Szilard Pall

Szilárd Páll is an HPC software scientist at the KTH Center for Scientific Computing (KCSC)at KTH Royal Institute of Technology. His work combines deep contributions to molecular-dynamics algorithms with broader research on parallel algorithms and software for heterogeneous, large-scale HPC systems.

 

As a core developer of GROMACS, he helped reformulate key molecular-dynamics algorithms for modern processor architectures and was an early architect of its heterogeneous GPU acceleration. His contributions continue to shape GROMACS’ parallelization design, enabling it to exploit emerging computing technologies while delivering high performance on contemporary HPC systems. He has also played a key role in advancing portability and performance portability of GROMACS, from its original OpenCL backend to the current SYCL backend.

 

Szilárd established and leads the long-running GROMACS–NVIDIA academic-industry co-design collaboration, translating emerging hardware and programming technologies into production scientific-software capabilities. Drawing on his long-standing expertise in parallel algorithm design for molecular dynamics, he has extended his impact to other scientific domains, contributing to the heterogeneous parallelization design and scalability of the Neko CFD code.

 

His current work focuses on GPU-native communication for strong scaling of molecular-dynamics simulations and performance portability. He co-organizes the APerOL minisymposium serieson performance-portable scientific software. His growing focus on energy-efficient algorithms for scientific computing is pursued as PI of the SSF-funded Swedish Energy-Efficient Scientific Software Initiative (SEESSI).