- By:
- Godoy, William F; Hernandez Mendoza, Oscar R; Kent, Paul R; Patrou, Maria ; Asifuzzaman, Kazi ; Miniskar, Narasinga Rao ; Valero Lara, Pedro ; Vetter, Jeffrey S; Sinclair, Matthew; Lowe-Power, Jason; Bruce, Bobby
- Page Number:
- 177-190
- Volume:
- 16091
- Book Title:
- High Performance Computing. ISC High Performance 2025. Lecture Notes in Computer Science
- Publication Date:
- March 12, 2026
- Publisher Location:
- Springer Nature, Switzerland
- Conference Name:
- ISC High Performance 2025: International Conference on High Performance Computing
- Conference Location:
- Hamburg, Germany
- Conference Sponsor:
- ISC Group
- View DOI Listing:
- https://doi.org/10.1007/978-3-032-07612-0_14
Abstract
We characterize the GPU energy usage of two widely adopted exascale-ready applications representing two classes of particle and mesh solvers: (i) QMCPACK, a quantum Monte Carlo package, and (ii) AMReX-Castro, an adaptive mesh astrophysical code. We analyze power, temperature, utilization, and energy traces from double-/single (mixed)-precision benchmarks on NVIDIA’s A100 and H100 and AMD’s MI250X GPUs using queries in NVML and rocm_smi_lib, respectively. We explore application-specific metrics to provide insights on energy vs. performance trade-offs. Our results suggest that mixed-precision energy savings range between 6–25% on QMCPACK and 45% on AMReX-Castro. Also, we found gaps in the AMD tooling used on Frontier GPUs that need to be understood, while query resolutions on NVML have little variability between 1 ms-1 s. Overall, application level knowledge is crucial to define energy-cost/science-benefit opportunities for the codesign of future supercomputer architectures in the post-Moore era.
