NDFT: Accelerating Density Functional Theory Calculations via Hardware/Software Co-Design on Near-Data Computing System
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910903598841856 |
|---|---|
| author | Jiang, Qingcai Tu, Buxin Hao, Xiaoyu Chen, Junshi An, Hong |
| author_facet | Jiang, Qingcai Tu, Buxin Hao, Xiaoyu Chen, Junshi An, Hong |
| contents | Linear-response time-dependent Density Functional Theory (LR-TDDFT) is a widely used method for accurately predicting the excited-state properties of physical systems. Previous works have attempted to accelerate LR-TDDFT using heterogeneous systems such as GPUs, FPGAs, and the Sunway architecture. However, a major drawback of these approaches is the constant data movement between host memory and the memory of the heterogeneous systems, which results in substantial \textit{data movement overhead}. Moreover, these works focus primarily on optimizing the compute-intensive portions of LR-TDDFT, despite the fact that the calculation steps are fundamentally \textit{memory-bound}.
To address these challenges, we propose NDFT, a \underline{N}ear-\underline{D}ata Density \underline{F}unctional \underline{T}heory framework. Specifically, we design a novel task partitioning and scheduling mechanism to offload each part of LR-TDDFT to the most suitable computing units within a CPU-NDP system. Additionally, we implement a hardware/software co-optimization of a critical kernel in LR-TDDFT to further enhance performance on the CPU-NDP system. Our results show that NDFT achieves performance improvements of 5.2x and 2.5x over CPU and GPU baselines, respectively, on a large physical system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03451 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NDFT: Accelerating Density Functional Theory Calculations via Hardware/Software Co-Design on Near-Data Computing System Jiang, Qingcai Tu, Buxin Hao, Xiaoyu Chen, Junshi An, Hong Hardware Architecture Computational Physics Linear-response time-dependent Density Functional Theory (LR-TDDFT) is a widely used method for accurately predicting the excited-state properties of physical systems. Previous works have attempted to accelerate LR-TDDFT using heterogeneous systems such as GPUs, FPGAs, and the Sunway architecture. However, a major drawback of these approaches is the constant data movement between host memory and the memory of the heterogeneous systems, which results in substantial \textit{data movement overhead}. Moreover, these works focus primarily on optimizing the compute-intensive portions of LR-TDDFT, despite the fact that the calculation steps are fundamentally \textit{memory-bound}. To address these challenges, we propose NDFT, a \underline{N}ear-\underline{D}ata Density \underline{F}unctional \underline{T}heory framework. Specifically, we design a novel task partitioning and scheduling mechanism to offload each part of LR-TDDFT to the most suitable computing units within a CPU-NDP system. Additionally, we implement a hardware/software co-optimization of a critical kernel in LR-TDDFT to further enhance performance on the CPU-NDP system. Our results show that NDFT achieves performance improvements of 5.2x and 2.5x over CPU and GPU baselines, respectively, on a large physical system. |
| title | NDFT: Accelerating Density Functional Theory Calculations via Hardware/Software Co-Design on Near-Data Computing System |
| topic | Hardware Architecture Computational Physics |
| url | https://arxiv.org/abs/2504.03451 |