Institution profile

Hewlett Packard Enterprise

Industry researchnorthamerica · us
Official website
Research library69linked papers
Opportunities0open roles
Selected work

Representative Papers

A measurement-based approach to analyze the power consumption of the softwarized 5G core

Mar 01, 2024Comput. Networks

Accurately assessing energy consumption and carbon footprint remains challenging in software–hardware decoupled, virtualized 5G Core Networks (5GC). Method: This paper proposes a measurement-driven, fine-grained power consumption analysis framework—the first to jointly monitor container-, microservice-, and virtualization-layer power usage. It integrates eBPF/Prometheus for real-time telemetry, Kubernetes resource profiling, multi-dimensional workload injection, and physics-informed power modeling. Contribution/Results: Implemented on a production-grade OpenStack+Kubernetes platform, the framework achieves an average power estimation error of ±3.2%. It identifies CPU idling and memory bandwidth bottlenecks in the Session Management Function (SMF) and User Plane Function (UPF) as primary contributors to 37% redundant energy consumption. The work establishes a reusable, quantitatively grounded measurement paradigm for software–hardware co-optimization of energy efficiency in cloud-native 5GC deployments.

2 citationsRead paper

GEO-Flag: Detecting and Measuring GEO-Optimized Web Content

Aug 17, 2026

This study addresses the proliferation of Generative Engine Optimization (GEO) content and the lack of auditing mechanisms in generative search. We construct a benchmark dataset and propose an Interventional Paired Training (IPT) strategy alongside a GEO-gated Agent auditing system. By leveraging ModernBERT fine-tuning and agent-based provenance tracing, we achieve precise GEO identification and citation verification. Experiments demonstrate a detection F1-score of 0.944 and improved long-tail accuracy of 0.883, while quantifying real-world GEO prevalence at 8.90% for the first time. This work bridges the gap in systematic detection, providing critical empirical evidence and technical support for governing the generative search ecosystem.

0 citationsRead paper

Porting and Benchmarking Chapel on Emerging RISC-V Hardware: an HPC Viability Study

Aug 14, 2026

This study addresses the need to evaluate RISC-V’s suitability for high-performance computing (HPC) by presenting the first systematic port of the Chapel programming language to this platform. Leveraging standard HPC benchmark suites, we conduct a comprehensive cross-platform performance comparison that successfully validates Chapel’s adaptability on RISC-V while identifying critical performance anomalies and bottlenecks inherent in cross-architecture migration. The results demonstrate that RISC-V possesses the technical potential to support future HPC workloads effectively. Consequently, this work provides empirical evidence and methodological guidance for integrating emerging instruction set architectures into the broader HPC ecosystem, establishing a foundational baseline for subsequent research and development in this domain.

0 citationsRead paper
Recent publications

Latest Papers

GEO-Flag: Detecting and Measuring GEO-Optimized Web Content

Aug 17, 2026

This study addresses the proliferation of Generative Engine Optimization (GEO) content and the lack of auditing mechanisms in generative search. We construct a benchmark dataset and propose an Interventional Paired Training (IPT) strategy alongside a GEO-gated Agent auditing system. By leveraging ModernBERT fine-tuning and agent-based provenance tracing, we achieve precise GEO identification and citation verification. Experiments demonstrate a detection F1-score of 0.944 and improved long-tail accuracy of 0.883, while quantifying real-world GEO prevalence at 8.90% for the first time. This work bridges the gap in systematic detection, providing critical empirical evidence and technical support for governing the generative search ecosystem.

0 citationsRead paper

Porting and Benchmarking Chapel on Emerging RISC-V Hardware: an HPC Viability Study

Aug 14, 2026

This study addresses the need to evaluate RISC-V’s suitability for high-performance computing (HPC) by presenting the first systematic port of the Chapel programming language to this platform. Leveraging standard HPC benchmark suites, we conduct a comprehensive cross-platform performance comparison that successfully validates Chapel’s adaptability on RISC-V while identifying critical performance anomalies and bottlenecks inherent in cross-architecture migration. The results demonstrate that RISC-V possesses the technical potential to support future HPC workloads effectively. Consequently, this work provides empirical evidence and methodological guidance for integrating emerging instruction set architectures into the broader HPC ecosystem, establishing a foundational baseline for subsequent research and development in this domain.

0 citationsRead paper

LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs

Aug 07, 2026

This work addresses the communication bottleneck in large-scale distributed graph neural network (GNN) training, which is often hindered by congestion during inter-node data exchange. The authors propose the first approach that jointly offloads neighbor sampling and quantization onto SmartNICs (NVIDIA BlueField-2) attached to remote memory nodes, substantially reducing the volume of data transferred to compute nodes. By integrating two low-overhead communication mechanisms—DOCA-DMA and Socket—the method effectively alleviates network congestion. Experimental results on a proof-of-concept system demonstrate that neighbor sampling alone achieves speedups of up to 62.4× (Socket) and 17.5× (DOCA-DMA); when combined with quantization, performance further improves by 3.6× and 1.3×, respectively, significantly lowering communication overhead in distributed GNN training.

0 citationsRead paper