Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning Pareto-Frontier Resource Management Policies for Heterogeneous SoCs: An Information-Theoretic Approach
172
0
0.0
(
0
)
Added by
Ganapati Bhat
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Mobile system-on-chips (SoCs) are growing in their complexity and heterogeneity (e.g., Arms Big-Little architecture) to meet the needs of emerging applications, including games and artificial intelligence. This makes it very challenging to optimally manage the resources (e.g., controlling the number and frequency of different types of cores) at runtime to meet the desired trade-offs among multiple objectives such as performance and energy. This paper proposes a novel information-theoretic framework referred to as PaRMIS to create Pareto-optimal resource management policies for given target applications and design objectives. PaRMIS specifies parametric policies to manage resources and learns statistical models from candidate policy evaluation data in the form of target design objective values. The key idea is to select a candidate policy for evaluation in each iteration guided by statistical models that maximize the information gain about the true Pareto front. Experiments on a commercial heterogeneous SoC show that PaRMIS achieves better Pareto fronts and is easily usable to optimize complex objectives (e.g., performance per Watt) when compared to prior methods.
rate research
Read More
Dynamic resource management has become one of the major areas of research in modern computer and communication system design due to lower power consumption and higher performance demands. The number of integrated cores, level of heterogeneity and amount of control knobs increase steadily. As a result, the system complexity is increasing faster than our ability to optimize and dynamically manage the resources. Moreover, offline approaches are sub-optimal due to workload variations and large volume of new applications unknown at design time. This paper first reviews recent online learning techniques for predicting system performance, power, and temperature. Then, we describe the use of predictive models for online control using two modern approaches: imitation learning (IL) and an explicit nonlinear model predictive control (NMPC). Evaluations on a commercial mobile platform with 16 benchmarks show that the IL approach successfully adapts the control policy to unknown applications. The explicit NMPC provides 25% energy savings compared to a state-of-the-art algorithm for multi-variable power management of modern GPU sub-systems.
One of the most critical aspects of integrating loosely-coupled accelerators in heterogeneous SoC architectures is orchestrating their interactions with the memory hierarchy, especially in terms of navigating the various cache-coherence options: from accelerators accessing off-chip memory directly, bypassing the cache hierarchy, to accelerators having their own private cache. By running real-size applications on FPGA-based prototypes of many-accelerator multi-core SoCs, we show that the best cache-coherence mode for a given accelerator varies at runtime, depending on the accelerators characteristics, the workload size, and the overall SoC status. Cohmeleon applies reinforcement learning to select the best coherence mode for each accelerator dynamically at runtime, as opposed to statically at design time. It makes these selections adaptively, by continuously observing the system and measuring its performance. Cohmeleon is accelerator-agnostic, architecture-independent, and it requires minimal hardware support. Cohmeleon is also transparent to application programmers and has a negligible software overhead. FPGA-based experiments show that our runtime approach offers, on average, a 38% speedup with a 66% reduction of off-chip memory accesses compared to state-of-the-art design-time approaches. Moreover, it can match runtime solutions that are manually tuned for the target architecture.
Blockchain-enabled Federated Learning (BFL) enables mobile devices to collaboratively train neural network models required by a Machine Learning Model Owner (MLMO) while keeping data on the mobile devices. Then, the model updates are stored in the blockchain in a decentralized and reliable manner. However, the issue of BFL is that the mobile devices have energy and CPU constraints that may reduce the system lifetime and training efficiency. The other issue is that the training latency may increase due to the blockchain mining process. To address these issues, the MLMO needs to (i) decide how much data and energy that the mobile devices use for the training and (ii) determine the block generation rate to minimize the system latency, energy consumption, and incentive cost while achieving the target accuracy for the model. Under the uncertainty of the BFL environment, it is challenging for the MLMO to determine the optimal decisions. We propose to use the Deep Reinforcement Learning (DRL) to derive the optimal decisions for the MLMO.
Learning cooperative policies for multi-agent systems is often challenged by partial observability and a lack of coordination. In some settings, the structure of a problem allows a distributed solution with limited communication. Here, we consider a scenario where no communication is available, and instead we learn local policies for all agents that collectively mimic the solution to a centralized multi-agent static optimization problem. Our main contribution is an information theoretic framework based on rate distortion theory which facilitates analysis of how well the resulting fully decentralized policies are able to reconstruct the optimal solution. Moreover, this framework provides a natural extension that addresses which nodes an agent should communicate with to improve the performance of its individual policy.
Smart meters (SMs) share fine-grained electricity consumption of households with utility providers almost in real-time. This can violate the users privacy since sensitive information is leaked through the SMs data. In this study, a novel privacy-aware method which exploits the availability of a rechargeable battery (RB) is proposed. It is based on a Markov decision process (MDP) formulation in which the reward received by the agent is designed to control the trade-off between privacy and electricity cost. To obtain a robust and general privacy measure, we adopt the mutual information (MI) between the users demand load and the masked load seen by the grid. Unlike previous studies, we model the whole temporal correlation in the data to estimate the MI in its general form. The training of the agent is done using a model-free deep reinforcement learning algorithm known as the deep double Q-learning (DDQL) method. In order to estimate the MI-based privacy signal, a neural network termed the H-network is included in the scheme. The performance of the DDQL-MI algorithm is assessed empirically using actual SMs data and compared with simpler privacy measures. The results show significant improvements over the state-of-the-art privacy-aware SMs methods.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
