Papers for

electronic design automation teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Exact solver finds optimal terminal placement in 3d chip design quickly

Provably Optimal HBT Legalization in Seconds: Certified Optima Reveal Where the Headroom Really Lies

Abstract: Hybrid bonding terminal (HBT) legalization assigns every terminal of a face-to-face 3D IC to its own pitch-grid site with minimum total Manhattan displacement. Open3DBench reports that a reinforcement-learning (RL) legalizer reduces displacement by 19-22% relative to a sliding-window (SW) heuristic, but none of its legalizers is publicly released. We ask how much displacement any legalizer can still recover. We build an open benchmark of 21 design/pitch instances from Open3DBench placement data, with reconstructed greedy, SW (ViaLegal-style) and BTAssign-style baselines, and GEO-Exact, an exact solver that runs successive shortest augmenting paths over lazily generated spatial candidate edges. An independent dual certificate proves its assignment optimal on all 21 instances (relative primal-dual gap at most $8.2 \times 10^{-16}$). Against these optima, our SW reconstruction with ViaLegal's default configuration is on average 0.011% above optimal (worst 0.119%), while on the 16 contended instances BTAssign-style, a density-guided heuristic (DGHL) and greedy are 3.0%, 6.9% and 64.5% above. Headroom does appear outside this regime: with 2x2 windows SW reaches 34.1%, and above about 58% utilization, on three of six swept designs, it reaches 21.1% on bp, 27.5% on swerv and 8.9% on jpeg (217 further certified instances, and ten bp points checked against an independent exact solver). If the published 19-22% gain were measured on instances like ours, SW would have to be at least 24-28% above optimal on average, far more than any SW variant we tested at nominal pitch; the RL paper's own comparison with the Hungarian optimum puts its SW 3.05% above optimal on average. GEO-Exact is also about an order of magnitude faster than DGHL and SW in our harness (geometric means 8.1x and 40x; a compiled core against Python baselines on a shared server). Code, optimal values and certificates are released.

Wed 11 NovArtificial Intelligence
The gist
Placing tiny connection points, or terminals, on 3D chips is tricky and usually done with approximate methods that can be off by a bit. The authors built a tool called GEO-Exact that finds the best possible arrangement very quickly, proving exactly how close other methods come to the ideal. They tested it on a set of real design cases and confirmed their results with mathematical proofs. This helps chip designers know how much room for improvement their current placement methods really have.
Open → 2611.14928v1

Ai agents evaluated on real chip floorplanning quality and validity

Evaluating AI Agents for Industrial-Level Chip Floorplanning: A Framework and Empirical Study

Abstract: Floorplanning is an early step in turning a logical circuit into a physical chip: it positions large circuit modules and constrains the space available for subsequent logic placement and wiring. These decisions affect congestion and timing, but their physical consequences emerge through downstream implementation. For AI agents, the task requires translating engineering constraints into spatial decisions whose quality cannot be judged by successful tool execution alone. We present an evaluation framework that connects submitted layouts to a prescribed downstream implementation flow, checks geometric validity, measures physical quality, and reports resource use. On one industrial design whose 99 macros occupy approximately 71\% of a fixed L-shaped layout region, we compare our specialized system Nova-SI with general-purpose engineering agents and agents restricted to file access, obtaining complete physical measurements for 39 layout outputs. Under our 0--100 composite quality score, Nova-SI achieves a mean of 57.97 without online feedback from the prescribed power-grid and placement evaluation, compared with 31.17 for the strongest measured general-purpose configuration, GPT-6 Astra. The difference is supported by raw congestion and timing measurements and persists across scoring-sensitivity checks. Layout-level analysis further shows that similar global utilization can conceal substantially different local congestion. Together, the protocol and case study assess agents through the physical consequences of their delivered layouts and provide evidence about system performance on this industrial instance.

Mon 9 NovArtificial Intelligence
The gist
Designing a computer chip involves arranging large parts so everything fits and works well later. The authors created a way to measure how well AI can do this, checking if the layouts are valid and how they affect things like wiring and speed. They tested several AI systems on a real industrial chip design and found their specialized system performed much better than general AI. This helps understand how AI can assist in chip design by looking at the actual physical effects, not just if the software runs.
Open → 2611.12048v1

AutoC2V improves hardware design by guiding code to circuitry generation

AutoC2V: Synthesis-Guided LLM Training for QoR-Optimized C++-to-Verilog Generation

Abstract: High-level synthesis (HLS) can translate C/C++ kernels into register-transfer level (RTL) designs, yet generating high-quality hardware still relies heavily on manual pragma tuning and repeated synthesis evaluation. We propose AutoC2V, a C++-to-Verilog generation framework driven by real synthesis feedback that enables large language models (LLMs) to directly generate RTL with improved quality of results (QoR) from synthesizable C++ kernels. We construct training data from real synthesis results, including synthesizable C++ source code, the corresponding Verilog RTL, QoR metrics, and optimization objectives. Using this dataset, we align the model toward synthesis-aware RTL generation through Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO). To reduce the high cost of repeatedly invoking real synthesis during GRPO, we design the QoR Prediction Reward Model (QoR RM), which predicts latency and resource metrics by encoding RTL into long-context semantic representations, thereby providing low-cost and continuous QoR reward signals for policy optimization. Experimental results demonstrate that AutoC2V not only substantially improves RTL functional pass rates, but also achieves superior latency and resource optimization compared to the unfine-tuned base model, representative HLS optimization approaches (HLSPilot, LLM-DSE, and AutoDSE), and advanced general-purpose commercial models (Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro, DeepSeek v4 Pro, and GLM-5.2). These results indicate that combining real synthesis data with efficient QoR reward modeling can further improve the ability of LLMs to generate high-quality RTL.

Sat 7 NovHardware ArchitectureMachine Learning
The gist
Generating hardware designs from C++ code can be slow and tricky because designers tweak settings manually to get good performance. The authors created AutoC2V, a method that teaches large language models to directly produce better hardware circuitry from C++ by learning from real hardware synthesis results. They also made a tool to quickly estimate how well a design will perform without running full hardware checks every time. AutoC2V showed better success rates and produced designs with faster speeds and smaller sizes than other methods and popular AI models.
Open → 2611.10824v1

LLM-guided framework recovers exact high-level RTL from low-level designs

RTLREX: LLM-Guided Framework for Exact High-Level RTL Recovery

Abstract: Hardware designs may be available only as gate-level netlists or input-output descriptions when the original register-transfer-level (RTL) design and documentation are not accessible. Low-level representations obscure word-level computation and its finite-width behavior. Recovering high-level RTL from such representations therefore helps engineers understand a circuit's functionality and enables RTL rewriting and resynthesis. A plausible function model is also insufficient unless the generated RTL is equivalent to the original circuit for all input combinations. In this paper, we present RTLREX, a large language model (LLM)-guided framework that coordinates domain-specific tools for function recovery, RTL generation, independent verification, and cost-guided rewriting. Independent verification establishes equivalence between the recovered RTL and the original circuit. The LLM uses tool feedback to select further analyses, revise candidate RTL, and propose syntax-cost reductions. Experiments on 30 benchmarks from Problem A of the ICCAD 2022 CAD Contest show that RTLREX recovers equivalent high-level RTL for all benchmarks, surpassing the state-of-the-art method WolFEx in recovery coverage. On benchmarks recovered by both methods, RTLREX reduces mean syntax cost by 20.5% relative to WolFEx. On complete truth-table benchmarks from the IWLS 2026 Contest, our framework reduces mean syntax cost by 95.7% relative to an LLM agent baseline on the benchmarks validated by both methods.

Sat 7 NovHardware ArchitectureArtificial Intelligence
The gist
Sometimes engineers only have very detailed, low-level circuit descriptions without the original high-level code that explains what the circuit really does. This makes it hard to understand and improve those circuits. The authors created a system called RTLREX that uses a large language model along with specialized tools to rebuild the original high-level design exactly and verify it works perfectly. Their system outperforms previous methods in recovering these designs accurately and more simply.
Open → 2611.10798v1

DiffRouter speeds up FPGA routing with new gradient method

DiffRouter: A Differentiable Routing Framework for UltraScale FPGAs

Abstract: Routing has become a major bottleneck in large-scale FPGA design flows, where traditional routers rely on sequential net-by-net processing and rip-up-reroute heuristics. This inherent sequentialism limits parallelism, leads to suboptimal utilization of routing resources, and significantly increases runtime on modern FPGAs. This paper introduces DiffRouter, the first differentiable, gradient-based FPGA routing framework with GPU acceleration. By lifting routing into a continuous optimization space, DiffRouter enables highly concurrent routing and improved global optimality before projecting solutions back onto the discrete fabric. The framework consists of three key stages: (1) Resource-pruned preprocessing, which extracts compact routing variables per net to reduce memory footprint and problem complexity; (2) Differentiable global routing via gradient descent, which formulates routing as a Lagrangian-relaxed optimization that minimizes wirelength while iteratively enforcing connectivity and congestion constraints as relaxed terms; and (3) Postprocessing, which maps the continuous wire distributions to a valid UltraScale routing solution and completes solutions by detailed routing. Experiments on the FPGA 2024 Routing Contest benchmarks show that DiffRouter outperforms state-of-the-art parallel routers, achieving over 5x speedup over RWRoute and 2x over Vivado, and running 18% faster than the state-of-the-art academic FPGA router Potter while delivering competitive critical path wirelength.

Sat 24 OctHardware Architecture
The gist
Routing electrical connections on very large FPGAs can be slow and inefficient because traditional methods handle one connection at a time and rely on trial-and-error fixes. The authors created DiffRouter, which treats routing as a continuous problem that can be solved all at once using gradients and GPUs, making it much faster. After this smooth optimization, it converts the solution back into real, usable FPGA connections. Tests show DiffRouter runs several times faster than existing tools while keeping wiring efficient.
Open → 2610.33510v1

Open analog dataset enables better machine learning for circuit design

LOADBench: A Large Open Analog Dataset and Benchmark for Machine Learning in IC Design

Abstract: Machine learning (ML) for analog IC design is constrained by limited open data and the absence of standardized evaluation: results reported in different papers are typically obtained on bespoke, often closed, datasets and with ad-hoc metrics, leaving comparisons across methods unreliable. We address both gaps with a large opensource dataset and a suite of standardized benchmarks. The dataset contains more than 100 operational amplifier (opamp) topologies (1-, 2-, and 3-stage) in the SkyWater130 PDK, each shipped with structural and functional annotations, topology-specific sizing constraints (symmetry and sizing rules), an Ngspice testbench, and a multi-objective NSGA-II sizing run producing around 103 Pareto-optimal and 106 intermediate sizing-performance pairs per topology. On top of this data we define six benchmark tasks with precise protocols: inverse sizing, topology selection, sub-circuit classification, structural circuit generation, Pareto-membership prediction, and multi-objective optimization. Thus, the data presented here constitutes the most comprehensive dataset for ML development in over four decades of analog IC design automation. The dataset, ground-truth annotations, and reference implementations of the metric-defining routines are released under an open license, enabling reproducible and directly comparable evaluation across heterogeneous analog design automation methods.

Thu 15 OctArtificial Intelligence
The gist
Designing analog circuits is hard because there’s very little public data to help computers learn how to do it. The authors created a big open dataset with many types of operational amplifiers, including detailed information and test results. They also made clear tasks and rules so different methods can be fairly compared. This work aims to make computer-aided analog circuit design more accessible and reliable by providing a shared resource.
Open → 2610.21591v1

Vision language model improves analog circuit layout analysis by 73 percent

THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout

Abstract: The integration of artificial intelligence into computer-aided design frameworks has sparked a shift in the design of analog integrated circuits (ICs), transitioning the field from using manual and algorithmic-based solutions to adopting automated and intelligent paradigms. In this scenario, the GDSII file represents the industry-standard database containing the ultimate and most accurate source of information of the analog circuit, encapsulating the complex physical geometries and parasitic realities that define tape out performance. This paper proposes THEIA, a novel dataset containing thousands of layout images paired with question-answer conversations, along with a benchmark that employs a fine-tuned vision-language model (VLM) to analyze GDSII files of analog circuits, enabling designers to interact with and query physical layouts as intuitive, meaningful entities. Experimental results using thousands of analog designs across five realistic tasks demonstrate that the proposed fine-tuned VLM outperforms state-of-the-art general-purpose VLMs by a significant margin (up to 73%), highlighting a fundamental gap between general-purpose multimodal reasoning and domain-specific layout understanding.

Mon 28 SeptMachine Learning
The gist
Understanding complex analog circuit layouts is hard because they contain detailed physical shapes that define how circuits work. The authors created THEIA, a big dataset of layout pictures with question and answer pairs to help computers learn these designs better. They used a special vision-language model fine-tuned for analog circuit layouts and showed it performs much better than general models. This means designers can ask questions about circuit layouts in a more natural and helpful way.
Open → 2609.35035v1