Tapasya Patki

HPC Digital Twins for Evaluating Scheduling Policies, Incentive Structures and their Impact on Power and Cooling

Schedulers are critical for optimal resource utilization in high-performance computing. Traditional methods to evaluate schedulers are limited to post-deployment analysis, or simulators, which do...

Autonomy Loops for Monitoring, Operational Data Analytics, Feedback, and Response in HPC Operations

Monitoring Large Scale Supercomputers: A Case Study with the Lassen Supercomputer

Quantitative Trait Locus Analysis Using a Partitioned Linear Model on a GPU Cluster

Analyzing Resource Trade-offs in Hardware Overprovisioned Supercomputers

Systemwide Power Management with Argo

Predicting Cross-Architecture Performance of Parallel Programs

Production Hardware Overprovisioning: Real-World Performance Optimization Using an Extensible Power-Aware Resource Management Framework

Enabling Lightweight Performance Analysis of Complex Scientific Workflows with PerfFlowAspect

System-Level Energy Profiling of Wafer-Scale AI Systems: Characterizing Non-Accelerator Overheads in the Cerebras CS-2 System

Evaluating the Potential of Coscheduling on High-Performance Computing Systems

xAMM: "Attention" to Details Improves Cross-Platform Prediction Accuracy

Priority-Aware GPU Co-Scheduling for High Performance Computing

Flux Fiction: Hopping Toward Storage Graph Scheduling With El Capitan's Rabbits

Flux Emulator: First Insights into Optimizing Scheduling for Exascale HPC

Practical Resource Management in Power-Constrained, High Performance Computing

ModelX : A Novel Transfer Learning Approach Across Heterogeneous Datasets

Modeling Considerations in BPO Multiplexing Environment