Performance and scalability of Fourier domain optical coherence tomography acceleration using graphics processing units

Fourier domain optical coherence tomography (FD-OCT) provides faster line rates, better resolution, and higher sensitivity for noninvasive, in vivo biomedical imaging compared to traditional time domain OCT (TD-OCT). However, because the signal processing for FD-OCT is computationally intensive, real-time FD-OCT applications demand powerful computing platforms to deliver acceptable performance. Graphics processing units (GPUs) have been used as coprocessors to accelerate FD-OCT by leveraging their relatively simple programming model to exploit thread-level parallelism. Unfortunately, GPUs do not "share" memory with their host processors, requiring additional data transfers between the GPU and CPU. In this paper, we implement a complete FD-OCT accelerator on a consumer grade GPU/CPU platform. Our data acquisition system uses spectrometer-based detection and a dual-arm interferometer topology with numerical dispersion compensation for retinal imaging. We demonstrate that the maximum line rate is dictated by the memory transfer time and not the processing time due to the GPU platform's memory model. Finally, we discuss how the performance trends of GPU-based accelerators compare to the expected future requirements of FD-OCT data rates.     

管道射线底片图像图形计算机处理技术

管道是一种重要的运输载体,检测其使用状况并进行分析决策具有重要的意义.射线检测可以透过管道及其包覆层成像,是一种可行的检测手段.传统的射线照相检测方法依靠人工对底片进行评读,准确性和效率难以保证.为此,我们提出了用于管道射线底片检测的图像图形计算机处理技术,并完成了相应的硬件和软件的系统设计.     

Parallel particle swarm optimization on a graphics processing unit with application to trajectory optimization

In order to reduce the computational time, a fully parallel implementation of the particle swarm optimization (PSO) algorithm on a graphics processing unit (GPU) is presented. Instead of being executed on the central processing unit (CPU) sequentially, PSO is executed in parallel via the GPU on the compute unified device architecture (CUDA) platform. The processes of fitness evaluation, updating of velocity and position of all particles are all parallelized and introduced in detail. Comparative studies on the optimization of four benchmark functions and a trajectory optimization problem are conducted by running PSO on the GPU (GPU-PSO) and CPU (CPU-PSO). The impact of design dimension, number of particles and size of the thread-block in the GPU and their interactions on the computational time is investigated. The results show that the computational time of the developed GPU-PSO is much shorter than that of CPU-PSO, with comparable accuracy, which demonstrates the remarkable speed-up capability of GPU-PSO.     

Convergence of curved shell elements based on assumed covariant strain interpolations

A C⁰ 9-node shell element based on assumed interpolations of covariant strain components defined with respect to the element natural co-ordinate system has recently been proposed. In this formulation, the covariant strains are obtained directly from the Cartesian strains by tensor transformation without any need to compute laminar co-ordinate based strains. In the present work, the interpolated covariant strains used in this element are analysed to determine their satisfaction of the basic requirements for successful strain interpolation. These basic requirements are stated as invariance to rigid body motions and ability to represent constant and linear strain states. In the finite element formulation, the weak form of momentum balance is expressed in terms of covariant strains and contravariant stresses. The corresponding elasticity tensor is a function of the components of the metric tensor associated with the element natural co-ordinate system. The invariance properties of the metric tensor in the context of the finite element approximation are also discussed.     

Calculation method for computer-generated holograms with cylindrical basic object light by using a graphics processing unit

It takes an enormous amount of time to calculate a computer-generated hologram (CGH). A fast calculation method for a CGH using precalculated object light has been proposed in which the light waves of an arbitrary object are calculated using transform calculations of the precalculated object light. However, this method requires a huge amount of memory. This paper proposes the use of a method that uses a cylindrical basic object light to reduce the memory requirement. Furthermore, it is accelerated by using a graphics processing unit (GPU). Experimental results show that the calculation speed on a GPU is about 65 times faster than that on a CPU.     

用于中央空调的低成本双机热备冗余控制系统的研制

针对需使用双机热备冗余控制系统实现高可靠控制要求的场所,通过控制器的合理选型和软件编程的手段,研制一种低成本双机热备冗余控制系统。将该系统应用于一个由4台中央空调组成的冗余控制系统,可以取得良好的效果,且该控制系统中控制器成本不足目前市场上实现双机热备冗余控制的控制器的十分之一。     

Use of systems with central feed and counterflow in thermodiffusion units to clean fluids

A determination is made of the parameters necessary to evaluate the efficiency of different systems for cleaning fluids in thermodiffusion units.Translated from Inzhenerno-Fizicheskii Zhurnal, Vol. 53, No. 3, pp. 416–420, September, 1987.     

A novel three‐dimensional contact finite element based on smooth pressure interpolations

This article proposes a new three‐dimensional contact finite element which employs continuous and weakly coupled pressure interpolations on each of the interacting boundaries. The resulting formulation circumvents the geometric bias of one‐pass methods, as well as the surface locking of traditional two‐pass node‐on‐surface methods. A Lagrange multiplier implementation of the proposed element is validated for frictionless quasi‐static contact by a series of numerical simulations. Published in 2001 by John Wiley & Sons, Ltd.     

Transverse load and orientation measurement with multicore fiber Bragg gratings

We demonstrate the sensitivity of Bragg gratings in a multicore fiber to transverse load. The Bragg peaks are split because of stress-induced birefringence, the magnitude of which depends upon the load and grating position relative to the load axis. Experiments show that a set of gratings in a four-core fiber can measure a load axis angle to +/- 5 degrees and a load magnitude to +/- 15 N m(-1) up to 2500 N m(-1). We consider alternative designs of multicore fiber for optimal load sensing and compare experimental and modeled data.     

同步造型技术在工程图学教学中的应用研究

同步造型技术是一种新兴的三维造型技术,论文研究了如何将该技术应用于制图教学。通过分析同步造型技术与工程图学的相关内容,得到该技术在制图教学中的应用方式与方法。结果表明:同步造型的方向盘技术是一种非常灵活的造型工具,可用于截交线及切割体的造型与编辑,也可用于基本特征与表面的平移旋转。利用同步技术草图区域识别,造型更加灵活,对于读图—造型—投影教学与练习,可以显著提高学生的学习兴趣。     

Autonomy of foreign R&D units in an emerging market: An information processing perspective

The

Statistical study of fluctuation of gas flow rate in caps in fluidized-bed processing units

Results are presented from correlational and spectral analyses of gas flow rate fluctuations in caps in fluidized-bed processing units with bed depths up to 0.8 m.Translated from Inzhenerno-Fizicheskii Zhurnal, Vol. 43, No. 3, pp. 357–360, September, 1982.     

Bitapered fiber coupling characteristics between single-mode single-core fiber and single-mode multicore fiber

By splicing and tapering at the fusion point of one-core single-mode fiber and three- or four-core single-mode fiber, an effective bitapered fiber coupling technique is implemented. Based on the beam propagation method, the bitapered coupling characteristics between the one-core fiber and the multicore single-mode fiber are simulated and analyzed. The theoretical prediction is confirmed by the experimental results, and the difference between the simulation and the experimental results is also discussed.     

河水供冷中央空调风机盘管的干工况设计与运行分析

基于对全国首例河水自然冷源中央空调系统的案例研究，对该中央空调系统风机盘管的设计与技术创新过程及运行效果进行了理论分析和实践总结，利用盘管冷量换算方程对其风机盘管进行了制冷量估算，并建议自然冷源空调系统的风机盘管应按干工况设计。     

Atmospheric wavefront phase recovery by use of specialized hardware: graphical processing units and field-programmable gate arrays

To achieve the wavefront phase-recovery stage of an adaptive-optics loop computed in real time for 32 x 32 or a greater number of subpupils in a Shack-Hartmann sensor, we present here, for what is to our knowledge the first time, preliminary results that we obtained by using innovative techniques: graphical processing units (GPUs) and field-programmable gate arrays (FPGAs). We describe the stream-computing paradigm of the GPU and adapt a zonal algorithm to take advantage of the parallel computational power of the GPU. We also present preliminary results we obtained by use of FPGAs on the same algorithm. GPUs have proved to be a promising technique, but FPGAs are already a feasible solution to adaptive-optics real-time requirements, even for a large number of subpupils.     

Magnetic multicore nanoparticles for hyperthermia--influence of particle immobilization in tumour tissue on magnetic properties

When using magnetic nanoparticles as a heating source for magnetic particle hyperthermia it is of particular interest to know if the particles are free to move in the interstitial fluid or are fixed to the tumour tissue. The immobilization state determines the relaxation behaviour of the administered particles and thus their specific heating power. To investigate this behaviour, magnetic multicore nanoparticles were injected into experimentally grown tumours in mice and magnetic heating treatment was carried out in an alternating magnetic field (H = 25 kA m(-1), f = 400 kHz). The tested particles were well suited for magnetic heating treatment as they heated a tumour of about 100 mg by about 22 K within the first 60 s. Upon sacrifice, histological tumour examination showed that the particles form spots in the tissue with a mainly homogeneous particle distribution in these spots. The magnetic ex vivo characterization of the removed tumour tissue gave clear evidence for the immobilization of the particles in the tumour tissue because the particles in the tumour showed the same magnetic behaviour as immobilized particles. Therefore, the particles are not able to rotate and a temperature increase due to Brown relaxation can be neglected. To accurately estimate the heating potential of magnetic materials, the respective environments influencing the nanoparticle mobility status have to be taken into account.     

A hybrid task scheduling scheme for multicore processors based on improving the EDF algorithm

为解决多核处理器系统中的实时任务调度问题,尤其是实时任务和非实时任务的混合调度问题,在对最早截止时间优先(EDF)算法进行改进的基础上,提出多核处理器混合任务调度算法——EDF-segment算法.EDF-segment算法可以整理调度混合任务时出现的碎片,并通过对碎片的迁移、合并提高处理器的利用率,从而提高系统处理混合任务的性能.通过EDF-segment算法不但可以解决混合任务的调度问题,还可以避免使用EDF算法时造成的多核处理器利用率下降,在保证实时任务处理延迟的前提下提升多核处理器的利用率.经过理论推导和实验分析证明,EDF-segment算法可以有效地应用于多核处理器系统中.     

建立工程设计的工程图学教学模式

随着计算机技术的发展和三维设计软件的推广普及,工程设计已由二维工程图设计向直接三维设计发展.以工程设计为主线,在工程图学教学中引入三维设计的方法与思想,培养学生利用三维设计技术进行设计和表达的能力,将是工程图学课程体系改革的必然趋势.     

In-phase supermode selection in ring-type and concentric-type multicore fibers using large-mode-area single-mode fiber

We propose an all-fiber-optic supermode selection scheme based on large-mode-area single-mode fiber for multicore fiber (MCF). The supermode selection in terms of the coupling coefficient is investigated and compared for various ring-type and concentric-type MCFs. The in-phase supermode is found to have a significantly higher coupling coefficient than other supermodes--demonstrating significant and desirable supermode selection characteristics. This scheme has shown better in-phase supermode selection performance than the conventional free-space Talbot cavity. It is found to be effective in selecting the in-phase supermode for both ring-type and concentric-type MCFs and promising for all-fiber MCF lasers with high power output and good beam quality.