Data processing center of RadioAstron space VLBI project

In this paper, questions on development, implementation, and operation of RadioAstron project Data Processing Center (DPC) are reviewed. The main components of the dedicated DPC are the computer complex with 1 TFlops/s performance, storage with memory capacity of approximately 10 PB, the network infrastructure, and the corresponding communication channels. Performance enhancement methods and resolution of information storage, archiving, and process problems of space VLBI high-speed digital data flows are analyzed. It is shown that successful operation of DPC is mainly provided by optimal organization of computer system structure, storage, and networking transmission. Some of the important key features of RadioAstron project DPC and its comparative differences from the standard VLBI procedures are considered.     

Using parallel computing for the display and simulation of the space debris environment

Parallelism is becoming the leading paradigm in today’s computer architectures. In order to take full advantage of this development, new algorithms have to be specifically designed for parallel execution while many old ones have to be upgraded accordingly. One field in which parallel computing has been firmly established for many years is computer graphics. Calculating and displaying three-dimensional computer generated imagery in real time requires complex numerical operations to be performed at high speed on a large number of objects. Since most of these objects can be processed independently, parallel computing is applicable in this field. Modern graphics processing units (GPUs) have become capable of performing millions of matrix and vector operations per second on multiple objects simultaneously.     

Semi-analytical investigations of the long term evolution of the eccentricity of Galileo and GPS-like orbits

This paper aims at investigating the stability over 150 years of a very large number of trajectories in the Medium Earth Orbit (MEO) region, near the orbits devoted to radionavigation such as the Global Navigation Satellite Systems (GNSS like GPS, Glonass, Galileo, COMPASS).     

An efficient large-scale mesh deformation method based on MPI/OpenMP hybrid parallel radial basis function interpolation

An efficient MPI/OpenMP hybrid parallel Radial Basis Function (RBF) strategy for both continuous and discontinuous large-scale mesh deformation is proposed to reduce the computational cost and memory consumption. Unlike the conventional parallel methods in which all processors use the same surface displacement and implement the same operation, the present method employs different surface points sets and influence radius for each volume point movement, accompanied with efficient geometry searching strategy. The deformed surface points, also called Control Points (CPs), are stored in each processor. The displacement of spatial points is interpolated by using only 20–50 nearest control points, and the local influence radius is set to 5–20 times the maximum displacement of control points. To shorten the searching time for the nearest control point clouds, an Alternating Digital Tree (ADT) algorithm for 3D complex geometry is designed based on an iterative bisection technique. Besides, an MPI/OpenMP hybrid parallel approach is developed to reduce the memory cost in each High-Performance Computing (HPC) node for large-scale applications. Three 3D cases, including the ONERA-M6 wing and a commercial transport airplane standard model with up to 2.5 billion hybrid elements, are used to test the present mesh deformation method. The robustness and high parallel efficiency are demonstrated by a wing deflection case with a maximum bending angle of 45° and more than 80% parallel efficiency with 1024 MPI processors. In addition, the availability for both continuous and discontinuous surface deformation is verified by interpolating the projecting displacement with opposite directions surface points to the spatial points.     

Asymptotically Optimal Simulation Budget Allocation under Fixed Confidence Level by Ordinal Optimization

Ordinal optimization concentrates on isolating a subset of good designs with high probability and reduces the required simulation time dramatically for discrete event simulation. To obtain the same probability level,we may optimally allocate our computing budget among different designs,instead of equally simulating all different designs. In this paper we present an effective approach to optimally allocate computing budget for discrete-event system simulation. While ordinal optimization can dramatically reduce the computation cost, our approach can further reduce the already-low cost.     

风扇叶片脱落机匣包容性仿真并行计算一致性研究

风扇叶片脱落并行计算结果的一致性非常重要。在共享内存并行(SMP)模式下,由于计算随机误差和误差累积现象的存在,计算结果可能不一致。针对该问题,对某型大涵道比涡扇发动机简化的三叶片模型进行并行仿真计算,分析造成计算结果不一致的误差来源,提出四种控制策略,研究表明,通过计算方法的改进和计算平台的选择可以有效避免误差累积现象,提高并行计算精度。     

星载软件在轨重配置中断处理机制研究

文章主要介绍星载处理器软件在轨重配置中断处理机制。首先说明软件在轨重配置功能的基本处理流程，接着重点分析了在轨重配置过程中两类中断处理机制，并给出了中断处理在轨重配置的实现方法。     

一种应用云计算技术的航天器综合测试方法

首先介绍了目前国内外航天器综合测试系统的现状,指出其资源利用率低、测试成本高的不足;然后针对这些不足,结合未来航天器综合测试业务新需求,提出了一种应用云计算平台的航天器综合测试方法,给出了该方法的综合测试云架构,分析了其在资源利用率、可靠性、可扩展性等方面的技术优势;最后给出航天器综合测试云系统的实施方案,供今后我国航天器测试系统建设参考。     

方向交替隐含法并行计算的一种模型

介绍了流体力学计算中运用的方向交替隐含法和求解三对角方程组的追赶法，提出了利用方向交替法并行求解流体力学问题的一种模型。该模型将计算中的通信复杂度降到了很低的情况。给出了该模型的节点机互连结构及其数据的划分及存储方式，确定了共享数据和其主、从节点，讨论了共享数据的交换方法，并给出了并行计算的实现细节。     

二进制乘法器的面—时平方复杂性研究

讨论了n位二进制整数乘法下界面－时平方复杂性问题，给出了一种树型布局的乘法器网络模型，并分析了它的AT~2复杂性