Short Bio

Dr. Sohan Lal is a Junior Professor and Head of the Institute for Massively Parallel Systems at Hamburg University of Technology (TUHH). Before joining TUHH, he was a postdoctoral researcher at the Technical University of Berlin (TU Berlin), where he worked on the DFG-funded project Celerity, focusing on advanced modeling and runtime support for large-scale HPC clusters. He earned his Ph.D. in Computer Science from TU Berlin in 2019 under the supervision of Prof. Ben Juurlink. His dissertation, titled “Power Modeling and Architectural Techniques for Energy-Efficient GPUs,” investigated GPU bottlenecks and proposed architectural solutions for improved performance and energy efficiency. His research has been published in leading venues such as IPDPS, DATE, and ISPASS.

During his Ph.D., Dr. Lal contributed significantly to two EU-funded projects on low power parallel computing on GPUs (LPGPU), where he led technical tasks, collaborated with international partners, and co-authored several key deliverables. He received multiple HiPEAC travel and collaboration grants, including one that led to a joint publication with Prof. Henk Corporaal’s group at TU Eindhoven. He was also a semifinalist at the ACM Student Research Competition at MICRO 2018.

Dr. Lal’s broader research interests lie in computer architecture, with a particular focus on GPU and heterogeneous architectures. His work spans power and performance modeling, memory systems, parallel computing, approximate computing, applied machine learning, and GPU security.

Prior to his Ph.D., he earned a master’s degree in Information Technology from the Indian Institute of Technology Delhi (IITD) in 2011. He began his academic career as a Lecturer at Shri Mata Vaishno Devi University (SMVDU), which sparked his passion for teaching and mentorship. He also worked as an IT specialist for the Government of India. Dr. Lal completed his undergraduate studies in Computer Science and Engineering at Government College of Engineering and Technology (GCET), Jammu, in 2003.

Education

  • 🎓 Ph.D. (Dr.-Ing.) in Computer Science, 2019, Technical University of Berlin
  • 🎓 M.S (Research) in Information Technology, 2011, Indian Institute of Technology Delhi
  • 🎓 B.Tech in Computer Science & Engineering, 2003, Govt. College of Engineering & Technology Jammu

Invited Talks

On Performance and Energy Efficiency of GPUs

  • Technical University of Hamburg, November 2020
  • Queens University of Belfast, January 2020

A Perspective on Performance, Power, and Energy Efficiency of GPUs

  • Shri Govindram Seksaria Institute of Technology and Science, SGSITS, Indore, June 2020

Architectural Techniques for Energy-Efficient GPUs

  • RWTH Aachen, April 2019
  • Indian Institute of Technology Jammu, March 2019
  • Indian Institute of Technology Ropar, March 2019
  • Technical University of Dresden, February 2019

Conference Talks

  • QSLC: Quantization-Based, Low-Error Selective Approximation for GPUs (DATE’21)
  • SYCL-Bench: A Versatile Cross-Platform Benchmark Suite for Heterogeneous Computing (Euro-Par’20)
  • A Quantitative Study of Locality in GPU Caches (SAMOS’20)
  • Memory Access Granularity Aware Selective Lossy Compression for GPUs (DATE’19)
  • A Case for Memory Access Granularity Aware Selective Lossy Compression for GPUs (MICRO’18)
  • E2MC: Entropy Encoding Based Memory Compression for GPUs (IPDPS’17)
  • GPGPU Workload Characteristics and Performance Analysis (SAMOS’14)
  • Exploring GPGPU Workload Characteristics and Power Consumption (ACACES’13)
  • A Framework for Modeling GPU Power Consumption (HiPEAC’13)