Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “computational efficiency”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 163 records · Page 9

Decode the Workload: Training Deep Learning Models for Efficient Compute Cluster Representation

Monitoring the status of a high throughput computing cluster running computationally intensive production jobs is a crucial yet challenging system administration task due to the complexity of such systems. To this end, we train autoencoders using the Linux kernel CPU metrics of the cluster. Additionally, we explore assisting these models with graph neural networks to share information across threads within a compute node. The models are compared in terms of their ability to: 1) Produce a compressed latent representation that captures the salient features of the input, 2) Detect anomalous activity, and 3) Make distinction between different kinds of jobs run at Jefferson Lab. The goal is to have a robust encoder whose compressed embeddings are used for several downstream tasks. We extend this study further by deploying these models in a human-in-the-loop production-based setting for the anomaly detection task and discuss the associated implementation aspects such as continual learning and the criterion to generate alarms. This study represents a first step in the endeavor towards building self-supervised large-scale foundation models for computing centers.

Mohammed, Ahmed↗

Efficiently Computable Limits on EPR Pair Generation in Quantum Broadcast Channels

We investigate the generation of EPR pairs between three observers in a general causally structured setting, where communication occurs via a noisy quantum broadcast channel. The most general quantum codes for this setup take the form of tripartite quantum channels. Since the receivers are constrained by causal ordering, additional temporal relationships naturally emerge between the parties. These causal constraints enforce intrinsic no-signalling conditions on any tripartite operation, ensuring that it constitutes a physically realizable quantum code for a quantum broadcast channel. We analyze these constraints and, more broadly, characterize the most general quantum codes for communication over such channels. We examine the capabilities of codes that are fully no-signalling among the three parties, positive partial transpose (PPT)-preserving, or both, and derive simple semidefinite programs to compute the achievable entanglement fidelity. We then establish a hierarchy of semidefinite programming converse bounds -- both weak and strong -- for the capacity of quantum broadcast channels for EPR pair generation, in both one-shot and asymptotic regimes. Notably, in the special case of a point-to-point channel, our strong converse bound recovers and strengthens existing results. Finally, we demonstrate how the PPT-preserving codes we develop can be leveraged to construct PPT-preserving entanglement combing schemes, and vice versa.

FOS: Physical sciences↗

Adaptive real-time methodology for optimizing energy-efficient computing

Dynamic voltage and frequency scaling (DVFS) is an effective way to reduce energy and power consumption in microprocessor units. Current implementations of DVFS suffer from inaccurate modeling of power requirements and usage, and from inaccurate characterization of the relationships between the applicable variables. A system and method is proposed that adjusts CPU frequency and voltage based on run-time calculations of the workload processing time, as well as a calculation of performance sensitivity with respect to CPU frequency. The system and method are processor independent, and can be applied to either an entire system as a unit, or individually to each process running on a system.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Adaptive real-time methodology for optimizing energy-efficient computing

Dynamic voltage and frequency scaling (DVFS) is an effective way to reduce energy and power consumption in microprocessor units. Current implementations of DVFS suffer from inaccurate modeling of power requirements and usage, and from inaccurate characterization of the relationships between the applicable variables. A system and method is proposed that adjusts CPU frequency and voltage based on run-time calculations of the workload processing time, as well as a calculation of performance sensitivity with respect to CPU frequency. The system and method are processor independent, and can be applied to either an entire system as a unit, or individually to each process running on a system.

97 MATHEMATICS AND COMPUTING↗