An investigation of the performance portability of OpenCL

This paper reports on the development of an MPI/OpenCL implementation of LU, an application-level benchmark from the NAS Parallel Benchmark Suite. An account of the design decisions addressed during the development of this code is presented, demonstrating the importance of memory arrangement and work-item/work-group distribution strategies when applications are deployed on different device types. The resulting platform-agnostic, single source application is benchmarked on a number of different architectures, and is shown to be 1.3–1.5× slower than native FORTRAN 77 or CUDA implementations on a single node and 1.3–3.1× slower on multiple nodes. We also explore the potential performance gains of OpenCL’s device fissioning capability, demonstrating up to a 3× speed-up over our original OpenCL implementation.     

基于GPU的AES算法实现

近几年图形处理器GPU的通用计算能力发展迅速,现在已经发展成为具有巨大并行运算能力的多核处理器,而CUDA架构的推出突破了传统GPU开发方式的束缚,把GPU巨大的通用计算能力解放了出来.本文利用GPU来加速AES算法,即利用GPU作为CPU的协处理器,将AES算法在GPU上实现,以提高计算的吞吐量.最后在GPU和CPU...     

基于GPU的GPS信号捕获算法设计与实现

文章对GPS信号的捕获在GPU和CPU架构下的平台进行研究。GPS信号的捕获是卫星导航接收机关键环节之一,其实现对硬件资源和处理时间均有较高的要求。GPU具有较高的可编程能力和大量并行处理单元,并在大规模的并行计算工作中使用,其并行处理能力可以为GPS信号捕获的实现提供可靠保证,同时GPU可编程的特点提高了GPS信号捕获的灵活性和可重构性。文章提出了基于GPU的GPS信号捕获实现结构,并通过仿真验证了该结构的可靠性和有效性。     

Efficient modeling and analysis of energy consumption for 3D graphics rendering

This paper proposes new models of GPU energy consumption from the perspectives of hardware architects and graphics programmers by performing an architecture-independent analysis of the classical graphics rendering pipeline which is still in widespread use today. The detailed analysis includes graphics rendering workload, memory bandwidth and energy consumption . Although the models are derived from classical 3D pipeline, they are extensible to programmable pipelines. There are many factors that affect the performance and energy consumption of 3D graphics rendering, such as the number of textures, vertex sharing, level of details, and rendering algorithms. The proposed models are validated by our simulation study and used to guide our 3D graphics hardware design and 3D graphics programming in order to optimize performance and energy consumption of our GPU prototypes which have been successfully fabricated in SMIC 0.13 μm CMOS technology.     

国产智能机芯片发展现状

简要介绍了国内安卓智能手机和智能平板芯片发展现状,分析了国产智能机芯片在CPU性能、GPU能力、功耗、制程工艺等方面的技术指标以及与高通等国际领先智能机芯片厂商之间存在的差距.华为海思、珠海全志、广东新岸线等公司依托自身的特点和技术积累,针对市场的各种需求,占据了一席之地.面对更为残酷的竞争和创新的压力,中国芯还有很长的路要走.     

一种红外探测器效应的实时模拟方法

文中剖析了Ogre渲染引擎的工作原理,描述了基于GPU的后处理技术,利用Ogre渲染引擎通过GPU实现了二维快速傅里叶变换,添加了探测器成像系统调制传递函数(MTF),实现了系统线性噪声和随机噪声的添加,模拟了实时三维红外场景中的探测器效应.     

基于CPU＋GPU异构计算的编程方法研究

基于CPU＋GPU的异构计算系统是在传统计算机系统中加入GPU作为加速部件并配合CPU共同承担计算任务的新型系统,相比于传统的单纯以CPU作为计算部件的同构计算系统,异构系统优势明显。分析了基于CPU＋GPU异构计算模式程序开发面临的主要困难,重点研究了当前可用的主要解决途径和研究方向,并总结了当前各种编程方法的适用场合和各自的优缺点。     

EDGE网络小区重选时延及恢复研究

EDGE网络优化过程中,有些指标对网络的整体性能起着关键性的作用,小区重选就是其中一个,为了解决小区重选过多的问题,我们进行了专项的优化研究。     

基于GPGPU的离散数据挖掘研究

为了提高数据挖掘的效率,提出了一种基于GPU加速的离散数据挖掘方法,并且详细论述了实现的过程以及关键技术。通过实验表明,相对于传统方法该方法具有较高的计算效率和准确性,是实现数据挖掘的实用方法。