A Precision Emulation Approach to the GPU Acceleration of Ab Initio Electronic Structure Calculations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914435496411136 |
|---|---|
| author | Liu, Hang Li, Junjie Wang, Yinzhi Nepal, Niraj K. Wang, Yang |
| author_facet | Liu, Hang Li, Junjie Wang, Yinzhi Nepal, Niraj K. Wang, Yang |
| contents | This study explores the use of INT8-based emulation for accelerating traditional FP64-based HPC workloads on modern GPU architectures. Through SCILIB-Accel automatic BLAS offload tool for cache-coherent Unified Memory Architecture, we emulate FP64 matrix multiplications in the LSMS CPU application in the MuST suite without code changes. We find that accuracy depends on both arithmetic precision and the properties of the operator, which can be dealt with through tunable precision emulation. Unlike traditional mixed-precision approaches, this method preserves original algorithms while optimizing hardware utilization. We showcase the potential of improving accuracy and performance at the same time. This work highlights the potential of AI-driven hardware to transform HPC, advocating for adaptive precision strategies in future scientific computing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29975 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Precision Emulation Approach to the GPU Acceleration of Ab Initio Electronic Structure Calculations Liu, Hang Li, Junjie Wang, Yinzhi Nepal, Niraj K. Wang, Yang Distributed, Parallel, and Cluster Computing Performance Computational Physics This study explores the use of INT8-based emulation for accelerating traditional FP64-based HPC workloads on modern GPU architectures. Through SCILIB-Accel automatic BLAS offload tool for cache-coherent Unified Memory Architecture, we emulate FP64 matrix multiplications in the LSMS CPU application in the MuST suite without code changes. We find that accuracy depends on both arithmetic precision and the properties of the operator, which can be dealt with through tunable precision emulation. Unlike traditional mixed-precision approaches, this method preserves original algorithms while optimizing hardware utilization. We showcase the potential of improving accuracy and performance at the same time. This work highlights the potential of AI-driven hardware to transform HPC, advocating for adaptive precision strategies in future scientific computing. |
| title | A Precision Emulation Approach to the GPU Acceleration of Ab Initio Electronic Structure Calculations |
| topic | Distributed, Parallel, and Cluster Computing Performance Computational Physics |
| url | https://arxiv.org/abs/2603.29975 |