Abstract
Computational modeling and simulation have become essential tools in the quest to better understand the brain’s makeup and to decipher the causal interrelations of its components. The breadth of biochemical and biophysical processes and structures in the brain has led to the development of a large variety of model abstractions and specialized tools, often times requiring high performance computing resources for their timely execution. What has been missing so far was an in-depth analysis of the complexity of the computational kernels, hindering a systematic approach to identifying bottlenecks of algorithms and hardware. If whole brain models are to be achieved on emerging computer generations, models and simulation engines will have to be carefully co-designed for the intrinsic hardware tradeoffs. For the first time, we present a systematic exploration based on analytic performance modeling. We base our analysis on three in silico models, chosen as representative examples of the most widely employed modeling abstractions: current-based point neurons, conductance-based point neurons and conductance-based detailed neurons. We identify that the synaptic modeling formalism, i.e. current or conductance-based representation, and not the level of morphological detail, is the most significant factor in determining the properties of memory bandwidth saturation and shared-memory scaling of in silico models. Even though general purpose computing has, until now, largely been able to deliver high performance, we find that for all types of abstractions, network latency and memory bandwidth will become severe bottlenecks as the number of neurons to be simulated grows. By adapting and extending a performance modeling approach, we deliver a first characterization of the performance landscape of brain tissue simulations, allowing us to pinpoint current bottlenecks for state-of-the-art in silico models, and make projections for future hardware and software requirements.
Highlights
IntroductionIn the field of computational neuroscience, simulations of biological neural networks represent one of the fundamental
Our analysis is based on stateof-the-art high performance computing (HPC) hardware architecture and applied to three published neural network simulations that have been selected to represent the diversity of neuron models in the literature
We develop our analysis of the performance landscape in a two-step process as show in Fig. 1: first we identify relevant in silico models and experiments from the literature that constitute a representative sample of state-of-the-art models and algorithms, and present a set of hardware-agnostic descriptive metrics that can give a first insight on their performance properties; we intersect the hardwareagnostic description with a model of the hardware platform, by extending and adapting well-established performance models to neuroscientific simulations use cases
Summary
In the field of computational neuroscience, simulations of biological neural networks represent one of the fundamental. Despite the multiple years of research in efficient implementations of neuron models, we are still missing a more quantitative treatment of what are the actual computational characteristics of a given level of detail and how a particular level of detail may be limited by specific hardware trade-offs. We extend performance modeling techniques to the field of computational neuroscience, allowing us to establish a quantitative relationship between the parameters dictated by the biophysical model, the complexity properties of the simulation algorithm and the details of the hardware specifications. Our analysis is based on stateof-the-art high performance computing (HPC) hardware architecture and applied to three published neural network simulations that have been selected to represent the diversity of neuron models in the literature
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
