一款多核处理器FPGA验证平台的设计与实现

高性能处理器设计日趋复杂,为了缩短验证周期,降低研制风险通常需要在流片之前进行基于现场可编程门阵列(field programmable gate-array, FPGA)原型验证平台的软硬件协同验证.随着处理器多核化的发展,FPGA原型验证平台的实现变得越来越具有挑战性.介绍了一款高性能多核微处理器FPGA验证平台的设计与实现方法,详细阐述了该FPGA验证平台采用的母板/子板总体架构、分片策略、时分复用实现技术及I/O接口实现方法.该平台具有良好的可扩展性,能够方便灵活地实现目标芯片在各种规模和配置下的FPGA验证,用于在流片前对目标芯片进行功能正确性验证和性能评估.经过该FPGA平台验证的目标芯片,首次流片返回的芯片能成功运行操作系统和各种应用程序,实现了一次流片成功的目标.最后对该FPGA验证平台的应用前景进行了分析总结.     

复杂铅铋精矿氧化熔池熔炼过程的热力学模拟

采用热力学平衡模拟方法研究复杂铅铋精矿富氧熔池熔炼过程中的元素分配行为,分析氧料比(OFR)和硫分压(pSO2)对Bi、Pb、As、Sb、Cu和Ag分配行为的影响,并对比模拟计算结果与工业数据.结果表明,该过程中OFR在6.3～6.8 kmol/t之间有利于最大化Bi、Pb、Cu和Ag在金属相中的分配,进一步增加OFR...     

基于MSHC继电保护一体化智能分区算法的研究

继电保护一体化图形拼接后电网规模不断扩大,运行方式越发复杂,继电保护整定计算不可避免地存在计算维数过高,计算量过大且求解效率过低等问题。深入研究一体化继电保护图形拼接的特点,提出了一种基于Mean Shift算法和层次聚类算法的MSHC继电保护一体化图形智能分区方法。根据割集最小、互感支路处于同一个子区域、子区域内厂站个数适中的三个厂站划分准则确定最优厂站分区方法。最后通过实际电网算例验证了该方法的快速性及有效性。     

An ultrahigh strength steel produced through deformation-induced ferrite transformation and Q&P process

In this work,DIFT technology and Q&P process were combined in order to introduce ultrafine-grained ferrite into the matrix of martensite and retained austenite to develop a new kind of advanced high strength steel,and two kinds of steels were investigated by this novel combined process.The newly designed process resulted in a sophisticated microstructure of a large amount of ferrite(about 5 m in diameter),martensite and a considerable amount of retained austenite for TRIP 780 steel.The ultimate tensile strength can reach about 1200 MPa with elongation above 16% for TRIP 780,that is much higher than the one solely treated by Q&P process.Tensile tests showed that both steels with the novel combined process achieved a good combination of strength and ductility,indicating that the new process is promising for the new generation of advanced high strength steels.     

基于表计配置的配电网可观测性分析

给出了一种配电网可观测性分析的定义，即使用典型负荷模式描述负荷变化规律，且每个负荷用户被赋予不同的表征指标，在变化的网络结构下，支路上优先配置最小数目的功率量测表计，利用量测方程求解典型负荷模式，从而获得各节点负荷，配电网可观测；有效的网络分割方法分割期望网络结构的加权树来优化表计配置，使得在量测方程可解的前提下，量测区域用户的指标均衡。算例进行了可观测分析和表计配置的测试。所提出的可观测分析思路能够折衷考虑经济性和运行需要，而表计配置也为配电网自动化改造提供一个思路。     

Elemental Partitioning Characteristics of Equilibrium Phases in Inconel 718 Alloy at 600-1100 ℃

 The optimization of heat treatment and chemical composition for Inconel 718 alloy has been investigated uninterruptedly because of its excellent mechanical properties and metallurgical workability. The species, chemical compositions and content of equilibrium phases of Inconel 718 alloy in the temperature range of 600-1100 ℃ were calculated by using thermodynamic software “Thermo-Calc” and the latest relevant datebase of Ni-base superalloys. A concept of elemental partitioning fraction was used to study the partitioning characteristics of alloying elements in each equilibrium phase at different temperatures, such as Ni, Cr, Fe, Nb, Mo, Al, Ti and C, and some calculation results were confirmed under a scanning transmission electron microscope (STEM). The results showed that the elemental partitioning characteristics with the change of temperature revealed the selective partitioning characteristic of alloying elements in equilibrium phases at different temperatures, such as Nb was mainly distributed in δ and γ′ phase, C in carbides, Al and Ti in γ′ phase and Cr, Mo in Laves phase. At the same time, the effect of the change of component and quantity for each precipitated phase on matrix phase can be helpfully understood, which provided a theoretic foundation to optimize the chemical composition and heat treatment in different environments for Inconel 718 alloy.     

Implementation of AVS Jizhun decoder with HW/SW partitioning on a coarse-grained reconfigurable multimedia system

In this paper,a TPP(Task-based Parallelization and Pipelining)scheme is proposed to implement AVS(Audio Video coding Standard)video decoding algorithm on REMUS(REconfigurable MUltimedia System),which is a coarse-grained reconfigurable multimedia system.An AVS decoder has been implemented with the consideration of HW/SW optimized partitioning.Several parallel techniques,such as MB(Macro-Block)-based parallel and block-based parallel techniques,and several pipeline techniques,such as MB level pipeline and block level pipeline techniques are adopted by hardware implementation,for performance improvement of the AVS decoder.Also,most computation-intensive tasks in AVS video standards,such as MC(Motion Compensation),IP(Intra Prediction),IDCT(Inverse Discrete Cosine Transform),REC(REConstruct)and DF(Deblocking Filter),are performed in the two RPUs(Reconfigurable Processing Units),which are the major computing engines of REMUS.Owing to the proposed scheme,the decoder introduced here can support AVS JP(Jizhun Profile)1920×1088@39fps streams when exploiting a 200 MHz working frequency.     

一种HEVC帧内预测快速算法

HEVC作为新一代的视频编码标准,比现有H.264标准的压缩效率提高近一倍,但其存在复杂度较高的问题。为此,针对HEVC中帧内预测最耗时的模块,即编码单元块划分模块和帧内预测模式选择模块,提出一种适合HEVC帧内预测的快速算法。该算法将率失真(RD)代价作为阈值参数,利用候选模式集中预测模式被选中概率快速递减的规律,基于RD代价进行帧内预测块划分和帧内预测模式选择。实验结果表明,该算法在相同编码质量条件下可减少59%的HM10.0帧内预测模块复杂度,相应比特率的增加幅度小于1.34%。     

一种新的改进精细直接积分法

针对结构动力方程转化为状态空间方程后矩阵维数增加而导致计算量增大的问题,考虑状态空间方程中所含外部荷载的特点,提出了一种新的改进精细直接积分法.给出了利用梯形公式、复化梯形公式、辛普生公式、复化辛普生公式、科特斯公式、高斯公式计算杜哈姆积分时的计算格式,分析了不同计算格式下的计算精度和计算效率.数值算例表明本文改进方法的正确性.     

智能分区PID控制算法在电动缸伺服系统中的研究

针对电动缸伺服系统中的非线性环节,采用带线性补偿的分区二级前馈PID控制算法;首先建立电动缸伺服系统的仿真模型,并采用单组控制参数的二级前馈PID控制算法,通过仿真发现系统存在着抖动、精度较低的问题;然后提出了具有线性补偿的分区二级前馈PID控制算法,改进了相应的控制器结构并实现控制器的数字离散化;最后通过线性补偿的方法整定实际系统在各分区的控制参数,计算出相应的控制量;对比分析实际系统的稳态误差,发现智能分区PID控制器在电动缸伺服系统中能够取得更好的控制效果.