mass production industries,techniques such as digital signal processing(DSP)systems are implemented to control motors.These systems are efficient but very expensive for certain applications.From this arises the need for a controller capable of handling AC and DC motors that improves efficiency and maintains low energy consumption.This project presents the design of an adaptive control system for brushless AC induction and DC motors,which is functional to any type of plant in the industry.The design was possible by implementing Matlab software and tools such as digital signal processor(DSP)and Simulink.Through an extensive investigation of the state of the art,three models needed to represent the control system have been specified.The first model for the AC motor,the second for the DC motor and the third for the DSP control;this is done in this way so that the probability of failure is lower.Subsequently,these models have been programmed in Simulink,integrating the three main models into one.In this way,the design of a controller for use in AC induction motors,specifically squirrel cage and brushless DC motors,has been achieved.The final model represents a response time of 0.25 seconds,which is optimal for this type of application,where response times of 2e-3 to 3 seconds are expected.
摘要随着电子设备功率密度的不断提升,其散热系统产生的气动噪声问题日益突出。研究一种基于数字信号处理器(Digital Signal Processor,DSP)的主动噪声控制系统,采用声学超材料被动抑制与自适应主动控制相结合的混合架构。通过压电致动器与改进型滤波型最小均方误差(Filtered-x Least Mean Square,FxLMS)算法,实现对复杂工况下低频湍流噪声的有效抑制。实验结果表明,所提系统具有良好的实时性与健壮性。
摘要为了避免放射源检测烟支重量过程中对环境和人体造成伤害,设计了一种通过金属谐振腔作为密度传感器的烟支密度检测系统。该系统主要由微波信号源发送接收模块、微波谐振腔、数据处理模块组成。微波谐振腔是用于检测烟支密度的中心开通孔的金属谐振腔,当烟支通过微波谐振腔的通孔时,烟支密度使谐振腔的谐振频率产生偏移和功率衰减,数据处理模块中的核心部件高速数字信号处理器DSP(D igital Signal Processor)根据数值变化计算出烟支密度,从而实现烟支密度的在线检测功能。现场调试表明,微波检测系统和放射源检测系统在平均重量控制效果上无明显差异,标准偏差控制方面微波系统略优于放射源系统,其标准偏差在25 mg以下。微波检测系统实现了烟支密度的连续在线测量,满足了生产精度要求,减少了环境污染和对人体的不良影响。