The Construction of Large Scale Reconfigurable Parallel Computing Systems (The Architecture of the SC320)

1997 ◽  
Vol 08 (03) ◽  
pp. 347-361 ◽  
Author(s):  
Burkhard Monien ◽  
Ralf Diekmann ◽  
Reinhard Lüling
Keyword(s):  
Communication Networks ◽  
Large Scale ◽  
Design Principle ◽  
Massively Parallel ◽  
Regular Graphs ◽  
Computing Systems ◽  
Routing Switches ◽  
Time Requirements ◽  
User Access ◽  
Static Routing

Reconfigurable communication networks for massively parallel multiprocessor systems offer the possibility to realize a number of application demands like special communication patterns or real-time requirements. This paper presents the design principle of a reconfigurable network which is able to realize any graph of maximal degree four. The architecture is based on a special multistage Clos network, constructed out of a number of static routing switches of equal size. Upper bounds on the cut size of 4-regular graphs, if split into a number of clusters, allow minimizing the number of switches and connections while still offering the desired reconfiguration capabilities as well as large scalability and flexible multi-user access. Efficient algorithms configuring the architecture are based on an old result by Petersen27 about the decomposition of regular graphs. The concept presented here is the basis for the Parsytec SC series of reconfigurable MPP-systems. The currently largest realization with 320 processors is presented in greater detail.

scholarly journals Acoustoelectronic nanotweezers enable dynamic and large-scale control of nanomaterials

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Peiran Zhang ◽  
Joseph Rufo ◽  
Chuyi Chen ◽  
Jianping Xia ◽  
Zhenhua Tian ◽  
...  
Keyword(s):  
Large Scale ◽  
Condensed Matter ◽  
Dynamic Control ◽  
Massively Parallel ◽  
Large Field ◽  
Graphene Flakes ◽  
Field Dynamic ◽  
Scale Control ◽  
Orientation Pattern ◽  
Resolution Single

AbstractThe ability to precisely manipulate nano-objects on a large scale can enable the fabrication of materials and devices with tunable optical, electromagnetic, and mechanical properties. However, the dynamic, parallel manipulation of nanoscale colloids and materials remains a significant challenge. Here, we demonstrate acoustoelectronic nanotweezers, which combine the precision and robustness afforded by electronic tweezers with versatility and large-field dynamic control granted by acoustic tweezing techniques, to enable the massively parallel manipulation of sub-100 nm objects with excellent versatility and controllability. Using this approach, we demonstrated the complex patterning of various nanoparticles (e.g., DNAs, exosomes, ~3 nm graphene flakes, ~6 nm quantum dots, ~3.5 nm proteins, and ~1.4 nm dextran), fabricated macroscopic materials with nano-textures, and performed high-resolution, single nanoparticle manipulation. Various nanomanipulation functions, including transportation, concentration, orientation, pattern-overlaying, and sorting, have also been achieved using a simple device configuration. Altogether, acoustoelectronic nanotweezers overcome existing limitations in nano-manipulation and hold great potential for a variety of applications in the fields of electronics, optics, condensed matter physics, metamaterials, and biomedicine.

scholarly journals A Survey on Machine-Learning Based Security Design for Cyber-Physical Systems

2021 ◽  
Vol 11 (12) ◽  
pp. 5458
Author(s):  
Sangjun Kim ◽  
Kyung-Joon Park
Keyword(s):  
Machine Learning ◽  
Physical System ◽  
Large Scale ◽  
Computing System ◽  
Future Research ◽  
Physical Security ◽  
Computing Systems ◽  
Physical Systems ◽  
Security Research ◽  
Simultaneous Control

A cyber-physical system (CPS) is the integration of a physical system into the real world and control applications in a computing system, interacting through a communications network. Network technology connecting physical systems and computing systems enables the simultaneous control of many physical systems and provides intelligent applications for them. However, enhancing connectivity leads to extended attack vectors in which attackers can trespass on the network and launch cyber-physical attacks, remotely disrupting the CPS. Therefore, extensive studies into cyber-physical security are being conducted in various domains, such as physical, network, and computing systems. Moreover, large-scale and complex CPSs make it difficult to analyze and detect cyber-physical attacks, and thus, machine learning (ML) techniques have recently been adopted for cyber-physical security. In this survey, we provide an extensive review of the threats and ML-based security designs for CPSs. First, we present a CPS structure that classifies the functions of the CPS into three layers: the physical system, the network, and software applications. Then, we discuss the taxonomy of cyber-physical attacks on each layer, and in particular, we analyze attacks based on the dynamics of the physical system. We review existing studies on detecting cyber-physical attacks with various ML techniques from the perspectives of the physical system, the network, and the computing system. Furthermore, we discuss future research directions for ML-based cyber-physical security research in the context of real-time constraints, resiliency, and dataset generation to learn about the possible attacks.

Crack Growth and Propagation in Metallic Alloys

1995 ◽  
Vol 409 ◽  
Author(s):  
W. C. Morrey ◽  
L. T. Wille
Keyword(s):  
Large Scale ◽  
Critical Strain ◽  
Cleavage Plane ◽  
Crack Tip ◽  
Metallic Alloys ◽  
Propagation Direction ◽  
Dynamics Simulation ◽  
Parallel Computer ◽  
Massively Parallel ◽  
Tip Position

AbstractUsing large-scale molecular dynamics simulation on a massively parallel computer, we have studied the initiation of cracking in a Monel-like alloy of Cu-Ni. In a low temperature 2D sample, fracture from a notch starts at a little beyond 2.5% critical strain when the propagation direction is perpendicular to a cleavage plane. We discuss a method of characterizing crack tip position using a measure of area around the crack tip.

scholarly journals Beyond spatial scalability limitations with a massively parallel method for linear oscillatory problems

2017 ◽  
Vol 32 (6) ◽  
pp. 913-933 ◽  
Author(s):  
Martin Schreiber ◽  
Pedro S Peixoto ◽  
Terry Haut ◽  
Beth Wingate
Keyword(s):  
High Performance ◽  
Large Scale ◽  
Weather Prediction ◽  
Finite Difference Methods ◽  
Scaling Limit ◽  
Performance Model ◽  
Massively Parallel ◽  
Large Set ◽  
Problem Size ◽  
Single Node

This paper presents, discusses and analyses a massively parallel-in-time solver for linear oscillatory partial differential equations, which is a key numerical component for evolving weather, ocean, climate and seismic models. The time parallelization in this solver allows us to significantly exceed the computing resources used by parallelization-in-space methods and results in a correspondingly significantly reduced wall-clock time. One of the major difficulties of achieving Exascale performance for weather prediction is that the strong scaling limit – the parallel performance for a fixed problem size with an increasing number of processors – saturates. A main avenue to circumvent this problem is to introduce new numerical techniques that take advantage of time parallelism. In this paper, we use a time-parallel approximation that retains the frequency information of oscillatory problems. This approximation is based on (a) reformulating the original problem into a large set of independent terms and (b) solving each of these terms independently of each other which can now be accomplished on a large number of high-performance computing resources. Our results are conducted on up to 3586 cores for problem sizes with the parallelization-in-space scalability limited already on a single node. We gain significant reductions in the time-to-solution of 118.3× for spectral methods and 1503.0× for finite-difference methods with the parallelization-in-time approach. A developed and calibrated performance model gives the scalability limitations a priori for this new approach and allows us to extrapolate the performance of the method towards large-scale systems. This work has the potential to contribute as a basic building block of parallelization-in-time approaches, with possible major implications in applied areas modelling oscillatory dominated problems.

scholarly journals Supercomputer simulations of structure formation in the Universe

2016 ◽  
Vol 12 (S325) ◽  
pp. 10-16
Author(s):  
Tomoaki Ishiyama
Keyword(s):  
Domain Decomposition ◽  
Structure Formation ◽  
Short Range ◽  
Large Scale ◽  
Massively Parallel ◽  
Average Performance ◽  
And Performance ◽  
Performance Results ◽  
The Universe ◽  
Peak Speed

AbstractWe describe the implementation and performance results of our massively parallel MPI†/OpenMP‡ hybrid TreePM code for large-scale cosmological N-body simulations. For domain decomposition, a recursive multi-section algorithm is used and the size of domains are automatically set so that the total calculation time is the same for all processes. We developed a highly-tuned gravity kernel for short-range forces, and a novel communication algorithm for long-range forces. For two trillion particles benchmark simulation, the average performance on the fullsystem of K computer (82,944 nodes, the total number of core is 663,552) is 5.8 Pflops, which corresponds to 55% of the peak speed.

Sign in / Sign up

Export Citation Format

Share Document