Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.11021 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910745762988032 |
|---|---|
| author | Ni, Xiaobing Ge, Mengke Ruan, Jiaheng Chen, Song Kang, Yi |
| author_facet | Ni, Xiaobing Ge, Mengke Ruan, Jiaheng Chen, Song Kang, Yi |
| contents | Streaming coarse-grained reconfgurable array (CGRA) is a promising architecture for data/computing-intensive applications because of its fexibility, high throughput and efcient memory system. However,when accelerating sparse CNNs, the irregular input data demands inside sparse CNNs would cause excessive caching operations (COPs) and multi-cycle internal dependencies (MCIDs) between operations, declining the throughput of the streaming CGRA. We propose a mapping method for sparse CNNs onto streaming CGRA, SparseMap, which incorporates an efcient I/O data management along with operation scheduling and binding, to reduce the COPs and MCIDs, thereby ensuring the optimal throughput of streaming CGRA.The experimental results show SparseMap reduces 92.5% COPs and 46.0 % MCIDs while achieves the same or even smaller initiation interval (II) compared to previous works. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11021 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SparseMap: Loop Mapping for Sparse CNNs on Streaming Coarse-grained Reconfigurable Array Ni, Xiaobing Ge, Mengke Ruan, Jiaheng Chen, Song Kang, Yi Distributed, Parallel, and Cluster Computing Streaming coarse-grained reconfgurable array (CGRA) is a promising architecture for data/computing-intensive applications because of its fexibility, high throughput and efcient memory system. However,when accelerating sparse CNNs, the irregular input data demands inside sparse CNNs would cause excessive caching operations (COPs) and multi-cycle internal dependencies (MCIDs) between operations, declining the throughput of the streaming CGRA. We propose a mapping method for sparse CNNs onto streaming CGRA, SparseMap, which incorporates an efcient I/O data management along with operation scheduling and binding, to reduce the COPs and MCIDs, thereby ensuring the optimal throughput of streaming CGRA.The experimental results show SparseMap reduces 92.5% COPs and 46.0 % MCIDs while achieves the same or even smaller initiation interval (II) compared to previous works. |
| title | SparseMap: Loop Mapping for Sparse CNNs on Streaming Coarse-grained Reconfigurable Array |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2412.11021 |