CERCIS:一种视频媒体编解码片上系统的设计实现

基于面向特定应用的可配置处理器架构及其设计方法,设计并完成了一种视频媒体编解码片上系统芯片,它具有通用数字信号处理器的柔性编程及特定目标应用时的高性能等特点。该视频编解码片上系统由编码和解码2部分组成,编码和解码部分都采用相同的媒体信号处理架构。媒体信号处理编码、解码架构中分别包含一个8发射超长指令字数字信号处理器核,还包括实现视频媒体应用的专用数据传输单元,变长编解码单元以及接口单元,可以完成H.263视频媒体编码和解码。在0.13μm工艺库下模拟验证表明,该片上系统在17MH z工作频率下可完成15帧/s QC IF图像的H.263编码,在10MH z工作频率下可完成15帧/s QC IF图像的H.263解码。     

一种异构双核系统芯片平台设计与实现

提出了一种基于CKCore RISC处理器和Spock DSP处理器的异构双核系统芯片平台(GEM-SoC).该平台通过提供可配的功能IP模块和灵活完善的软硬件架构,使得异构双核SoC设计更为准确高效.实验证明,GEM-SoC平台可以有效地加快Ogg解码应用的双核软件程序设计开发.原型芯片在37.68 MHz时钟频率时运行,即可实现实时Ogg音频解码播放,具有较好的功耗性能比.     

可编程语音压缩专用处理器设计

为了提高通信系统的保密性,降低制造成本,需要进行专用处理器的设计。基于正弦激励线性预测(SELP)算法模型,设计了一款多速率语音专用处理器。芯片使用可重构体系结构和超长指令字(VLIW),优化了高复杂度函数。仿真结果表明:该处理器对0.6kb/s速率SELP算法的执行效率明显优于通用数字信号处理器(DSP)。处理器内部程序数据外部不可见,指令并行度显著提高,常用函数可被修改,从而达到高保密性、低复杂度、易开发性。     

一种可编程安全处理器体系结构的研究与实现

提出了一种可编程安全处理器PSP(Programm ab le Security Processor)的体系结构,该体系结构由SPARC V8处理器内核、AHB片上总线及密码算法模块等部分构成,密码算法模块通过AHB总线与处理器内核进行高速交互.FPGA原型实现表明,该安全处理器能通过SPARC指令编程进行灵活控制,密码算法模块可以按需配置,能够满足嵌入式计算中对安全性和灵活性的需要.     

VLSI design of 3D display processing chip for binocular stereo displays

In order to develop the core chip supporting binocular stereo displays for head mounted display(HMD)and glasses-TV,a very large scale integrated(VLSI)design scheme is proposed by using a pipeline architecture for 3D display processing chip(HMD100).Some key techniques including stereo display processing and high precision video scaling based bicubic interpolation,and their hardware implementations which improve the image quality are presented.The proposed HMD100 chip is verified by the field-programmable gate array(FPGA).As one of innovative and high integration SoC chips,HMD100 is designed by a digital and analog mixed circuit.It can support binocular stereo display,has better scaling effect and integration.Hence it is applicable in virtual reality(VR),3D games and other microdisplay domains.     

自保持接口在模拟芯核虚数字化测试中的优化

数模混合片上系统(SoC)正逐步成为片上系统的主导,而其中模拟芯核的测试问题是研究的难点之一。利用自保持模拟测试接口(SHATI)可以实现模拟芯核对外接口虚数字化,对其进行并行测试。该文对自保持模拟测试接口进行了面积优化,以减少片上DFT(design for test)面积开销,并利用Hspice仿真实验验证了面积改进的可行性。同时,针对并行测试的测试激励调度问题,该文给出了测试时序设计的优化算法,并通过实际示例验证了算法的可行性。     

红外/毫米波复合制导信息处理方法及MPSoC实现

针对共口径红外/毫米波复合制导应用需求,提出一种基于自回归(AR)谱估计和扩展卡尔曼滤波的信息融合处理新方法,基于此方法构建了实现红外/毫米波复合制导信息处理的多处理器片上系统(multiprocessor SoC,MPSoC),该系统采用主/从流水线结构,解决了基于此系统框架的多核通信、系统同步等问题.所提多处理器片上系统在单片FPGA上实现,FPGA实测结果表明,目标融合预测轨迹和真实轨迹基本重合,误差不超过10-2 rad,航向角融合精度远高于毫米波雷达和红外的精度,取得了比较好的融合效果;在100MHz的时钟下,整个红外/毫米波复合制导的信号处理的处理时间不超过2ms,满足复合制导对系统的实时性要求.     

基于UWB无线定位的汽车防撞系统设计

汽车测速、测距的防撞预警可有效避免交通事故的发生。介绍了测速、测距原理,在此基础上论述了基于系统及芯片(system on a chip,SoC)的汽车防撞系统,提出了一种应用SoC芯片和超宽带(ultra wide band,UWB)无线定位技术的汽车防撞系统方案,研究了系统中关键功能模块UWB模块和SoC信号处理模块的实现和软件处理流程。结果表明,该方案可对行驶中的汽车与汽车以及汽车与其他障碍物之间的距离进行实时监测,在距离较近时能准确及时地判断并采取合理的处理措施,避免碰撞的发生,保障行车安全。     

一种面向多媒体和通信应用的处理器指令集及架构实现

提出了一种面向多媒体和通信应用的CPU和DSP一体化计算的指令集架构,并设计实现了一款基于该指令集架构的VLIW DSP处理器.该CPU和DSP融合指令集架构中的CPU指令兼容已有MIPS 4KC指令集,DSP指令为自主设计.针对多媒体和通信常用算法中并行度高等特点,提出了多条基于像素操作、向量操作和复数操作的DSP指令,并详细说明了实现这些指令的关键功能模块的电路实现方法.实验结果表明,在多媒体的插值、重建以及通信的滤波、FFT等算法上,采用本文提出的面对特定应用的指令集具有较明显的优势.流片测试结果证明该指令集架构可实现且有效.     

Implementation of transaction level AMBA bus models using systemC

This paper deals with how to implement AMBA bus transaction level modeling in SystemC.There are twom ain techniques used in the whole modeling process,which consist of starting the platform modeling at the transaction level and using the uniformed modeling language-System C.According to the concepts of interface,port and hierarchical channel introduced in SystemC 2.0,the system of master-channel (AMBA bus) slave is created as the architecture of the AMBA bus transaction level model,which can make it more extendable.The port and interface classes of the model that are prone to program are defined in accordance with the SoC hierarchical design methodology,In addition,method calls,not signal communication,are used between different modules in the model,so the higher-level abstraction is achieved and the simulation performance is improved.The AMBA bus transaction level model is analyzed and certified by simulation experiment,and proved to be completely compliant to the AMBA specification 2.0.     

SoC与嵌入式系统

SoC是嵌入式系统的一种新形式,是将微处理器、模拟IP核、数字IP核和存储器(或片外存储控制接口)集成在单一芯片上,它通常是客户定制的,或是面向特定用途的标准产品.在一块硅片里实现了能完成一个计算机系统功能所需要的硬件集成电路和嵌入式软件,属于计算机与微电子的新兴交叉学科.就SoC的关键技术做了分析,对其应用及发展进行了讨论.     

Multiple MIPS 4Kc cores based interrupt controller design and its implementation on HDTV SoC platform

A multiple MIPS 4Kc processor cores based interrupt processing system is introduced. The interrupt controller plays a key role in the high definition television （HDTV） system-on-a-chip （SoC） platform, especially when it is a multiple processor system. Based on a general introduction to the whole HDTV SoC platform, a layered interrupt controller and its implementation are discussed in detail. The proposed scheme was implemented in our FPGA verification board. The results indicate that our scheme is reliable and efficient. Meanwhile, as a functional intellectual property （IP）, the interrupt controller has reusability and expandability with the layered structure.     

New Generation Processor Architecture Research

With the rapid development of microelectronics and hardware, the use ot ever faster microprocessors and new architecture must be continued to meet tomorrow‘s computing needs. New processor microarchitectures are needed to push performance further and to use higher transistor counts effectively. At the same time, aiming at different usages, the processor has been optimized in different aspects,such as high performace,low power consumption,small chip area and high security. SOC (System on chip)and SCMP (Single Chip Multi Processor) constitute the main processor system architecture.     

Smart Image Sensor with Integrated Low Complexity Image Processing for Wireless Endoscope Capsules

A smart image sensor was developed which integrates a digital pixel image sensor array with an image processor designed for wireless endoscope capsules. The camera-on-a-chip architecture and its on-chip functionality facilitate the design of the packaging and power consumption of the integrated capsule. The power reduction techniques were carried out at both the architectural and circuit level. Gray coding and power gating in the sensor array to eliminate almost 50% of the switch activity on the data bus and more than 99% of the power dissipation in each pixel at a transmitting rate of 2 frames per second. Filtering and compression in the processor reduces the data transmission by more than 2/3. A parallel fully pipelined architecture with a dedicated clock management scheme was implemented in the JPEG-LS engine to reduce the power consumption by 15.7%. The smart sensor has been implemented in 0.18 μm CMOS technology.     

ASIP Approach for Multimedia Applications Based on a Scalable VLIW DSP Architecture

The rapid development of multimedia techniques has increased the demands on multimedia processors.This paper presents a new design method to quickly design high performance processors for new multimedia applications.In this approach,a configurable processor based on the very long instruction-set word architecture is used as the basic core for designers to easily configure new processor cores for multimedia algorithm.Specific instructions designed for multimedia applications efficiently improve the performance of the target processor.Functions not implemented in the digital signal processor (DSP) core can be easily integrated into the target processor as user-defined hardware to increase the performance.Several examples are given based on the architecture.The results show that the processor performance is enhanced approximately 4 times on the H.263 codec and that the processor outperforms both DSPs and single instruction multiple data (SIMD) multimedia extension architectures by up to 8 times when computing the 2-D-IDCT.     

CT图像重建的可扩展多DSP并行计算系统结构

为提高大型工业CT的图像重建速度,通过分析卷积反投影算法的特点,提出了一种并行计算方案。设计了一种基于SPMD(单指令集,多数据流)并行处理结构的可扩展的多DSP(数字信号处理器)并行计算系统模型。通过仿真实验,确定了系统设计的重要参数——DSP的数量的选择依据。仿真结果表明,利用这种模型,可以将重建的时间从100 s量级降低到1 s量级。这样就大幅度地提高了CT图像重建的速度,扩大了大型工业CT的运用范围。     

Architecture Design of Computing Intensive SoCs

Most existing system-on-chip (SoC) architectures are for microprocessor-centric designs. They are not suitable for computing intensive SoCs, which have their own configurability, extendibility, performance, and data exchange characteristics. This paper analyzes these characteristics and gives design principles for computing intensive SoCs. Three architectures suitable for different situations are compared with selection criteria given. The architectural design of a high performance network security accelerator (HPNSA) is used to elaborate on the design techniques to fully exploit the performance potential of the architectures. A behavior-level simulation system is implemented with the C++ programming language to evaluate the HPNSA performance and to obtain the optimum system design parameters. Simulations show that this architecture provides high performance data transfer.     

ARM926EJ-S处理器中Cache一致性问题的探讨

在基于高性能ARM处理器的SoC结构中,Cache一致性问题是系统稳定运行的潜在威胁,消除该障碍是系统设计师必须解决的问题。介绍了ARM926EJ-S处理器内Cache的工作原理以及基于该处理器的典型SoC结构,重点论述了产生Cache一致性问题的原因,并提出具体的解决方法。相关测试表明该方法切实可行,能够有效避免数据不一致情况的发生,已被成功应用于课题项目中。     

降低系统芯片测试时间的芯核联合测试方案

引入扩展的模式游程(x PRL)编码技术,通过无关位的动态传播策略以提高测试数据压缩效率.在此基础上,将系统芯片的多个芯核测试集联合为单一的测试数据流,用x PRL编码技术实施压缩,提出一种可重配置的串行扫描链结构,实现多核测试模式的联合应用.对嵌入6个大的ISCAS’89基准电路的样本系统芯片（SoC）应用建议的联合测试方案.结果表明,与传统芯核测试集独立压缩与应用技术相比,该方案不仅提高了测试数据的压缩性能,而且减少了扫描测试中的冗余移位和捕获周期,从而有效降低了SoC的测试应用时间.     

3DSoC的多频测试架构设计

随着芯片集成度的提高,三维片上系统（three-dimensionalSystemonChip,3DSoC）是集成电路发展的必然趋势,其中可测性设计成为研究的重点．为了降低测试代价,提出一种符合工业实际的多频测试架构及适用于该架构的测试算法,并结合功耗对测试架构进行了仿真实验．实验结果表明,与传统的SoC相比,在同样TAM测试数据位宽数限制下,多频架构的3DSoC测试时间更短,测试代价更小．