Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.01078 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917377938030592 |
|---|---|
| author | Hao, Cong Kahng, Andrew B. Pramanik, Bodhisatta Youssef, Ismael |
| author_facet | Hao, Cong Kahng, Andrew B. Pramanik, Bodhisatta Youssef, Ismael |
| contents | 3D field-programmable gate arrays (FPGAs) promise higher performance through vertical integration. However, existing placement tools, largely inherited from 2D frameworks, fail to capture the unique delay characteristics and optimization dynamics of 3D fabrics. We introduce a 3D FPGA placement flow that integrates partitioning-based initialization, adaptive cost scheduling, refined delay estimation, and a simulated annealing move set -- all targeted at 3D FPGA architecture. Together, these enhancements improve timing estimates and the exploration of layer assignments during placement. Compared to Verilog-To-Routing (VTR), our experiments show geometric-mean (max) critical-path delay reductions of ~3% (~7%), ~2% (~4%), ~3% (~8%), and ~6% (~18%) for four 3D architectures: 3D CB, 3D CB-O, 3D CB-I, and 3D SB, respectively. We also achieve geometric-mean (max) routed wirelength reductions of ~1% (~3%), ~2% (~8%), < 1% (~5%), and ~5% (~10%), respectively. Our work will be permissively open-sourced on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01078 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Escaping Flatland: A Placement Flow for Enabling 3D FPGAs Hao, Cong Kahng, Andrew B. Pramanik, Bodhisatta Youssef, Ismael Hardware Architecture 3D field-programmable gate arrays (FPGAs) promise higher performance through vertical integration. However, existing placement tools, largely inherited from 2D frameworks, fail to capture the unique delay characteristics and optimization dynamics of 3D fabrics. We introduce a 3D FPGA placement flow that integrates partitioning-based initialization, adaptive cost scheduling, refined delay estimation, and a simulated annealing move set -- all targeted at 3D FPGA architecture. Together, these enhancements improve timing estimates and the exploration of layer assignments during placement. Compared to Verilog-To-Routing (VTR), our experiments show geometric-mean (max) critical-path delay reductions of ~3% (~7%), ~2% (~4%), ~3% (~8%), and ~6% (~18%) for four 3D architectures: 3D CB, 3D CB-O, 3D CB-I, and 3D SB, respectively. We also achieve geometric-mean (max) routed wirelength reductions of ~1% (~3%), ~2% (~8%), < 1% (~5%), and ~5% (~10%), respectively. Our work will be permissively open-sourced on GitHub. |
| title | Escaping Flatland: A Placement Flow for Enabling 3D FPGAs |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2604.01078 |