基于GPU的位并行多模式串匹配研究

图形处理器(GPU)具有较强的单一运算能力及高度并行的体系结构。根据上述特点,选择基于位并行技术的多模式串匹配算法M-BNDM,将其移植到GPU上加以实现和优化。通过对需要处理的数据进行预处理,将串匹配的过程简化为更适合CUDA计算数据的位操作。对基于CUDA架构的并行串匹配算法的性能影响因子进行分析。实验结果表明,与同等CPU算法相比,该算法能够获得约十几倍的加速比。     

基于Tesla平台的快速反投影运算

反投影运算是锥束CT图像重建算法中运算量最大,最耗时的部分,是制约重建速度的瓶颈。为此,在计算统一设备架构模型下,应用体素驱动法实现基于Tesla平台的反投影(BP)并行运算,并对BP运算上的访存和数学指令进行优化。实际CT数据的重建结果表明,该方法的运算速度是CPU串行程序的198倍,效率高且易于实现。     

基于CUDA的3G视频清晰度评估方法

针对传统视频清晰度评估方法实时性较差的问题,利用统一计算架构(CUDA)高度并行性的特点,提出一种基于CUDA的3G视频清晰度评估方法。实验结果表明,与传统的视频清晰度评估方法相比,该方法能在保证准确评估视频清晰度的同时缩短算法的执行时间,计算速度约是传统串行算法的30倍。     

On optimization of finite-difference time-domain (FDTD) computation on heterogeneous and GPU clusters

A model for the computational cost of the finite-difference time-domain (FDTD) method irrespective of implementation details or the application domain is given. The model is used to formalize the problem of optimal distribution of computational load to an arbitrary set of resources across a heterogeneous cluster. We show that the problem can be formulated as a minimax optimization problem and derive analytic lower bounds for the computational cost. The work provides insight into optimal design of FDTD parallel software. Our formulation of the load distribution problem takes simultaneously into account the computational and communication costs. We demonstrate that significant performance gains, as much as 75%, can be achieved by proper load distribution.     

Interactive Fibre Structure Visualization of the Heart

The heart consists of densely packed muscle fibres. The orientation of these fibres can be acquired by using Diffusion Tensor Imaging (DTI) ex vivo. A good way to visualize the fibre structure in a cross section of the heart is by showing short line segments originating from the cross section and aligned with the local direction of the fibres. If the line segments are placed dense enough, one can see how the fibre orientations change. However, generation of the line segments takes time and thus the user has to wait for new geometry to be generated when the plane defining the cross section is changed. We present a new direct rendering method for the visualization of the 3D vector field in a 2D user‐definable cross section of a heart. On the intersection of the plane with the vector field, the full 3D vectors are rendered as 3D line segments with a local ray casting approach. No preprocessing of the data is needed and no geometry is generated. This technique allows a fast inspection of the data to identify interesting areas where further analysis is necessary (e.g. quantification or generation of streamlines). We also show how the technique is generalized to other glyph shapes than line segments by implementing ellipsoids.     

基于GPU的遥感影像数据融合IHS变换算法

提出基于图形处理单元（GPU）的遥感影像IHS融合算法,利用图形硬件的可编程渲染器和其处理数据的并行性,把IHS的正反变换映射到GPU中进行计算。应用RTT和MRT技术实现IHS正反变换中3个分量的并行渲染输出,加速计算过程。实验结果表明,在数据量较大时,该算法的处理速度比基于CPU的算法速度更快。     

一种基于GPU的高精度体系结构级功耗模型

随着硬件功能的不断丰富和软件开发环境的逐渐成熟,GPU开始被应用于通用计算领域,协助CPU加速程序运行。为了追求高性能,GPU往往包含成百上千个核心运算单元,高密度的计算资源使得其性能远高于CPU的同时功耗也高于CPU,功耗问题已经成为制约GPU发展的重要问题之一。在深入研究Fermi GPU架构的基础上,提出一种高精度的体系结构级功耗模型,该模型首先计算不同native指令及每次访问存储器消耗的功耗;然后根据应用在硬件上的执行指令和采样工具获得采样结果,分析预测其功耗;最后通过13个基准测试应用对实际测试与功耗模型测试结果进行对比分析,该模型的预测精度可达90%左右。     

移动智能终端的SIFT特征检测并行算法

特征的检测和匹配在计算机视觉应用中是一个重要的组成部分,如图像匹配、物体识别和视频跟踪等。SIFT算法以其尺度不变性和旋转不变性在图像配准领域得到了广泛应用。传统的SIFT算法效率低,因此提出一种在移动智能终端上实现的高效方法。在Android平台利用OpenCL框架实现了移动智能终端的SIFT算法,通过计算任务的重新分配,优化SIFT算法在移动GPU上的并行实现。实验结果表明,移动平台的SIFT算法充分利用了GPU并行计算能力,大大提高了SIFT算法的执行效率,实现了高效的特征检测。     

真实感眩光效果实时绘制

针对现有眩光效果绘制方法的真实感和速度问题,提出一种基于GPU的真实感眩光效果绘制方法.首先根据光圈和镜头生成带有随机镜头噪声的二维衍射光栅图像;其次考虑夫琅禾费和菲涅耳2种不同的衍射效果,利用预存算法系数的快速傅里叶变换模拟衍射效果的光学过程,并通过衍射效果的光谱模型实现真实感绘制,同时利用2个独立的一维高斯卷积核加速实现bloom效果;再通过随机小角度旋转和混合操作进行真实感增强;最后采用实时光线跟踪渲染框架,在三维场景中实现了真实感眩光效果的实时绘制.该方法的主要步骤采用CUDA实现,充分利用了GPU强大的并行计算能力并兼顾考虑存储器优化策略.实验结果表明,文中方法绘制结果具有较强的真实感和实时性.     

GPU accelerated tensor contractions in the plaquette renormalization scheme

We use the graphical processing unit (GPU) to accelerate the tensor contractions, which is the most time consuming operations in the variational method based on the plaquette renormalized states. Using a frustrated Heisenberg J₁–J₂ model on a square lattice as an example, we implement the algorithm based on the compute unified device architecture (CUDA). For a single plaquette contraction with the bond dimensions C = 3 of each rank of the tensor, results are obtained 25 times faster on GPU than on a current CPU core. This makes it possible to simulate systems with the size 8 × 8 and larger, which are extremely time consuming on a single CPU. This technology successfully relieves the computing time dependence with C, while in the CPU serial computation, the total required time scales both with C and the system size.