Power is a limiting factor for supercomputers limiting their scale and operation. Characterizing the power signatures of different application types can enable data centers to operate efficiently, even when power constrained. This paper investigates power profiles of diverse scientific applications, spanning both traditional simulations and modern machine learning (ML) running on the Perlmutter supercomputer at the National Energy Research Scientific Computing Center (NERSC). Our findings indicate that traditional simulations typically consume more power on average than ML workloads. Furthermore, ML applications exhibit periodic power fluctuations attributed to epoch transitions during training. Finally, we discuss the potential implications of the research insights toward automatic demand response (ADR) and considerations for designing future systems.
12 July 2024 in IEEE Transactions on Parallel and Distributed Systems
DaCe is a framework for Python that claims to provide massive speedups with C-like speeds compared to already existing high-performance Python frameworks (e.g. Numba or Pythran). In this work, we take a closer look at reproducing the NPBench work. We use performance results to confirm that NPBench achieves higher performance than NumPy in a variety of benchmarks and provide reasons as to why DaCe is not truly as portable as it claims to be, but with a small adjustment it can run anywhere.