Search

With the increasing demand for distributed big data analytics and data-intensive programs which contribute to large volumes of packets among processing elements (PEs) and memory banks, we witness a pressing need for new mathematical models and algorithms that can engineer a brain-inspired plasticity into the computing platforms by mining the topological complexity of high-level programs (HLPs) and exploiting their self-similar and fractal characteristics for designing reconfigurable domain-specific computing architectures. In this article, we present Plasticity-on-Chip (PoC) by engineering plasticity into ”artificial brains” to mine and exploit the self-similarity of HLPs. First, we present a communication modeling of HLPs (e.g., C/C++ implementations of various applications) that relies on static and dynamic compiler analysis of programs with varying input seeds, performing comprehensive program analysis of all traces, and representing the HLPs as weighted directed acyclic graphs while capturing the intrinsic timing constraints and data/control flow requirements. Second, we propose a rigorous mathematical framework for determining the optimal parallel degree of executing a set of interacting HLPs (by partitioning them into clusters of densely interconnected supernodes - tasks) which helps us decide the number of available heterogeneous PEs, the amount of required memory and the structure of the synthesized deadlock-free irregular NoC topology that offers an efficient communication medium. These clusters serve as abstract models of computation for the synthesized PEs within the parallel execution model. Finally, exploiting the fractal and complex networks concepts, we extract in-depth features from graphs that serve as inputs for distributed reinforcement learning. Our experimental results on synthesized PEs and NoCs show performance improvements as high as 7.61x when compared to the traditional NoC and 2.6x compared to gem5-Aladdin. [ABSTRACT FROM AUTHOR]

Novel dynamics are emerging in the power system due to the new Smart Grid (SG) environment. The high sampling rate of the Phasor Measurement Units (PMUs) enables them to capture the dynamic fluctuations in the power system measurements. Understanding the statistical and dynamic characteristics of the PMU data requires advanced data analytics techniques capable of performing accurate modeling of the power system variables (voltage, frequency, phase angle, and rate of change of frequency (ROCOF)). In this article, we provide evidence of the non-stationarity and fractality of PMU data collected from Europe. We adopt the Autoregressive Fractionally Integrated Moving Average (ARFIMA) models with non-integer differencing parameter to model the short-range and long-range correlations in the PMU data. Furthermore, the goodness-of-fit of the ARFIMA model is confirmed by analyzing the correlation and independence of the model residuals. Anomaly detection is among the promising applications of the PMU ARFIMA models. It is shown that the 2012 Indian blackout is accompanied by a change point in the differencing parameter opening the road to event (anomaly) detection by ARFIMA monitoring. [ABSTRACT FROM AUTHOR]

Cloud computing has attracted both end-users and cloud service providers (CSPs) in recent years. Improving resource utilization rate (RUtR), such as CPU and memory usages on servers, while maintaining quality of service (QoS) is one key challenge faced by CSPs with warehouse-scale datacenters. Prior works proposed various algorithms to reduce energy cost or to improve RUtR, which either lack the fine-grained task scheduling capabilities, or fail to take a comprehensive system model into consideration. This article presents H2O-Cloud, a Hierarchical and Hybrid Online task scheduling framework for warehouse-scale Cloud service providers, to improve resource usage effectiveness while maintaining QoS. H2O-Cloud is highly scalable and considers comprehensive information, such as various workload scenarios, cloud platform configurations, user request information, and dynamic pricing model. The hierarchy and hybridity of the framework, combined with its deep reinforcement learning (DRL) engines, enable H2O-Cloud to efficiently start on-the-go scheduling and learning in an unpredictable environment without pretraining. Our experiments confirm the high efficiency of the proposed H2O-Cloud when compared to baseline approaches, in terms of energy and cost while maintaining QoS. Compared with a state-of-the-art DRL-based algorithm, H2O-Cloud achieves up to 201.17% energy cost efficiency improvement, 47.88% energy efficiency improvement, and 551.76% reward rate improvement. [ABSTRACT FROM AUTHOR]

There exists an urgent need for determining the right amount and type of specialization while making a heterogeneous system as programmable and flexible as possible. Therefore, in this paper, we pioneer a self-optimizing and self-programming computing system (SOSPCS) design framework that achieves both programmability and flexibility and exploits computing heterogeneity [e.g., CPUs, GPUs, and hardware accelerators (HWAs)]. First, at compile time, we form a task pool consisting of hybrid tasks with different processing element (PE) affinities according to target applications. Tasks preferred to be executed on GPUs or accelerators are detected from target applications by neural networks. Tasks suitable to run on CPUs are formed by community detection to minimize data movement overhead. Next, a distributed reinforcement learning-based approach is used at runtime to allow agents to map the tasks onto the network-on-chip-based heterogeneous PEs by learning an optimal policy based on $Q$ values in the environment. We have conducted experiments on a heterogeneous platform consisting of CPUs, GPUs, and HWAs with deep learning algorithms such as matrix multiplication, ReLU, and sigmoid functions. We concluded that SOSPCS provides performance improvement up to $4.12\times $ and energy reduction up to $3.24\times $ compared to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Understanding the dynamics and functionality of the human brain and its relationship with different physical entities has proven to be extremely useful in many applications including disability therapy and designing the next-generation user-interfaces. Communication between the brain and external hardware using neural stimulation and recordings has also been demonstrated recently. Such systems are usually analyzed by employing the brain–machine–body interface (BMBI) model. However, owing to the high complexity of the human brain activity, modeling and analyzing the neural-signals is a resource-intensive task. Moreover, coupling neural signals from different physical entities inevitably leads to large input data sets and hence, also making it data- and computationally intensive. Hence, here we employ a spatiotemporal fractal parallel algorithm to efficiently generate and analyze the BMBI models. However, such an algorithm can lead to demanding on-chip traffic patterns requiring an efficient communication infrastructure among different computing cores. To address this issue, we propose a machine-learning-inspired wireless network-on-chip (WiNoC)-based manycore architecture for handling the compute- and communication-intensive nature of the BMBI applications. The experimental results show that, compared with the traditional wireline mesh NoC, WiNoC achieves up to 55% savings in energy delay product for a system size of 1024 cores. [ABSTRACT FROM AUTHOR]