Real-Time Cortical Simulations: Energy and Interconnect Scaling on Distributed Systems

@article{Simula2019RealTimeCS,
  title={Real-Time Cortical Simulations: Energy and Interconnect Scaling on Distributed Systems},
  author={Francesco Simula and Elena Pastorelli and Pier Stanislao Paolucci and Michele Martinelli and Alessandro Lonardo and Andrea Biagioni and C. Capone and Fabrizio Capuani and Paolo Cretaro and Giulia De Bonis and Francesca Lo Cicero and Luca Pontisso and Piero Vicini and Roberto Ammendola},
  journal={2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},
  year={2019},
  pages={283-290}
}
  • F. SimulaE. Pastorelli R. Ammendola
  • Published 12 December 2018
  • Computer Science
  • 2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)
We profile the impact of computation and inter-processor communication on the energy consumption and on the scaling of cortical simulations approaching the real-time regime on distributed computing platforms. Also, the speed and energy consumption of processor architectures typical of standard HPC and embedded platforms are compared. We demonstrate the importance of the design of low-latency interconnect for speed and energy consumption. The cost of cortical simulations is quantified using the… 

Scaling of a Large-Scale Simulation of Synchronous Slow-Wave and Asynchronous Awake-Like Activity of a Cortical Model With Long-Range Interconnections

Performance scaling of the proprietary Distributed and Plastic Spiking Neural Networks (DPSNN) simulation engine in both SWA and AW for bidimensional grids of neural populations, which reflects the modular organization of the cortex.

Computational characteristics and hardware implications of brain tissue simulations

It is argued that performance analyses such as the authors' are required to enable the next generation of brain tissue simulations – or else scientific progress risks being hindered by the presence of severe hardware bottlenecks.

Performance and energy footprint assessment of FPGAs and GPUs on HPC systems using Astrophysics application

This work quantitatively evaluates the impact of computation on energy consumption when running on four different platforms and investigates the behavior of the different devices where the high-end GPUs excel in terms of time-to-solution while MPSoC-FPGA systems outperform GPUs in power consumption.

Characterizing and Predicting Scientific Workloads for Heterogeneous Computing Systems

A device independent predictor is presented – a methodology to use device-independent characteristics of an OpenCL code to select the optimal accelerator device on which to execute each OpenCL kernel with regard to execution time or energy expenditure.

References

SHOWING 1-10 OF 23 REFERENCES

Compass: A scalable simulator for an architecture for cognitive computing

  • Robert PreisslT. Wong D. Modha
  • Biology
    2012 International Conference for High Performance Computing, Networking, Storage and Analysis
  • 2012
Inspired by the function, power, and volume of the organic brain, we are developing TrueNorth, a novel modular, non-von Neumann, ultra-low power, compact architecture. TrueNorth consists of a

Power analysis of large-scale, real-time neural networks on SpiNNaker

The SpiNNaker neuromimetic architecture is designed to address these requirements, simulating large-scale heterogeneous models of spiking neurons in real-time, offering a unique combination of flexibility, scalability and power efficiency.

Gaussian and Exponential Lateral Connectivity on Distributed Spiking Neural Network Simulation

We measured the impact of long-range exponentially decaying intra-areal lateral connectivity on the scaling and memory occupation of a distributed spiking neural network simulator compared to that of

Distributed simulation of polychronous and plastic spiking neural networks: strong and weak scaling of a representative mini-application benchmark executed on a small-scale commodity cluster

A natively distributed mini-application benchmark representative of plastic spiking neural network simulators, designed to generate spiking behaviors and synaptic connectivity that do not change when the number of hardware processing nodes is varied, simplifying the quantitative study of scalability on commodity and custom architectures.

A million spiking-neuron integrated circuit with a scalable communication network and interface

Inspired by the brain’s structure, an efficient, scalable, and flexible non–von Neumann architecture is developed that leverages contemporary silicon technology and is well suited to many applications that use complex neural networks in real time, for example, multiobject detection and classification.

The cat is out of the bag: cortical simulations with 109 neurons, 1013 synapses

Two cortical simulations -- at unprecedented scale -- that effectively saturate the entire memory capacity and refresh it at least every simulated second are reported, marking the dawn of a new era in the scale of cortical simulations.

Slow Waves in Cortical Slices: How Spontaneous Activity is Shaped by Laminar Structure

This work focuses on ongoing slow waves in cortical slices reconstructed from a 16-electrode array designed to probe the neuronal activity at multiple spatial scales, and reproducibly found a smooth strip of loci leading the SW fronts, overlapping cortical layers 4 and 5, along which Up states were the longest and displayed the highest firing rate.

The Mont-Blanc Prototype: An Alternative Approach for HPC Systems

The Mont-Blanc prototype is presented; the first HPC system built with commodity SoCs, memories, and network interface cards (NICs) from the embedded and mobile domain, and off-the-shelf HPC networking, storage, cooling, and integration solutions.

Next generation of Exascale-class systems: ExaNeSt project and the status of its interconnect and storage development