Dr. Marcin Copik, graduate of ETH Zurich
Recognized for his dissertation "High Performance Serverless for HPC and Clouds"
Advisor: Torsten Hoefler
ACM's Special Interest Group on High Performance Computing (SIGHPC) is pleased to announce that Dr. Marcin Copik has won the 2025 SIGHPC Doctoral Dissertation Award. This award is given each year for the best doctoral dissertation completed in high performance computing (HPC) in the previous year. Nominations were evaluated on the novelty of the work, quality of scholarship, significance of the research contributions, and potential impact on theory and practice. The award includes a $2,000 cash prize, a plaque, and recognition at the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'25) in November 2025.
Dr. Copik's dissertation research bridges the domains of high-performance computing (HPC) and modern cloud computing, confronting the critical challenge of resource underutilization in supercomputing systems by adapting and integrating serverless programming models in HPC. By conducting a comprehensive evaluation of a Function-as-a-Service (FaaS) computing stack, his work represents a foundational shift in how HPC resources can be better managed and utilized to ultimately deliver a more efficient approach to supercomputing. Dr. Copik makes fundamental advances from the hardware interface up to system-level design and optimization, including RDMA networking in FaaS, co-locatiion of HPC workloads, serverless disaggregation using ephemeral FaaS, and enabling efficient data movement and MPI-style collective communication algorithms essential for optimizing distributed serverless workloads. He also contributed the SeBS benchmarking suite for serverless functions that provides methodologies crucial for performance analysis in the emerging hybrid cloud-HPC computing environments. The dissertation further introduces Process-as-a-Service, a generalized programming model inspired by classical operating system processes, where serverless processes overcome the limitations of FaaS paradigms, effectively bringing the richer semantics of distributed applications into the serverless cloud environment.
"Supercomputers enable and accelerate scientific discovery, yet their resources often sit idle while researchers wait in queues for their turn to run computations. Our work explores how serverless computing - a flexible programming model from cloud computing where resources are allocated on-demand - can be adapted to the requirements of scientific workloads and transform how we use these powerful machines," said Dr. Copik. "I hope that these contributions will help bridge the worlds of cloud and HPC computing, making both more efficient and accessible."
Dr. Copik received his Ph.D. degree in Computer Science at ETH Zurich, where he was advised by Prof. Torsten Hoefler. Currently, he is a post-doctoral researcher at the Scalable Parallel Computing Laboratory in the Department of Computer Science at ETH Zurich.
"The SIGHPC Doctoral Dissertation Award nominations received this year were exceptionally strong, with each dissertation contributing state-of-the-art results in different areas of HPC," said Christine Harvey, SIGHPC Chair. "Dr. Copik's outstanding achievement highlights the reach of HPC research to deliver new solutions for building complex and high-performance applications, in this case through well-validated and innovative solutions to persistent challenges in Function-as-a-Service (FaaS) on modern cloud systems. Congratulations to all nominees on their excellent work and we look forward to their contributions to the HPC community in the future."
Dr. Avinash Maurya, graduate of Rochester Institute of Technology
Recognized for his dissertation “Scalable Access‑Pattern Aware I/O Acceleration and Multi‑Tiered Data Management for HPC and AI Workloads”
Advisor: M. Mustafa Rafique
Given the high-quality of dissertations this year, the SIGHPC Doctoral Dissertation Award committee decided on an Honorable Mention award. The winner is Dr. Avinash Maurya for his work on optimizing large-scale data management across heterogeneous memory tiers and accelerating I/O performance for both classical HPC simulations and AI applications. Dr. Maurya obtained his Ph.D. in Computer Science at Rochester Institute of Technology. Prof. M. Mustafa Rafique was his advisor and Dr. Bogdan Nicolae from Argonne National Laboratory (ANL) his co-advisor. Presently, Dr. Maurya is post-doctoral researcher at the Mathematics and Computer Science Division at ANL, and a postdoc-at-large at the University of Chicago. He will receive a certificate at the SC'25 awards ceremony in honor of his achievement.
The ACM SIGHPC Doctoral Dissertation Award committee was composed of eight international HPC researchers: Ana Gainaru (Oak Ridge National Laboratory), Jeff Hammond (NVIDIA), Tanzima Islam (Texas State University), Shantenu Jha (Rutgers University), Allen D. Malony (Chair, University of Oregon), Sarah Neuwirth (Johannes Gutenberg University Mainz), Hari Subramoni (Ohio State University), and Rich Vuduc (Georgia Institute of Technology).