arXiv subjects

Keren Zhu

Publications and source records attributed to Keren Zhu.

13 recordsLinked to original sources

arXiv2026

Differentiable Partitioning with Placement and Hybrid Bonding Terminal Awareness for Optimized 3D Placement

Research on 3D-ICs physical design has expanded rapidly in recent years. Hybrid bonding-enabled 3D integrated circuits (3D-ICs) offer substantial benefits in interconnect scaling and system integration, yet tier assignment remains challenging because it jointly determines 3D wirelength and hybrid bonding terminal (HBT) assignment. This paper presents a differentiable partitioning framework that directly optimizes placement-aware tier assignment for 3D-ICs through gradient-based optimization. Discrete tier assignment is relaxed to continuous probabilities, and a Dual-Max 3D wirelength model is introduced to capture per-tier half-perimeter wirelength (HPWL). In addition, a terminal-aware cutsize penalty selectively suppresses cross-die nets in HBT-congested regions, and a local balance constraint enforces grid-cell density equilibrium across tiers. Experimental results on OpenROAD benchmarks show that our method reduces D2D HPWL by 2.0% on average over two min-cut baselines and by 12.1% over the state-of-the-art 3D placer. We open-source our partition code with 3D placement flow to support reproducibility.

cs.ET↗

arXiv2026

Rethinking Logic Optimization Operators: Theory-Derived Operator Compression via Agentic Source Analysis

Logic synthesis has evolved from compact two-level minimization to large multilevel flows with many interacting optimization operators. Recent work has invested substantial effort in sequencing these operators: actions are commonly treated as opaque choices in a rapidly expanding search space, while learned circuit representations and heuristic or local-greedy orchestration provide increasingly informed ways to explore it. A central obstacle is the operator vocabulary itself. Production operators are numerous, span different representations and mathematical foundations, and expose behaviors determined by implementation-level guards, bounds, and update order. We address this gap through agentic source analysis, using LLM agents to formulate operator-level relations from pinned ABC and mockturtle implementations and adversarial audits to test their stated scope. The resulting certified relations yield theory-derived operator compression: 40 deployed recipe actions collapse to a 31-action exact Pareto cover, and source-level conditions compile into deterministic admission gates. We integrate these gates directly into ABC Orchestrate to form TACO. Two exact gates reduce Orchestrate runtime by 11% with bit-identical outputs on 66 circuits. In a held-fixed integrated comparison, TACO uses fewer nodes on 14 of 16 circuits, with geometric-mean reductions of 1.0% in nodes and 3.2% in levels, while running 2.6x faster. TACO-max achieves an NDP geometric-mean ratio of 0.903 on HeLO's three exact-input rows.

cs.LO↗

arXiv2026

Provably Good Prim-Dijkstra Revisited: New Theory and a Practical Algorithm for a Classical VLSI Routing Problem with LLMs

Large language models may make precise but dormant algorithmic problems practical to revisit, and may expose new paths toward fundamental ones. We demonstrate this possibility through Prim-Dijkstra routing, a classic VLSI problem whose terminal-only Manhattan complexity remained open despite decades of practical work. We prove weak NP-completeness, derive a continuous cost-radius tradeoff with a balanced (2,2) guarantee, and build HP-RCRST, a height-partition-based multi-mode solver. On 28 development instances, its stronger modes Pareto-dominate the published-method union on 23 and tie on five. The case shows how conflicting conjectures, counterexamples, formal checks, and implementation can reopen neglected questions. Code and reproducibility materials are available at https://github.com/CODA-Team/hp-rcrst.

cs.AR↗

arXiv2024

LLM-Enhanced Bayesian Optimization for Efficient Analog Layout Constraint Generation

Analog layout synthesis faces significant challenges due to its dependence on manual processes, considerable time requirements, and performance instability. Current Bayesian Optimization (BO)-based techniques for analog layout synthesis, despite their potential for automation, suffer from slow convergence and extensive data needs, limiting their practical application. This paper presents the \texttt{LLANA} framework, a novel approach that leverages Large Language Models (LLMs) to enhance BO by exploiting the few-shot learning abilities of LLMs for more efficient generation of analog design-dependent parameter constraints. Experimental results demonstrate that \texttt{LLANA} not only achieves performance comparable to state-of-the-art (SOTA) BO methods but also enables a more effective exploration of the analog circuit design space, thanks to LLM's superior contextual understanding and learning efficiency. The code is available at https://github.com/dekura/LLANA.

cs.AI↗

arXiv2024

Automated Curvy Waveguide Routing for Large-Scale Photonic Integrated Circuits

As photonic integrated circuit (PIC) designs advance and grow in complexity, largely driven by innovations in photonic computing and interconnects, traditional manual physical design processes have become increasingly cumbersome. Available PIC layout automation tools are mostly schematic-driven, which has not alleviated the burden of manual waveguide planning and layout drawing for engineers. Previous research in automated PIC routing largely relies on off-the-shelf algorithms designed for electrical circuits, which only support high-level route planning to minimize waveguide crossings. It is not customized to handle unique photonics-specific routing constraints and metrics, such as curvy waveguides, bending, port alignment, and insertion loss. These approaches struggle with large-scale PICs and cannot produce real layout geometries without design-rule violations (DRVs). This highlights the pressing need for electronic-photonic design automation (EPDA) tools that can streamline the physical design of modern PICs. In this paper, for the first time, we propose an open-source automated PIC detailed routing tool, dubbed APR, to generate DRV-free PIC layout for large-scale real-world PICs. APR features a grid-based curvy-aware A* engine with adaptive crossing insertion, congestion-aware net ordering and objective, and crossing-waveguide optimization scheme, all tailored to the unique property of PIC. On large-scale real-world photonic computing cores and interconnects, APR generates a DRV-free layout with 14% lower insertion loss and 6.25x speedup than prior methods, paving the way for future advancements in the EPDA toolchain. Our codes are open-sourced at https://github.com/ScopeX-ASU/APR.

cs.ET↗

arXiv2024

AnalogGym: An Open and Practical Testing Suite for Analog Circuit Synthesis

Recent advances in machine learning (ML) for automating analog circuit synthesis have been significant, yet challenges remain. A critical gap is the lack of a standardized evaluation framework, compounded by various process design kits (PDKs), simulation tools, and a limited variety of circuit topologies. These factors hinder direct comparisons and the validation of algorithms. To address these shortcomings, we introduced AnalogGym, an open-source testing suite designed to provide fair and comprehensive evaluations. AnalogGym includes 30 circuit topologies in five categories: sensing front ends, voltage references, low dropout regulators, amplifiers, and phase-locked loops. It supports several technology nodes for academic and commercial applications and is compatible with commercial simulators such as Cadence Spectre, Synopsys HSPICE, and the open-source simulator Ngspice. AnalogGym standardizes the assessment of ML algorithms in analog circuit synthesis and promotes reproducibility with its open datasets and detailed benchmark specifications. AnalogGym's user-friendly design allows researchers to easily adapt it for robust, transparent comparisons of state-of-the-art methods, while also exposing them to real-world industrial design challenges, enhancing the practical relevance of their work. Additionally, we have conducted a comprehensive comparison study of various analog sizing methods on AnalogGym, highlighting the capabilities and advantages of different approaches. AnalogGym is available in the GitHub repository https://github.com/CODA-Team/AnalogGym. The documentation is also available at http://coda-team.github.io/AnalogGym/.

cs.AR↗

arXiv2024

Physically Aware Synthesis Revisited: Guiding Technology Mapping with Primitive Logic Gate Placement

A typical VLSI design flow is divided into separated front-end logic synthesis and back-end physical design (PD) stages, which often require costly iterations between these stages to achieve design closure. Existing approaches face significant challenges, notably in utilizing feedback from physical metrics to better adapt and refine synthesis operations, and in establishing a unified and comprehensive metric. This paper introduces a new Primitive logic gate placement guided technology MAPping (PigMAP) framework to address these challenges. With approximating technology-independent spatial information, we develop a novel wirelength (WL) driven mapping algorithm to produce PD-friendly netlists. PigMAP is equipped with two schemes: a performance mode that focuses on optimizing the critical path WL to achieve high performance, and a power mode that aims to minimize the total WL, resulting in balanced power and performance outcomes. We evaluate our framework using the EPFL benchmark suites with ASAP7 technology, using the OpenROAD tool for place-and-route. Compared with OpenROAD flow scripts, performance mode reduces delay by 14% while increasing power consumption by only 6%. Meanwhile, power mode achieves a 3% improvement in delay and a 9% reduction in power consumption.

cs.LO↗

arXiv2024

The Dawn of AI-Native EDA: Opportunities and Challenges of Large Circuit Models

Within the Electronic Design Automation (EDA) domain, AI-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domains, such as vision, text, and graph analytics, applying them to circuit design without tailoring to the unique complexities of electronic circuits. Such an AI4EDA approach falls short of achieving a holistic design synthesis and understanding, overlooking the intricate interplay of electrical, logical, and physical facets of circuit data. This paper argues for a paradigm shift from AI4EDA towards AI-native EDA, integrating AI at the core of the design process. Pivotal to this vision is the development of a multimodal circuit representation learning technique, poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources, such as functional specifications, RTL designs, circuit netlists, and physical layouts. We champion the creation of large circuit models (LCMs) that are inherently multimodal, crafted to decode and express the rich semantics and structures of circuit data, thus fostering more resilient, efficient, and inventive design methodologies. Embracing this AI-native philosophy, we foresee a trajectory that transcends the current innovation plateau in EDA, igniting a profound shift-left in electronic design methodology. The envisioned advancements herald not just an evolution of existing EDA tools but a revolution, giving rise to novel instruments of design tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance, power, and area (PPA) is achieved not incrementally, but through leaps that redefine the benchmarks of electronic systems' capabilities.

cs.AR↗

arXiv2023

Practical Layout-Aware Analog/Mixed-Signal Design Automation with Bayesian Neural Networks

The high simulation cost has been a bottleneck of practical analog/mixed-signal design automation. Many learning-based algorithms require thousands of simulated data points, which is impractical for expensive to simulate circuits. We propose a learning-based algorithm that can be trained using a small amount of data and, therefore, scalable to tasks with expensive simulations. Our efficient algorithm solves the post-layout performance optimization problem where simulations are known to be expensive. Our comprehensive study also solves the schematic-level sizing problem. For efficient optimization, we utilize Bayesian Neural Networks as a regression model to approximate circuit performance. For layout-aware optimization, we handle the problem as a multi-fidelity optimization problem and improve efficiency by exploiting the correlations from cheaper evaluations. We present three test cases to demonstrate the efficiency of our algorithms. Our tests prove that the proposed approach is more efficient than conventional baselines and state-of-the-art algorithms.

cs.LG↗

arXiv2023

Domain Wall-Magnetic Tunnel Junction Analog Content Addressable Memory Using Current and Projected Data

With the rise in in-memory computing architectures to reduce the compute-memory bottleneck, a new bottleneck is present between analog and digital conversion. Analog content-addressable memories (ACAM) are being recently studied for in-memory computing to efficiently convert between analog and digital signals. Magnetic memory elements such as magnetic tunnel junctions (MTJs) could be useful for ACAM due to their low read/write energy and high endurance, but MTJs are usually restricted to digital values. The spin orbit torque-driven domain wall-magnetic tunnel junction (DW-MTJ) has been recently shown to have multi-bit function. Here, an ACAM circuit is studied that uses two domain wall-magnetic tunnel junctions (DW-MTJs) as the analog storage elements. Prototype DW-MTJ data is input into the magnetic ACAM (MACAM) circuit simulation, showing ternary CAM function. Device-circuit co-design is carried out, showing that 8-10 weight bits are achievable, and that designing asymmetrical spacing of the available DW positions in the device leads to evenly spaced ACAM search bounds. Analyzing available spin orbit torque materials shows platinum provides the largest MACAM search bound while still allowing spin orbit torque domain wall motion, and that the circuit is optimized with minimized MTJ resistance, minimized spin orbit torque material resistance, and maximized tunnel magnetoresistance. These results show the feasibility of using DW-MTJs for MACAM and provide design parameters.

cond-mat.mes-hall↗

arXiv2022

TAG: Learning Circuit Spatial Embedding From Layouts

Analog and mixed-signal (AMS) circuit designs still rely on human design expertise. Machine learning has been assisting circuit design automation by replacing human experience with artificial intelligence. This paper presents TAG, a new paradigm of learning the circuit representation from layouts leveraging text, self-attention and graph. The embedding network model learns spatial information without manual labeling. We introduce text embedding and a self-attention mechanism to AMS circuit learning. Experimental results demonstrate the ability to predict layout distances between instances with industrial FinFET technology benchmarks. The effectiveness of the circuit representation is verified by showing the transferability to three other learning tasks with limited data in the case studies: layout matching prediction, wirelength estimation, and net parasitic capacitance prediction.

cs.AR↗

arXiv2022

Fuse and Mix: MACAM-Enabled Analog Activation for Energy-Efficient Neural Acceleration

Analog computing has been recognized as a promising low-power alternative to digital counterparts for neural network acceleration. However, conventional analog computing is mainly in a mixed-signal manner. Tedious analog/digital (A/D) conversion cost significantly limits the overall system's energy efficiency. In this work, we devise an efficient analog activation unit with magnetic tunnel junction (MTJ)-based analog content-addressable memory (MACAM), simultaneously realizing nonlinear activation and A/D conversion in a fused fashion. To compensate for the nascent and therefore currently limited representation capability of MACAM, we propose to mix our analog activation unit with digital activation dataflow. A fully differential framework, SuperMixer, is developed to search for an optimized activation workload assignment, adaptive to various activation energy constraints. The effectiveness of our proposed methods is evaluated on a silicon photonic accelerator. Compared to standard activation implementation, our mixed activation system with the searched assignment can achieve competitive accuracy with $>$60% energy saving on A/D conversion and activation.

cs.ET↗

arXiv2021

Optimizer Fusion: Efficient Training with Better Locality and Parallelism

Machine learning frameworks adopt iterative optimizers to train neural networks. Conventional eager execution separates the updating of trainable parameters from forward and backward computations. However, this approach introduces nontrivial training time overhead due to the lack of data locality and computation parallelism. In this work, we propose to fuse the optimizer with forward or backward computation to better leverage locality and parallelism during training. By reordering the forward computation, gradient calculation, and parameter updating, our proposed method improves the efficiency of iterative optimizers. Experimental results demonstrate that we can achieve an up to 20% training time reduction on various configurations. Since our methods do not alter the optimizer algorithm, they can be used as a general "plug-in" technique to the training process.

cs.LG↗