Franz Franchetti is the Kavčić-Moura Professor of Electrical & Computer Engineering at Carnegie Mellon University. He serves as Associate Dean for Research and Director of the Engineering Research Accelerator at CMU. Education: Ph.D. in Computational Mathematics (Vienna University of Technology, 2003) M.Sc. in Technical Mathematics (Vienna University of Technology, 2000) His research interests focus on automatic performance tuning and program generation for emerging parallel computing platforms , including multicore CPUs , GPUs , and 3DIC chip design . He leads the SPIRAL effort to automate highly optimized software libraries and explores domain-specific compiler transformations in HPC applications for smart grids and material sciences . Recent work extends SPIRAL to quantum computing . The scientific awards Franchetti has received include the Gordon Bell Prize (2006) , HPC Challenge Class II Award (2010) , and the CIT Dean's Early Career Fellowship (2013) . He and his students have won multiple Best Paper Awards at HPEC, DAC, and ISPA ACM TODAES Best Paper (2014) Student Research Competition wins (PACT 2024, CGO 2023) Franchetti has advised students like Richard Veras and Thom Popovici . He has secured significant grants from agencies such as DARPA, DOE, NSF, and industry partners (Intel, NVIDIA, Mercury). He co-founded SpiralGen, Inc. and holds leadership roles in organizations like ASciNA Western Pennsylvania and as Honorary Consul of Austria in Pittsburgh.
Garth Gibson is a Professor in the Computer Science Department and Department of Electrical and Computer Engineering at Carnegie Mellon University's School of Computer Science. He serves as Co-Director of the Master of Computational Data Science program and as Associate Dean for Master's Programs. Gibson has been a faculty member at CMU since 1991, after receiving his Ph.D. and M.Sc. in Computer Science from the University of California at Berkeley and a Bachelor of Mathematics in Computer Science and Applied Mathematics from the University of Waterloo. Gibson's research focuses on large-scale parallelism in computer systems, secondary memory system technologies and optimization, scalable file and key-value storage systems, scalable machine learning, and systematic testing for large scale systems. His work bridges theoretical concepts with practical implementations, with a strong emphasis on shepherding technological advances from academic research to commercial reality. He has made significant contributions to RAID technology, network-attached secure disks (NASD), and parallel file systems that have shaped industry standards and products. Gibson's recent publications reveal a strong trend toward data-intensive scalable computing, with increasing focus on machine learning systems, distributed storage solutions, and high-performance computing infrastructure. His research has evolved from foundational storage technologies to address the challenges of petascale and exascale computing environments, with particular attention to the intersection of storage systems and machine learning workloads. The papers demonstrate a consistent theme of addressing system scalability challenges through innovative architectural approaches. Scientific Awards: 2014 Fellow of the IEEE for contributions to the performance and reliability of transformative storage systems 2012 Fellow of the ACM for contributions to the performance and reliability of storage systems 2012 Jean-Claude Laprie Award in Dependable Computing Industrial/Commercial Product Impact Category 2011 SIGOPS Hall of Fame for the SIGMOD88 RAID paper 1999 Reynold B. Johnson Information Storage Award 1999 Allan Newell Award for Research Excellence 1998 Test of Time Award 1991 A.C.M. Doctoral Dissertation Award (tied for second) Gibson has advised numerous graduate students who have gone on to influential positions in both academia and industry, including Swapnil Patil who won first place in the 2010 ACM Graduate Student Research Competition. He has secured significant research funding through initiatives like the DOE Petascale Data Storage Institute and the Intel Science and Technology Center for Cloud Computing. His research has been supported by collaborations with national laboratories including Los Alamos, Sandia, Oak Ridge, Pacific Northwest, and Lawrence Berkeley. Gibson founded CMU's Parallel Data Laboratory (PDL) in 1993, which has grown into a vibrant research community comprising 6-9 faculty members, 2-3 dozen students, and 4-10 staff. The PDL operates with guidance from the Parallel Data Consortium, which includes 15-25 companies interested in parallel data systems. He also founded Panasas Inc. in 1999, a scalable storage cluster company that has deployed technology in national laboratories, energy sectors, and other high-performance computing environments. More recently, Gibson established the Big Learning research group and created the Systems Major curriculum within CMU's Master of Computational Data Science program.
Tze Meng Low is an Associate Research Professor in the Department of Electrical and Computer Engineering at Carnegie Mellon University (CMU), part of the College of Engineering. His research focuses on high-performance algorithms, formal methods, and hardware-software co-design, with an emphasis on achieving performance portability across architectures. He holds a Ph.D. and M.S. in Computer Science and dual B.A./B.S. degrees in Economics and Computer Science from the University of Texas at Austin. His research interests span parallel computing, graph algorithms, machine learning, and cyber-physical systems. He has contributed to projects like the DARPA BRASS initiative, collaborating on adaptive software systems for resource-challenged environments. His work also involves developing tools such as SMaLL and qLD, which address challenges in machine learning library instantiation and genomic analysis. Low has received the Dean’s Early Career Fellowship (2022) and led the $2.7M DARPA-funded BRASS project (2016–2020), supported by SpiralGen, Inc. and academic collaborators. His contributions include code generation frameworks like SPIRAL and advancements in linear algebra-based graph algorithms, emphasizing analytical models and automated code optimization. His research bridges theoretical formal methods with practical implementations, aiming to enhance software reliability and scalability in emerging domains. Collaborations include work on fault-tolerant coded computing and high-assurance systems for cyber-physical applications.
George Amvrosiadis is a Research Professor in the Department of Electrical and Computer Engineering at Carnegie Mellon University, with a courtesy appointment in Computer Science. He is a core member of the Parallel Data Lab and spends part of his time at Amazon S3 as an Amazon Scholar. Education: 2016 - Ph.D., Computer Science, University of Toronto 2009 - BA, Computer Science, University of Ioannina Research Interests: His work focuses on distributed systems , operating systems , data analysis , cloud computing , and storage technologies . He explores high performance computing (HPC), zoned storage , systems security , and storage solutions for machine learning . Scientific Trends: Articles highlight innovations in storage systems, including zoned storage , HPC data services , and machine learning infrastructure . Research spans distributed systems , I/O optimization , and data integrity in large-scale environments. Scientific Awards: DeltaFS project received the R&D 100 Award from R&D World Magazine Teaching & Service: He co-teaches graduate courses on storage and cloud systems, serves on program committees for top conferences (SOSP, OSDI, FAST), and mentors students in systems research and infrastructure projects.
Gregory Ganger is the Stephen J. Jatras Professor at Carnegie Mellon University's College of Engineering, holding joint affiliations with the Computer Science Department and CyLab. He has served as Director of the Parallel Data Lab (PDL) since 2000 and teaches Storage Systems (Fall) and Advanced Cloud Computing (Spring) courses. Education: Ph.D. in Computer Science & Engineering (1995, University of Michigan) M.S. in Computer Science & Engineering (1993, University of Michigan) B.S. in Computer Science (1991, University of Michigan) Dr. Ganger's research spans computer systems, focusing on: cloud computing, distributed systems, storage architectures, and machine learning infrastructure. His work addresses challenges in resource scheduling, non-volatile memory optimization, and scalable infrastructure design through projects like BigLearning, CILES, HeART, and Zoned Storage systems. Recent publications demonstrate expertise in: DNN training optimization (GraphPipe, Nonuniform-Tensor-Parallelism), sustainable storage (Storage Emissions, FairyWREN), and cloud efficiency (MACARON Cache). These works intersect machine learning, storage systems, and hardware-software co-design. Scientific Awards: 2021 OSDI Best Paper 2021 SOSP Best Paper 2021 SoCC Test of Time Award 2021 R&D 100 Award As advisor to 8 graduate students, he contributes to training the next generation of systems researchers. His lab (PDL) collaborates with industry partners on cutting-edge storage and cloud infrastructure problems.
