4.3 Article

Routing brain traffic through the von Neumann bottleneck: Efficient cache usage in spiking neural network simulation code on general purpose computers

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Mathematical & Computational Biology

A Modular Workflow for Performance Benchmarking of Neuronal Network Simulations

Jasper Albers et al.

Summary: Modern computational neuroscience aims to develop complex network models to understand the dynamics and function of brains, and the advances in neuronal networks theory and anatomical data on brain connectivity are essential for this process. Simulation speed is crucial for large-scale models that study interactions between multiple brain areas and investigate long time scale phenomena. However, benchmarking simulations to assess the performance of simulators on high-performance computing (HPC) systems is challenging due to a lack of standardized specifications. To address this issue, researchers have developed a generic workflow and an open-source software framework called beNNch to facilitate benchmarking and improve simulation technology.

FRONTIERS IN NEUROINFORMATICS (2022)

Article Mathematical & Computational Biology

Routing Brain Traffic Through the Von Neumann Bottleneck: Parallel Sorting and Refactoring

Jari Pronold et al.

Summary: This article introduces a generic simulation code for spiking neuronal networks and focuses on the spike delivery process and the challenges as the network size grows. By optimizing the algorithm, the new alternative algorithm significantly reduces the simulation time.

FRONTIERS IN NEUROINFORMATICS (2022)

Article Engineering, Electrical & Electronic

Sub-realtime simulation of a neuronal network of natural density

Anno C. Kurth et al.

Summary: Simulating full-scale neuronal network models of the brain is challenging, but this study achieved shorter run times than the simulated biological time span by using a recent conventional compute node. Realtime performance is important for robotics and closed-loop applications, while sub-realtime performance is desirable for studying learning and development in the brain, which takes hours and days.

NEUROMORPHIC COMPUTING AND ENGINEERING (2022)

Article Mathematical & Computational Biology

Event-Based Update of Synapses in Voltage-Based Learning Rules

Jonas Stapmanns et al.

Summary: Efficient neural network simulators often use event-based simulation schemes for synapses due to the nature of neuronal spiking. However, many types of synaptic plasticity require the postsynaptic membrane potential as a third factor. This study provides two efficient algorithms for archiving postsynaptic membrane potentials and compares them with a time-driven synapse update scheme, showing the advantages in terms of memory and computations. The results suggest that event-based algorithms outperform the time-driven scheme for voltage-based plasticity rules in large-scale networks.

FRONTIERS IN NEUROINFORMATICS (2021)

Article Computer Science, Interdisciplinary Applications

Understanding Computational Costs of Cellular-Level Brain Tissue Simulations Through Analytical Performance Models

Francesco Cremonesi et al.

NEUROINFORMATICS (2020)

Article Computer Science, Hardware & Architecture

Analytic performance modeling and analysis of detailed neuron simulations

Francesco Cremonesi et al.

INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS (2020)

Review Neurosciences

The Scientific Case for Brain Simulations

Gaute T. Einevoll et al.

NEURON (2019)

Article Mathematical & Computational Biology

Large-Scale Simulation of a Layered Cortical Sheet of Spiking Network Model Using a Tile Partitioning Method

Jun Igarashi et al.

FRONTIERS IN NEUROINFORMATICS (2019)

Article Computer Science, Interdisciplinary Applications

SIMD vectorization for the Lennard-Jones potential with AVX2 and AVX-512 instructions

Hiroshi Watanabe et al.

COMPUTER PHYSICS COMMUNICATIONS (2019)

Article Computer Science, Hardware & Architecture

Interleaving with coroutines: a systematic and practical approach to hide memory latency in index joins

Georgios Psaropoulos et al.

VLDB JOURNAL (2019)

Article Mathematical & Computational Biology

Extremely Scalable Spiking Neuronal Network Simulation Code: From Laptops to Exascale Computers

Jakob Jordan et al.

FRONTIERS IN NEUROINFORMATICS (2018)

Article Biochemical Research Methods

A multi-scale layer-resolved spiking network model of resting-state dynamics in macaque visual cortical areas

Maximilian Schmidt et al.

PLOS COMPUTATIONAL BIOLOGY (2018)

Article Computer Science, Information Systems

Exploiting Coroutines to Attack the Killer Nanoseconds

Christopher Jonathan et al.

PROCEEDINGS OF THE VLDB ENDOWMENT (2018)

Article Anatomy & Morphology

Multi-scale account of the network structure of macaque visual cortex

Maximilian Schmidt et al.

BRAIN STRUCTURE & FUNCTION (2018)

Article Mathematical & Computational Biology

The NEST Dry-Run Mode: Efficient Dynamic Analysis of Neuronal Network Simulation Code

Susanne Kunkel et al.

FRONTIERS IN NEUROINFORMATICS (2017)

Article Mathematical & Computational Biology

Constructing Neuronal Network Models in Massively Parallel Environments

Tammo Ippen et al.

FRONTIERS IN NEUROINFORMATICS (2017)

Article Computer Science, Information Systems

Interleaving with Coroutines: A Practical Approach for Robust Index Joins

Georgios Psaropoulos et al.

PROCEEDINGS OF THE VLDB ENDOWMENT (2017)

Article Computer Science, Theory & Methods

A Survey of Recent Prefetching Techniques for Processor Caches

Sparsh Mittal

ACM COMPUTING SURVEYS (2016)

Article Anatomy & Morphology

Automatic Generation of Connectivity for Large-Scale Neuronal Network Models through Structural Plasticity

Sandra Diaz-Pier et al.

FRONTIERS IN NEUROANATOMY (2016)

Article Mathematical & Computational Biology

CyNEST: a maintainable Cython-based interface for the NEST simulator

Yury V. Zaytsev et al.

FRONTIERS IN NEUROINFORMATICS (2014)

Article Mathematical & Computational Biology

Spiking network simulation code for petascale computers

Susanne Kunkel et al.

FRONTIERS IN NEUROINFORMATICS (2014)

Article Mathematical & Computational Biology

Supercomputers ready for use as discovery machines for neuroscience

Moritz Helias et al.

FRONTIERS IN NEUROINFORMATICS (2012)

Article Mathematical & Computational Biology

Meeting the memory challenges of brain-scale network simulation

Susanne Kunkel et al.

FRONTIERS IN NEUROINFORMATICS (2012)

Article Mathematical & Computational Biology

An Ultrascalable Solution to Large-scale Neural Tissue Simulation

James Kozloski et al.

Frontiers in Neuroinformatics (2011)

Article Computer Science, Cybernetics

Phenomenological models of synaptic plasticity based on spike timing

Abigail Morrison et al.

BIOLOGICAL CYBERNETICS (2008)

Article Computer Science, Information Systems

Improving hash join performance through prefetching

Shimin Chen et al.

ACM TRANSACTIONS ON DATABASE SYSTEMS (2007)

Article Computer Science, Artificial Intelligence

Spike-timing-dependent plasticity in balanced random networks

Abigail Morrison et al.

NEURAL COMPUTATION (2007)

Article Computer Science, Interdisciplinary Applications

CHALLENGES IN PARALLEL GRAPH PROCESSING

Andrew Lumsdaine et al.

PARALLEL PROCESSING LETTERS (2007)

Article Computer Science, Artificial Intelligence

Advancing the boundaries of high-connectivity network simulation with distributed computing

A Morrison et al.

NEURAL COMPUTATION (2005)

Article Computer Science, Hardware & Architecture

Optimizing database architecture for the new bottleneck: memory access

S Manegold et al.

VLDB JOURNAL (2000)

Article Mathematical & Computational Biology

Dynamics of sparsely connected networks of excitatory and inhibitory spiking neurons

N Brunel

JOURNAL OF COMPUTATIONAL NEUROSCIENCE (2000)