• Corpus ID: 237605302

Routing brain traffic through the von Neumann bottleneck: Parallel sorting and refactoring

  title={Routing brain traffic through the von Neumann bottleneck: Parallel sorting and refactoring},
  author={Jari Pronold and Jakob Jordan and Brian J. N. Wylie and Itaru Kitayama and Markus Diesmann and Susanne Kunkel},
Generic simulation code for spiking neuronal networks spends the major part of time in the phase where spikes have arrived at a compute node and need to be delivered to their target neurons. These spikes were emitted over the last interval between communication steps by source neurons distributed across many compute nodes and are inherently irregular and unsorted with respect to their targets. For finding those targets, the spikes need to be dispatched to a three-dimensional data structure with… 

Figures from this paper


Spiking network simulation code for petascale computers
It is shown that the novel architecture presented here scales to the largest petascale supercomputers available today, and quantitatively discusses the performance on two supercomputing systems.
Constructing Neuronal Network Models in Massively Parallel Environments
This work uncovers that the lack of scaling of thread-parallel network creation is due to inadequate memory allocation strategies and demonstrates that thread-optimized memory allocators recover excellent scaling.
Extremely Scalable Spiking Neuronal Network Simulation Code: From Laptops to Exascale Computers
This work presents a two-tier connection infrastructure and a framework for directed communication among compute nodes accounting for the sparsity of brain-scale networks and shows that the new data structures and communication scheme prepare the simulation kernel for post-petascale high-performance computing facilities without sacrificing performance in smaller systems.
Supercomputers Ready for Use as Discovery Machines for Neuroscience
The improvements are explained, guided by a mathematical model of memory consumption, that enable us to exploit for the first time the computational power of the K supercomputer for neuroscience.
Efficient Communication in Distributed Simulations of Spiking Neuronal Networks With Gap Junctions
This work integrates an existing framework for continuous interactions with a recently proposed directed communication scheme for spikes, allowing, for the first time, the efficient exploration of the interactions of chemical and electrical coupling in large-scale neuronal networks models with natural synapse density distributed across thousands of compute nodes.
A unified framework for spiking and gap-junction interactions in distributed neuronal network simulations
A numerical algorithm based on a waveform-relaxation technique which allows for network simulations with gap junctions in a way that is compatible with the delayed communication strategy, and demonstrates that the algorithm and the required data structures can be smoothly integrated with existing code such that they complement the infrastructure for spiking connections.
Overview of the SpiNNaker System Architecture
Three of the principal axioms of parallel machine design (memory coherence, synchronicity, and determinism) have been discarded in the design without, surprisingly, compromising the ability to perform meaningful computations.
CoreNEURON : An Optimized Compute Engine for the NEURON Simulator
How CoreNEURON can be used as a library with NEURON and then compare performance of different network models on multiple architectures including IBM BlueGene/Q, Intel Skylake, Intel MIC and NVIDIA GPU is described.
Exact Subthreshold Integration with Continuous Spike Times in Discrete-Time Neural Network Simulations
It is shown that by exploiting the existence of a minimal synaptic propagation delay, the need for a central event queue is removed, so that the precision of event-driven simulation on the level of single neurons is combined with the efficiency of time-driven global scheduling.
Enabling Functional Neural Circuit Simulations with Distributed Computing of Neuromodulated Plasticity
This work develops a general framework to solve the problem of implementing neuromodulated plasticity in a time-driven distributed simulation, without reference to a particular implementation language, neurmodulator, or neurommodulated Plasticity mechanism.