PIMSIM-NN: An ISA-based Simulation Framework for Processing-in-Memory Accelerators
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910346779820032 |
|---|---|
| author | Wang, Xinyu Sun, Xiaotian Han, Yinhe Chen, Xiaoming |
| author_facet | Wang, Xinyu Sun, Xiaotian Han, Yinhe Chen, Xiaoming |
| contents | Processing-in-memory (PIM) has shown extraordinary potential in accelerating neural networks. To evaluate the performance of PIM accelerators, we present an ISA-based simulation framework including a dedicated ISA targeting neural networks running on PIM architectures, a compiler, and a cycleaccurate configurable simulator. Compared with prior works, this work decouples software algorithms and hardware architectures through the proposed ISA, providing a more convenient way to evaluate the effectiveness of software/hardware optimizations. The simulator adopts an event-driven simulation approach and has better support for hardware parallelism. The framework is open-sourced at https://github.com/wangxy-2000/pimsim-nn. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18089 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PIMSIM-NN: An ISA-based Simulation Framework for Processing-in-Memory Accelerators Wang, Xinyu Sun, Xiaotian Han, Yinhe Chen, Xiaoming Hardware Architecture Processing-in-memory (PIM) has shown extraordinary potential in accelerating neural networks. To evaluate the performance of PIM accelerators, we present an ISA-based simulation framework including a dedicated ISA targeting neural networks running on PIM architectures, a compiler, and a cycleaccurate configurable simulator. Compared with prior works, this work decouples software algorithms and hardware architectures through the proposed ISA, providing a more convenient way to evaluate the effectiveness of software/hardware optimizations. The simulator adopts an event-driven simulation approach and has better support for hardware parallelism. The framework is open-sourced at https://github.com/wangxy-2000/pimsim-nn. |
| title | PIMSIM-NN: An ISA-based Simulation Framework for Processing-in-Memory Accelerators |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2402.18089 |