Aasish Kumar Sharma

aasish_kumar_sharma.jpg

E-mailaasish-kumar.sharma@gwdg.de

Biography

Aasish Kumar Sharma is a researcher/scientific employee at Göttingen University employed under Professor Dr. Julian Kunkel and is focusing in high-performance computing performance optimization. His work includes developing efficient task scheduling algorithms for HPC systems, published in leading journals. Aasish is particularly interested in scalable solutions for heterogeneous architectures and has collected some publications and received the NHR Research Scholarship Award for his contributions. He is interested in optimization applying different smart algorithms, and emerging technologies like Artificial Intelligence/ Machine Learning (AI/ML) and Quantum Computing (QC) techniques. His previous work includes data engineering and big data analysis, and SQL query optimization while working as a Database Administrator. He is also a Microsoft Certified Trainer for Microsoft SQL Query Optimization for year 2025.
ResearchGate

Research Interests

  • High-Performance Computing
  • Data Analytics (SQL)
  • Emerging Technologies: AI/ML, Quantum Computing
  • Optimization (remember, resources are limited) and Ethics (responsible AI)

Teaching

Open Thesis Topics

Benchmarking and Characterization of Workflow Execution in Heterogeneous HPC SystemsApply

Accurate benchmarking is a prerequisite for meaningful workload mapping and scheduling research. This thesis focuses on designing and executing systematic benchmarks for heterogeneous HPC systems using workflow-based workloads. The student will characterize system properties (compute, memory, I/O, network) and workload behavior (task duration, data transfer, dependencies) using real and synthetic workflows. The outcome will be a reproducible benchmarking methodology and datasets that can be used as ground truth for evaluating optimization and AI-based schedulers.

Aasish Kumar Sharma HPCWorkflow BenchmarkingPerformance Engineering

Hybrid Scheduling: Combining Exact Solvers and Learning-Based Methods for HPC WorkflowsApply

Exact solvers provide optimal solutions but scale poorly, while learning-based methods scale well but lack guarantees. This thesis investigates hybrid scheduling strategies that combine MILP or CP-SAT solutions on small subproblems with learning-based generalization for larger workflows. The focus is on feasibility preservation and performance trade-offs.

Aasish Kumar Sharma Hybrid OptimizationHPCAI Scheduling

Quantum-Inspired Optimization for Workflow Mapping in Heterogeneous HPC SystemsApply

This thesis explores quantum-inspired optimization techniques, such as QUBO formulations, for workflow mapping problems in heterogeneous HPC environments. The student will translate classical scheduling constraints into QUBO models and compare solution feasibility and scalability against classical solvers.

Aasish Kumar Sharma Quantum-Inspired OptimizationQUBOHPC Scheduling

Ethical and Responsible AI Considerations in Automated HPC Scheduling SystemsApply

As AI-driven schedulers increasingly influence resource allocation decisions, ethical considerations such as fairness, transparency, and accountability become critical. This thesis examines ethical risks in automated HPC scheduling and proposes evaluation criteria or design guidelines for responsible scheduling systems, grounded in real HPC use cases.

Aasish Kumar Sharma Ethical AIHPCResponsible Computing

Constraint-Based Workflow Scheduling Using MILP and CP-SAT: A Comparative StudyApply

Constraint programming and mixed-integer linear programming are widely used for exact workflow scheduling but exhibit different scalability and modeling trade-offs. This thesis implements and compares MILP and CP-SAT formulations for workflow mapping and scheduling under heterogeneous resource constraints. The student will evaluate solution quality, feasibility guarantees, and solver performance across increasing problem sizes.

Aasish Kumar Sharma Constraint ProgrammingMILPWorkflow Scheduling

Modeling System and Workload Characteristics for Workflow Scheduling in the HPC Compute ContinuumApply

This project investigates how heterogeneous system resources and workflow characteristics can be modeled in a structured and extensible manner. The student will design data models for nodes, tasks, features, and performance properties, aligned with real HPC schedulers and workflow managers. The work emphasizes practical modeling choices that balance expressiveness and solvability, and results in machine-readable system and workload descriptions usable by optimization solvers.

Aasish Kumar Sharma HPCWorkflow ModelingHeterogeneous Systems

Theses

  • Performance Analysis of Convolutional Neural Network Applying Quantum Annealing, Aasish Kumar Sharma (Master's Thesis), Advisors: Sanjeeb Prasad Pandey, 2020-12-30, BibTeX URL

Publications

2025

  • Poster: Optimizing Workload in Heterogeneous HPC Workflows with Constraints (Aasish Kumar Sharma, Christian Boehme, Patrick Gelß, Julian Kunkel), ISC-HPC, Hamburg,Germany, 2025-06-11 BibTeX PDF
  • A Review of Tools and Techniques for Optimization of Workload Mapping and Scheduling in Heterogeneous HPC System (Aasish Kumar Sharma, Julian Kunkel), In ArXiv (1), pp. 12, 2025-05-16 BibTeX URL DOI
  • AI Work Quantization Model: Closed-System AI Computational Effort Metric (Aasish Kumar Sharma, Michael Bidollahkhani, Julian Martin Kunkel), In arXiv preprint arXiv:2503.14515, 2025-03-12 BibTeX URL
  • Performance Analysis of Convolutional Neural Network By Applying Unconstrained Binary Quadratic Programming (Aasish Kumar Sharma, Sanjeeb Prashad Pandey, Julian Martin Kunkel), In 2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC), IEEE COMPSAC Proceedings (49), pp. 483-488, IEEE Computer Society (Piscataway, New Jersey, USA), IEEE Computer Society, COMPSAC, 2025 BibTeX URL DOI
  • Grapheon RL: A Graph Neural Network and Reinforcement Learning Framework for Constraint and Data-Aware Workflow Mapping and Scheduling in Heterogeneous HPC Systems (Aasish Kumar Sharma, Julian Martin Kunkel), In 2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC), IEEE COMPSAC Proceedings (49), pp. 489-494, IEEE Computer Society (Piscataway, New Jersey, USA), IEEE Computer Society, COMPSAC, 2025 BibTeX URL DOI
  • Workflow-Driven Modeling for the Compute Continuum: An Optimization Approach to Automated System and Workload Scheduling (Aasish Kumar Sharma, Christian Boehme, Patrick Gelß, Ramin Yahyapour, Julian Martin Kunkel), In 2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC), IEEE COMPSAC Proceedings (49), pp. 2170-2177, IEEE Computer Society (Piscataway, New Jersey, USA), IEEE Computer Society, COMPSAC, 2025 BibTeX URL DOI

2024

All publications as BibTex