Murali Krishna Emani

Murali Krishna Emani is an Assistant Computer Scientist in the Data Science group at Argonne Leadership Computing Facility (ALCF) within Argonne National Laboratory. Previously, he served as a Postdoctoral Research Staff Member at Lawrence Livermore National Laboratory.

His research spans High Performance Computing, Scalable Machine Learning, and Emerging HPC architectures. Key interests include parallel programming models, runtime systems, and online adaptation for scientific applications. At ALCF, he co-leads the AI Testbed initiative exploring AI accelerator performance for scientific machine learning, and chaired the MLPerf HPC group at MLCommons for benchmarking large-scale ML on HPC systems.

His recent publications (2023-2025) reveal strong focus on LLM optimization (MoE inference, KV cache management), AI accelerator benchmarking, and scientific applications (climate modeling, protein design). The work demonstrates cross-cutting themes in hardware-software co-design and performance modeling for emerging architectures.

• ACM Gordon Bell Prize finalist for climate modeling (2025)
• Winner of ACM Gordon Bell Special Prize for HPC-based Covid-19 research (2022)

Emani actively mentors PhD students and postdocs, with advisees now faculty at Binghamton University, California State University, and researchers at NVIDIA, Microsoft, and national labs. His service includes program committees for SC, IPDPS, and AAAI conferences. Current projects focus on performance modeling for ML/DL frameworks on supercomputers, co-design of hardware architectures for ML algorithms, and benchmarking ML/DL frameworks on HPC systems.