Enhancing CGRA Efficiency Through Aligned Compute and Communication Provisioning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915060438269952 |
|---|---|
| author | Li, Zhaoying Dangi, Pranav Yin, Chenyang Bandara, Thilini Kaushalya Juneja, Rohan Tan, Cheng Bai, Zhenyu Mitra, Tulika |
| author_facet | Li, Zhaoying Dangi, Pranav Yin, Chenyang Bandara, Thilini Kaushalya Juneja, Rohan Tan, Cheng Bai, Zhenyu Mitra, Tulika |
| contents | Coarse-grained Reconfigurable Arrays (CGRAs) are domain-agnostic accelerators that enhance the energy efficiency of resource-constrained edge devices. The CGRA landscape is diverse, exhibiting trade-offs between performance, efficiency, and architectural specialization. However, CGRAs often overprovision communication resources relative to their modest computing capabilities. This occurs because the theoretically provisioned programmability for CGRAs often proves superfluous in practical implementations.
In this paper, we propose Plaid, a novel CGRA architecture and compiler that aligns compute and communication capabilities, thereby significantly improving energy and area efficiency while preserving its generality and performance. We demonstrate that the dataflow graph, representing the target application, can be decomposed into smaller, recurring communication patterns called motifs. The primary contribution is the identification of these structural motifs within the dataflow graphs and the development of an efficient collective execution and routing strategy tailored to these motifs. The Plaid architecture employs a novel collective processing unit that can execute multiple operations of a motif and route related data dependencies together. The Plaid compiler can hierarchically map the dataflow graph and judiciously schedule the motifs. Our design achieves a 43% reduction in power consumption and 46% area savings compared to the baseline high-performance spatio-temporal CGRA, all while preserving its generality and performance levels. In comparison to the baseline energy-efficient spatial CGRA, Plaid offers a 1.4x performance improvement and a 48% area savings, with almost the same power. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08137 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing CGRA Efficiency Through Aligned Compute and Communication Provisioning Li, Zhaoying Dangi, Pranav Yin, Chenyang Bandara, Thilini Kaushalya Juneja, Rohan Tan, Cheng Bai, Zhenyu Mitra, Tulika Hardware Architecture Coarse-grained Reconfigurable Arrays (CGRAs) are domain-agnostic accelerators that enhance the energy efficiency of resource-constrained edge devices. The CGRA landscape is diverse, exhibiting trade-offs between performance, efficiency, and architectural specialization. However, CGRAs often overprovision communication resources relative to their modest computing capabilities. This occurs because the theoretically provisioned programmability for CGRAs often proves superfluous in practical implementations. In this paper, we propose Plaid, a novel CGRA architecture and compiler that aligns compute and communication capabilities, thereby significantly improving energy and area efficiency while preserving its generality and performance. We demonstrate that the dataflow graph, representing the target application, can be decomposed into smaller, recurring communication patterns called motifs. The primary contribution is the identification of these structural motifs within the dataflow graphs and the development of an efficient collective execution and routing strategy tailored to these motifs. The Plaid architecture employs a novel collective processing unit that can execute multiple operations of a motif and route related data dependencies together. The Plaid compiler can hierarchically map the dataflow graph and judiciously schedule the motifs. Our design achieves a 43% reduction in power consumption and 46% area savings compared to the baseline high-performance spatio-temporal CGRA, all while preserving its generality and performance levels. In comparison to the baseline energy-efficient spatial CGRA, Plaid offers a 1.4x performance improvement and a 48% area savings, with almost the same power. |
| title | Enhancing CGRA Efficiency Through Aligned Compute and Communication Provisioning |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2412.08137 |