Understanding the Impact of Input Entropy on FPU, CPU, and GPU Power

S Bhalachandra, B Austin, S Williams… - arxiv preprint arxiv …, 2022 - arxiv.org
Power is increasingly becoming a limiting resource in high-performance, GPU-accelerated
computing systems. Understanding the range and sources of power variation is essential in …

Power analysis of nersc production workloads

Z Zhao, E Rrapaj, S Bhalachandra, B Austin… - Proceedings of the SC' …, 2023 - dl.acm.org
Power has become a key limiting factor in supercomputing. Understanding the power
signatures of current production workloads is essential to address this limit and continue to …

Power Consumption Trends in Supercomputers: A Study of NERSC's Cori and Perlmutter Machines

E Rrapaj, S Bhalachandra, Z Zhao… - ISC High …, 2024 - ieeexplore.ieee.org
The rising power demands of supercomputers put high importance on understanding the
underlying sources of power use. We compare a comprehensive set of power …

NPAT-A Power Analysis Tool at NERSC

A Zhang, S Bhalachandra, S Deng, Z Zhao - … of the SC'23 Workshops of …, 2023 - dl.acm.org
Power has recently become a significant limiting factor in supercomputing. It is imperative
that future high-performance computing (HPC) systems are energy-efficient. Efficient system …

Models and Techniques for Green High-Performance Computing

V Adhinarayanan - 2020 - vtechworks.lib.vt.edu
High-performance computing (HPC) systems have become power limited. For instance, the
US Department of Energy set a power envelope of 20MW in 2008 for the first exascale …