Into the Third Dimension: Architecture Exploration Tools for 3D Reconfigurable Acceleration Devices
Bibliographic record
Abstract
Recent chip integration processes enable 3D stacking of multiple active dice in the same package, offering higher logic density, lower power consumption, and significant die-to-die bandwidth. Field-programmable gate arrays (FPGAs) can benefit from 3D chip integration either by stacking multiple homogeneous FPGA fabrics to increase logic capacity or by integrating with other heterogeneous application-specific integrated circuits (ASICs). This opens up a myriad of research questions and interrelated design choices. However, we lack the tools necessary to model these 3D reconfigurable devices and quantitatively explore their vast design space. In this work, we enhance existing FPGA architecture exploration tools and build new ones to address this gap, with a cross-stack focus on circuit-level fabric modeling, 3D integration considerations, system-level architecture, and computer-aided design (CAD) tools. We extend the RAD-Gen framework by integrating an upgraded version of the COFFE automatic transistor sizing tool that supports 7 nm FinFETs with a more accurate, metal-aware area model for newer process technologies. We also implement new tools in RAD-Gen for modeling the inter-die connections and power distribution networks of 3D architectures. In addition, we introduce a new version of the Versatile Place & Route (VPR) tool that can model 3D devices, with enhancements to its architecture description language and its placement and routing engines. Finally, we showcase the capabilities of our enhanced tools by modeling and evaluating both homogeneous and heterogeneous 3D reconfigurable devices.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".