基于图形处理器的形态学重建系统

形态学重建是医学图像处理中非常基础和重要的操作。它根据掩膜图像的特征对标记图像反复进行膨胀操作，直到标记图像中的像素值不再变化为止。对于传统基于中央处理器（CPU）的形态学重建系统计算效率不高的问题，提出了使用图形处理器（GPU）来加速形态学重建。首先，设计了适合GPU处理的数据结构：并行堆集群；然后，基于并行堆集群，设计和实现了一套基于GPU的形态学重建系统。实验结果表明，相比传统基于CPU的形态学重建系统，基于GPU的形态学重建系统可以获取超过20倍的加速比。基于GPU的形态学重建系统展示了如何把基于复杂数据结构的软件系统高效地移植到GPU上。     

碳酸盐岩储层叠前逆时偏移及GPU/CPU异构计算方案研究

针对碳酸盐岩储层地质构造的特点,提出采用基于声波方程的叠前逆时偏移算法对其进行成像,并在偏移过程中引入优化差分系数和完全匹配层(PML)边界条件来提高波场的数值模拟精度,同时利用GPU/CPU异构并行加速技术对算法进行优化,从而显著提升偏移的计算效率。模型测试表明,与传统差分系数相比,同阶的优化差分系数具有更高精度,压制频散效果明显;PML边界条件能够有效的吸收边界反射,减少边界反射对有效波场的干扰;叠前逆时偏移方法可有效识别碳酸盐岩模型中的小尺寸孔洞和裂缝,归为准确,刻画清晰,对碳酸盐岩储层成像具有显著优势;GPU/CPU异构并行加速技术可明显提高偏移的计算效率,与传统CPU算法相比,加速比可达60倍,对于实际推广应用具有重要意义。     

Voronoi图栅格生成算法GPU并行实现

针对矢量法生成Voronoi图计算与存储复杂的缺点,重点分析研究了Voronoi图的栅格生成方法。对不同的栅格生成算法的复杂性和效率进行了比较分析,并针对以往方法速度较慢的问题,提出一种CUDA平台下GPU并行栅格扫描的方法。该方法利用GPU的多线程特性,将各个栅格的计算分散到不同的线程中并行处理。相比其他栅格生成方法,该方法不需要考虑栅格的规模,能够以几乎线性的时间完成Voronoi图的生成,极大地提高了生成速度。     

基于GPU通用计算平台的乐谱自动识别系统设计

在GPU通用计算平台上实现了一个钢琴独奏乐曲的乐谱识别系统,它读取WAV格式音频文件,利用GPU通用计算技术加速自相关函数算法来实现音高的识别,并综合考虑短时能量和基音周期的变化进行节拍划分。通过实际测试,验证了该乐谱识别系统的准确性,并证明了GPU并行计算对系统计算效率提升的效果：将计算时间减少到传统CPU计算时间的16%左右。     

基于GPU 的PCM/FM 信号非相干鉴频解调算法

面向未来任务日益多样化,试验环境日趋复杂化,传统基于FPGA 的脉冲编码调制/调频(pulse code modulation/frequency modulation,PCM/FM)遥测系统存在软硬件紧耦合、研发周期长、升级维护困难等缺点,无法 满足未来遥测系统大规模部署对弹性、灵活和敏捷的需求。针对以上问题,设计基于GPU 的PCM/FM 信号非相干 鉴频解调实现方法。根据算法原理和GPU 并行方法设计出基于GPU 的并行解调实现方法,分别从并行数字下变频、 并行FIR 滤波和并行差分鉴频3 部分分析具体模块的并行化实现方法。实验结果表明：在码速率为10 Mbps、每处 理1 s 数据的条件下,基于GPU 的非相干鉴频过程消耗的时间约为426.867 ms,满足解调的实时性要求;解调增益 稍优于传统基于FPGA 的PCM/FM 遥测基带,有约0.1 dB 的解调增益。     

Towards a hydrodynamic modelling framework appropriate for applications in urban flood assessment and mitigation using heterogeneous computing

We present a new hydrodynamic modelling framework capable of fully exploiting modern graphics and central processing units (GPUs and CPUs) from any of the mainstream vendors, to be used in the design and assessment of sustainable drainage systems. A finite-volume Godunov-type scheme is combined with the HLLC Riemann solver to create a robust numerical model which correctly addresses wetting and drying and transient flow conditions, and is suitable for application to a wide range of flood simulations. The software is tested with a three day flood event in Carlisle during 2005, at resolutions from 25 m to 2 m. Run-times are significantly reduced without compromising numerical accuracy. Excellent agreement is found between the simulation results and a comprehensive post-event survey. Changes in sensitivity to Manning's n are examined at different resolutions, with changes to the floodplain found to have little influence at 2 m resolution.     

GPU集群能耗优化控制模型研究

随着大数据技术的发展,GPU集群作为一种高效的并行系统被应用到大规模数据实时计算中.能量是实时计算时重要的资源,GPU集群的能耗优化及实时消减成为一个具有挑战性的问题.从集群全局角度引入模型预测控制策略,并建立闭环反馈机制的多输入多输出控制器.通过调整计算频率和改变活跃流多处理器来改变能耗状态,利用反馈和滚动优化机制完成对未来的控制预判,实现消减冗余能耗的目标.实验表明:控制模型的精度和节能效果优于基准模型,而且具有较好的稳定性,适合应用到大规模数据实时计算中.     

Multi-product continuous plant scheduling: combination of decomposition,genetic algorithm,and constructive heuristic

We propose a polylithic method for medium-term scheduling of a large-scale industrial plant operating in a continuous mode. The method combines a decomposition approach, a genetic algorithm (GA) and a constructive MILP-based heuristic. In the decomposition, decisions are made at two levels, using the rolling horizon approach. At the upper level, a reduced set of products and the time period is chosen to be considered in the lower level. At the lower level, a short-term scheduling MILP-model with event-based representation is used. A heuristic solution to the lower level problem is found using a constructive Moving Window heuristic guided by a genetic algorithm. The GA is applied for finding efficient utilisation of critical units in the lower level problem. For solving the one unit scheduling problem, a parallel dynamic programming algorithm is proposed. Implementation of the dynamic programming algorithm for a graphics processing unit (GPU) is incorporated in the GA for improving its performance. The experimental study of the proposed method on a real case of a large-scale plant shows a significant improvement of the solution quality and the solving time comparing to the pure decomposition algorithm proposed in the earlier study, and confirmed suitability of the proposed approach for the real-life production scheduling. In particular, the reduction of the number of changeovers and their duration in the obtained solution as well as the CPU time of solving the problem was about 60% using the new approach.     

GPU加速MOC输运计算性能分析研究

特征线方法（MOC）在求解堆芯规模中子输运方程时面临计算时间长的问题，加速和并行算法是目前研究的热点。基于MOC在特征线和能群层面的并行特性，采用统一计算设备构架（CUDA）编程规范，实现了基于图形处理器（GPU）的并行二维MOC算法。测试了菱形差分和步特征线法分别在双精度、混合精度及单精度浮点运算下的计算精度、效率及GPU加速效果。采用性能分析工具对GPU程序性能进行了分析，识别了程序性能瓶颈。结果表明：菱形差分和步特征线法在不同浮点运算精度下均表现出良好的计算精度；相比于CPU单线程计算，GPU加速效果在双精度和单精度情况下分别达到35倍和100倍以上。     

Location Related Signals with Satellite Image Fusion Method Using Visual Image Integration Method

Investigations were performed on a group utilizing (General Purpose Unit) GPU and executions were evaluated for the utilization of the created parallel usages to process satellite pictures from satellite Landsat7.The usage on a realistic group gives execution change from 2 to 18 times. The nature of the considered techniques was assessed by relative dimensionless global error in synthesis (ERGAS) and Quality Without Reference (QNR) measurements. The outcomes demonstrate execution picks ups and holding of value with the bunch of GPU contrasted with the outcomes and different analysts for a CPU and single GPU. The errand of upgrading the view of a scene by combining data caught from various picture sensors is usually known as multisensor picture combination. This paper displays a territory based picture combination calculation to consolidate SAR (Synthetic Aperture Radar) and optical pictures. The co-enlistment of the two images is first led utilizing the proposed enrollment method prior to picture combination. The paper displays a parallel execution of existing picture combination techniques on a graphical group. Parallel executions of techniques in view of discrete wavelet changes are created. Division into dynamic and motionless regions is then executed on the SAR surface picture for particular injection of the SAR picture into panchromatic (PAN) picture. An integrated image in view of these two pictures is produced by the novel region based combination plot, which forces diverse combination rules for each fragmented region. At long last, this picture is melded into a multispectral(MS) picture through the half breed skillet honing technique proposed in past research. Exploratory outcomes exhibit that the proposed strategy demonstrates preferred execution over different fusion algorithms and can possibly be connected to the multisensory combination of SAR and optical pictures.