Search results for "hardware"

showing 10 items of 1372 documents

Fast spiking neural network architecture for low-cost FPGA devices

2012

Spiking Neural Networks (SNN) consist of fully interconnected computation units (neurons) based on spike processing. This type of networks resembles those found in biological systems studied by neuroscientists. This paper shows a hardware implementation for SNN. First, SNN require the inputs to be spikes, being necessary a conversion system (encoding) from digital values into spikes. For travelling spikes, each neuron interconnection is characterized by weights and delays, requiring an internal neuron processing by a Postsynaptic Potential (PSP) function and membrane potential threshold evaluation for a postsynaptic output spike generation. In order to model a real biological system by arti…

Spiking neural networkReduction (complexity)InterconnectionComputer sciencebusiness.industryComputationEncoding (memory)Real-time computingSpike (software development)Function (mathematics)Field-programmable gate arraybusinessComputer hardware7th International Workshop on Reconfigurable and Communication-Centric Systems-on-Chip (ReCoSoC)
researchProduct

Static and dynamic glass transitions in the 10-state Potts glass: What can Monte Carlo simulations contribute?

2002

The p-state Potts glass with infinite range Gaussian interactions can be solved exactly in the thermodynamic limit and exhibits an unconventional phase behavior if p >4: A dynamical transition from ergodic to non-ergodic behavior at a temperature T D is followed by a first order transition at T 0 < T D, where a glass order parameter appears discontinuously, although the latent heat is zero. If one assumes that a similar scenario occurs for the structural glass transition as well (though with the singular behavior at T D rounded off), the p-state Potts glass should be a good test case to develop methods to deal with finite size effects for the static as well as the dynamic transition, and to…

Spin glassGaussianMonte Carlo methodExtrapolationGeneral Physics and Astronomysymbols.namesakeHardware and ArchitectureThermodynamic limitsymbolsErgodic theoryStatistical physicsGlass transitionMathematicsPotts modelComputer Physics Communications
researchProduct

Digital background calibration algorithm and its FPGA implementation for timing mismatch correction of time-interleaved ADC

2019

Sample time error can degrade the performance of time-interleaved analog to digital converters (TIADCs). A fully digital background algorithm is presented in this paper to estimate and correct the timing mismatch errors between four interleaved channels, together with its hardware implementation. The proposed algorithm provides low computation burden and high performance. It is based on the simplified representation of the coefficients of the Lagrange interpolator. Simulation results show that it can suppress error tones in all of the Nyquist band. Results show that, for a four-channel TIADC with 10-bit resolution, the proposed algorithm improves the signal to noise and distortion ratio (SN…

Spurious-free dynamic rangeEnginyeria elèctricaComputer scienceDynamic rangeComputation020208 electrical & electronic engineering020206 networking & telecommunications02 engineering and technologySurfaces Coatings and FilmsData acquisitionHardware and ArchitectureSignal Processing0202 electrical engineering electronic engineering information engineeringElectronic engineeringNyquist–Shannon sampling theoremCircuits integratsSystem timeField-programmable gate arrayCommunication channel
researchProduct

Magnetic domain-wall racetrack memory for high density and fast data storage

2012

The racetrack memory device is a new concept of Magnetic RAM (MRAM) based on controlling domain wall (DW) motion in ferromagnetic nanowires. It promises ultra-high storage density thanks to the possibility to store multiple narrow DWS per memory cell. By using read and write heads based on magnetic tunnel junctions (MTJ) with perpendicular magnetic anisotropy (PMA) fast data access speed can also be achieved. Thereby the racetrack memory can be used as universal storage to address both embedded and standalone applications. In this paper, we present the device physics, integration circuit and architecture designs of a racetrack memory based on MTJs with PMA. Mixed SPICE simulations at 65 nm …

Standalone applicationsMagnetic domainComputer scienceSpiceArchitecture designsMRAM devicesMemory cellElectronic engineeringRacetrack memoryPerpendicular magnetic anisotropyMagnetic domainsMagnetoresistive random-access memoryHardware_MEMORYSTRUCTURESIntegration circuitsNanowiresbusiness.industryMagnetic devicesElectrical engineeringNon-volatile memory technologyDomain wall motionTunnel magnetoresistanceData storage equipmentComputer data storageFerromagnetic nanowireNode (circuits)Magnetic tunnel junctionbusinessRandom access storage
researchProduct

Lone Star Stack: Architecture of a Disk-Based Archival System

2014

The need for huge storage systems rises with the ever growing creation of data. With growing capacities and shrinking prices, "write once read sometimes" workloads become more common. New data is constantly added, rarely updated or deleted, and every stored byte might be read at any time - a common pattern for digital archives or big data scenarios. We present the Lone Star Stack, a disk based archival storage system building block that is optimized for high reliability and energy efficiency. It provides a POSIX file system interface that uses flash based storage for write-offloading and metadata and the disk-based Lone Star RAID for user data storage. The RAID attempts to spin down disks a…

Standard RAID levelsHardware_MEMORYSTRUCTURESComputer scienceRAIDDisk array controllerbusiness.industryDisk mirroringDisk controllerDisk buffercomputer.software_genreDisk Data Formatlaw.inventionData recoverylawData_FILESOperating systembusinesscomputer2014 9th IEEE International Conference on Networking, Architecture, and Storage
researchProduct

LoneStar RAID

2016

The need for huge storage archives rises with the ever growing creation of data. With today’s big data and data analytics applications, some of these huge archives become active in the sense that all stored data can be accessed at any time. Running and evolving these archives is a constant tradeoff between performance, capacity, and price. We present the LoneStar RAID, a disk-based storage architecture, which focuses on high reliability, low energy consumption, and cheap reads. It is designed for MAID systems with up to hundreds of disk drives per server and is optimized for “write once, read sometimes” workloads. We use dedicated data and parity disks, and export the data disks as individu…

Standard RAID levelsHardware_MEMORYSTRUCTURESRAIDDisk array controllerComputer sciencebusiness.industryDisk mirroring020206 networking & telecommunicationsFault tolerance02 engineering and technologycomputer.software_genreDisk Data Formatlaw.inventionHardware and Architecturelaw020204 information systemsEmbedded systemData_FILES0202 electrical engineering electronic engineering information engineeringOperating systemCacheNon-standard RAID levelsbusinesscomputerACM Transactions on Storage
researchProduct

Importance of the Window Function Choice for the Predictive Modelling of Memristors

2021

Window functions are widely employed in memristor models to restrict the changes of the internal state variables to specified intervals. Here, we show that the actual choice of window function is of significant importance for the predictive modelling of memristors. Using a recently formulated theory of memristor attractors, we demonstrate that whether stable fixed points exist depends on the type of window function used in the model. Our main findings are formulated in terms of two memristor attractor theorems, which apply to broad classes of memristor models. As an example of our findings, we predict the existence of stable fixed points in Biolek window function memristors and their absenc…

State variableComputer science02 engineering and technologyMemristorType (model theory)Fixed pointTopologyWindow functionlaw.inventionPredictive modelsComputer Science::Hardware ArchitectureComputer Science::Emerging TechnologiesMathematical modellawAttractor0202 electrical engineering electronic engineering information engineeringEvolution (biology)Electrical and Electronic EngineeringPolarity (mutual inductance)threshold voltage020208 electrical & electronic engineeringmemristive systemsBiological system modeling020206 networking & telecommunicationsWindow functionmemristorsIntegrated circuit modelingPredictive modellingIEEE Transactions on Circuits and Systems Ii-Express Briefs
researchProduct

Branch-and-cut algorithms for the vehicle routing problem with trailers and transshipments

2013

This article studies the vehicle routing problem with trailers and transshipments VRPTT, a practically relevant, but challenging, generalization of the classical vehicle routing problem. The article makes three contributions: i Building on a nontrivial network representation, two mixed-integer programming formulations for the VRPTT are proposed. ii Based on these formulations, five different branch-and-cut algorithms are developed and implemented. iii The computational behavior of the algorithms is analyzed in an extensive computational study, using a large number of test instances designed to resemble real-world VRPTTs.Copyright © 2013 Wiley Periodicals, Inc. NETWORKS, Vol. 631, 119-133 20…

Static routingComputer Networks and CommunicationsGeneralizationComputer scienceTransshipmentHardware and ArchitectureSynchronization (computer science)Vehicle routing problemDestination-Sequenced Distance Vector routingRepresentation (mathematics)Branch and cutAlgorithmSoftwareInformation Systems
researchProduct

An Efficient Implementation of Distributed Routing Algorithms for NoCs

2008

The design of NoCs for multi-core chips introduces new design constraints like power consumption, area, and ultra low latencies. Although 2D meshes are preferred, heterogeneous blocks, fabrication faults, reliability issues, and chip virtualization may lead to the need of irregular topologies or regions. In this situation, efficient routing becomes a challenge. Although the use of routing tables at switches is flexible, it does not scale in terms of latency and area due to its memory requirements. LBDR (logic-based distributed routing) is proposed as a new routing method that removes the need of using routing tables at all. LBDR enables the implementation of many routing algorithms on most …

Static routingDynamic Source RoutingZone Routing ProtocolComputer sciencebusiness.industryDistributed computingRouting tableEnhanced Interior Gateway Routing ProtocolPolicy-based routingLink-state routing protocolMultipath routingHardware_INTEGRATEDCIRCUITSbusinessComputer networkSecond ACM/IEEE International Symposium on Networks-on-Chip (nocs 2008)
researchProduct

Simulating spin models on GPU

2010

Over the last couple of years it has been realized that the vast computational power of graphics processing units (GPUs) could be harvested for purposes other than the video game industry. This power, which at least nominally exceeds that of current CPUs by large factors, results from the relative simplicity of the GPU architectures as compared to CPUs, combined with a large number of parallel processing units on a single chip. To benefit from this setup for general computing purposes, the problems at hand need to be prepared in a way to profit from the inherent parallelism and hierarchical structure of memory accesses. In this contribution I discuss the performance potential for simulating…

Statistical Mechanics (cond-mat.stat-mech)Computer scienceHigh Energy Physics - Lattice (hep-lat)Monte Carlo methodFOS: Physical sciencesGeneral Physics and AstronomyParallel computingComputational Physics (physics.comp-ph)Power (physics)CUDAHigh Energy Physics - LatticeParallel processing (DSP implementation)Hardware and ArchitectureParallelism (grammar)Ising modelGraphicsPhysics - Computational PhysicsVideo gameCondensed Matter - Statistical MechanicsComputer Physics Communications
researchProduct