Papers for

analog circuit designers

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.

AMSchem generates readable analog circuit schematics from code

AMSchem: Automated Schematic Visualization of AMS Circuits via Verifiable Agentic Generation

Abstract: For decades, the netlist-to-schematic gap has remained a persistent challenge in design automation, especially for analog and mixed-signal (AMS) circuits. Netlists encode connectivity, not visual presentation, making their manual conversion into readable schematics time-consuming and dependent on expert conventions. The same gap leaves LLM-based design tools without structured visual feedback, forcing them to iterate on circuits they cannot see. We present AMSchem, a training-free, verifier-guided agentic framework that automatically generates human-readable schematics from AMS netlists. AMSchem separates circuit-aware visual planning (DrawingIntent) from executable schematic geometry (SchematicIR), and applies localized visual feedback with bounded, revalidated repair patches. Deterministic validators enforce device preservation, pin-net consistency, and geometric correctness throughout. For evaluation, we construct AMSchem-Bench comprising 64 circuits of 12 types. On the 40-circuit schematic subset, AMSchem with gpt-5.5 achieves 85.0\% validity (vs. 32.5\% direct generation). When integrated as a visual feedback module in LLM-based analog design, AMSchem resolves all 13 previously failed cases from AnalogCoder benchmark across five models, substantially improving the success rate. Our dataset and benchmark are available at https://www.amschem.com/benchmark

Mon 9 NovArtificial Intelligence
The gist
Turning a netlist, which is a list describing how electronic parts connect, into a clear circuit diagram is hard and slow, especially for analog circuits. The authors present AMSchem, a tool that automatically draws these circuit diagrams in a readable way by double-checking each step. This helps other AI tools that design circuits by giving them pictures they can understand, improving design success. They tested AMSchem on many circuit examples and found it made valid drawings much more often than previous methods.
Open → 2611.12333v1

CASCoDe improves analog circuit layout with feedback-driven design

CASCoDe: A Closed-Loop Agentic Framework for Analog Sizing and Layout Co-Design

Abstract: Expert analog layouts differ from auto-generated ones in density and regularity, not only in legality: experts make a succession of discrete, hierarchical physical decisions and revisit each after extracted electrical results, while most existing automated flows act on a physical search space fixed before the controller runs. We present CASCoDe, a closed-loop LLM agent framework for analog netlist-to-layout design that formalizes those expert decisions as a hierarchical discrete action space-sizing selection, structural floorplan, local layout refinement, routing-attempt selection-on which the agent runs feedback-driven tree search from a circuit netlist to a verified GDS. The agent authors the circuit-specific floorplans and scripts, and an execution layer of interface adaptations over adapted tools make every action land at physical implementation and be judged by DRC, LVS, and extracted-RC simulation. On 20 SKY130 amplifiers spanning single-, two-, and three-stage topologies, CASCoDe is the only flow that delivers a DRC- and LVS-clean routed layout when meeting design specifications for every circuit. It reduces area by 59-85% (mean 71%) against a conventional P&R flow on identical PCells, raises mean device density from 0.39 to 0.74 against APPlace, MAGICAL, ALIGN and ICPI. A layout that beats every baseline in area and legality appears after 11 minutes of agent time on average, and ablations show that the structured action space and the feedback-guided tree search each reduce area and search cost.

Mon 9 NovArtificial Intelligence
The gist
Designing analog circuit layouts is a complex task that experts do step-by-step, often revisiting decisions based on test results. The authors created CASCoDe, a computer agent that mimics this expert process using a feedback loop and hierarchical decision steps to produce physical layouts. This approach can generate denser, more efficient layouts faster and with fewer errors compared to existing automatic methods. CASCoDe was tested on 20 different amplifier circuits, consistently delivering clean, verified layouts while significantly reducing chip area.
Open → 2611.11710v1

Large language model improves analog circuit placement and space use

LAMP: LLM-Driven Analog Placement through Adaptive Tool Composition

Abstract: Analog placement requires circuit-specific trade-offs among area, matching, routability, and electrical performance. Balancing these trade-offs through predefined objectives and fixed placement flows remains difficult. In this paper, we propose an analog placement framework in which a large language model (LLM) acts as a layout engineer through composable placement components. These components support constraint management, placement and legalization, and lightweight evaluation of routability and electrical performance. Using multimodal checkpoints of the initial and evolving design, the LLM selects and combines components to construct and revise its own placement flow. It also adapts the placement hierarchy by reopening modules or partitioning and regrouping devices, allowing local layouts to respond to global design needs. An experience skill provides reusable design knowledge to guide these decisions. Evaluation on two SMIC 180 nm circuits shows that the framework reduces placement area and improves most measured post-layout performance metrics.

Thu 29 OctHardware Architecture
The gist
Designing the layout for analog circuits involves balancing many tricky factors like size, how well parts match, and how easy wiring is. The authors show how a large language model, like those used in AI, can act as a design engineer by picking and combining specialized tools to handle these trade-offs. This AI model can change its strategy as the design evolves, making local and global layout decisions to improve the circuit. Tests on real circuits show this approach reduces size and often improves performance.
Open → 2610.39882v1

Large language model agent designs opamps from specs to layout

OPERA: OPamp Design by an Expert-Taught Reasoning Agent, from Specifications to Layout

Abstract: Analog flows from specifications to a signed-off layout rarely run without manual iteration. Recent large language model (LLM) agents size circuits with optimizer loops over the device dimensions and stop at the schematic. We present OPERA (OPamp design by an Expert-taught Reasoning Agent), in which a general-purpose LLM agent designs CMOS opamps from specifications to post-layout sign-off with open-source tools. First, the designer teaches the agent the gm/ID method: map the specifications to transconductances and minimum currents, choose gm/ID per device role from characterized lookup tables, and size from equations, leaving a few knobs to search and an explainable design. Second, the agent learns the gLayout framework and taught layout practice, and writes a reusable layout generator that closes the layout and extraction loop at designer-approved gates. In SKY130, the agent designed a shared constant-gm bias and six opamps (5T, folded-cascode and telescopic OTAs; Miller, folded-cascode and telescopic two-stage) for fun >= 50 MHz, PM >= 60 degrees, SR 25 V/μs into 1 pF and a minimum dc gain of 30 to 60 dB. All six layouts are DRC-clean and LVS-matched, and their extracted netlists meet every target at all 15 PVT corners ( fun >= 53.7 MHz, PM >= 62.1 degrees, SR >= 27.9 V/μs). The benchmark netlists are released at https://github.com/AMPICLab/AMPICBench.

Thu 29 OctHardware ArchitectureArtificial Intelligence
The gist
Designing analog circuits like operational amplifiers (opamps) usually needs a lot of manual work to go from initial specs to a finished chip layout. The authors created OPERA, a system where a large language model is taught expert design methods to fully automate opamp design from specifications all the way to layout verification. OPERA uses known circuit design techniques and open-source tools to create different types of opamps meeting various performance targets. The resulting designs pass all standard checks, suggesting the approach can reliably replace some manual steps in analog circuit design.
Open → 2610.39395v1

Analogscout speeds analog circuit sizing with less simulation

AnalogScout: Simulation-Efficient PVT-Aware Analog Sizing with LLM Agents

Abstract: Analog device sizing must satisfy all specifications across process, voltage, and temperature (PVT) corners to ensure tape-out success, but simulating every candidate at all corners dominates the sizing time and slows design iteration. Conventional surrogate-based optimizers search the sizing space directly, while recent large language model (LLM) agents add circuit knowledge to designs but still delegate the sizes to global optimizers. Both learn the circuit response from repeated multi-corner SPICE simulations and optimize on top of it, which becomes expensive under a limited simulation budget. Providing an agent with reusable verified designs and sizing sub-blocks analytically could save most of this budget. We propose AnalogScout, a simulation-efficient PVT-aware sizing framework driven by an LLM agent. Combining elite-design reuse, analytic gm/Id local sizing and global refinement under full-corner verification, AnalogScout reduces power by 43.3% relative to the evolution strategy CMA-ES at an equal budget of 16k simulations on three SKY130 OTAs of increasing complexity, and reaches the final CMA-ES power after 7.0% of that budget. It also attains lower power than Bayesian optimization on all three OTAs and than two re-implemented LLM-driven flows on the two OTAs where they were tested.

Tue 27 OctHardware ArchitectureArtificial IntelligenceMachine Learning
The gist
Designing analog circuits often requires checking how they perform under different conditions, which takes a lot of time because many simulations are needed. The authors propose AnalogScout, a new way to speed up this process by having an intelligent assistant reuse verified designs and use mathematical shortcuts to size circuits. This method cuts the required simulations drastically while achieving lower power usage than other standard approaches. It helps designers make better circuits faster and more efficiently.
Open → 2610.37319v1

Language models improve analog circuit layout repairs with cost-aware planning

Who Plans, Who Edits? Verified, Cost-Aware Division of Labor for LLM-Driven Analog Layout Repair

Abstract: Language-model agents can repair analog layouts when sign-off tools check every edit, but which model should plan a repair, which should edit it, and at what cost remain open questions. In our tool-grounded repair agent, models only choose bounded layout operators; sign-off tools rerun each task's contract checks after every edit, so failing layouts are never accepted. On layout-versus-schematic (LVS), design-rule checking (DRC), and post-layout repairs of three designs (a production high-voltage digital-to-analog converter (DAC), a 5-V oscillator, and a SKY130 operational transconductance amplifier (OTA)) with six tier-matched models from two vendors, 182 blind runs show that cheap models execute plans but rarely succeed alone (the cheapest model: 1 of 11 runs alone, 16 of 17 under a flagship planner; p < 0.001), cheap planners fail more often, and no fixed assignment is cheapest on every task. We propose a learning controller that selects models for each role and the escalation order from the first tool evaluation and updates Bayesian estimates after every attempt. With rules and initial estimates frozen before testing, the controller fixed 7 of 8 episodes on four sealed held-out tasks, matching the OpenAI flagship alone, at 15-40% of the flagship's spend per fix on three tasks but 8% higher spend overall. The cheapest mid-tier model alone fixed 6 of 8 at the lowest overall spend per fix but missed the hardest task. All 32 extracted DAC repairs match the human-guided LVS repair's integral nonlinearity (INL) within 0.005 least significant bits (LSB) at every code.

Fri 16 OctHardware ArchitectureArtificial Intelligence
The gist
Fixing complex analog circuit designs by hand is slow and expensive. The authors show that using different language models to plan and carry out repairs, combined with checks after each step, can fix these designs more efficiently. They also teach a controller to pick which model to use and when to escalate to stronger models. This approach speeds up repairs while keeping costs low and produces fixes as accurate as those done by humans.
Open → 2610.24234v1

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

CktHGVAE automates analog circuit design using graph-based AI models

CktHGVAE: A Symmetric Design/State Heterogeneous Graph Variational Autoencoder for Transistor-level Analog/Mixed-signal Circuit Design and Analysis

Abstract: We propose CktHGVAE, a heterogeneous graph variational autoencoder for transistor-level analog/mixedsignal CMOS circuits that takes not only design variables but also state variables as its inputs and outputs. With a single hyperparameter configuration without topology-specific tuning, comparison between model-generated and SPICE-simulated circuit operational states gives median R2 values above 0.9 for typical single-ended voltage amplifiers and the CMOS inverter, and 0.81-0.96 for differential amplifiers with larger datasets. Latent-space optimization in the PCA-reduced latent space with Bayesian optimization, evolutionary search, random search, and quasi-exhaustive search is demonstrated for a common-source voltage amplifier with NMOS input and resistive load, where the objective function is defined as a penalty for deviation from required circuit specifications. For each search strategy, 93.3 - 100% of all design candidates suggested by the model satisfy the required circuit specifications at the decoder output, and SPICE simulations verify that 90 - 100% of them indeed satisfy the requirements. The model pretrained on a batch of topologies can be transferred to unseen topologies without retraining at all, with zero-shot reconstruction median R2 values of 0.72-0.90 in three of four scenarios, including transfer from single-ended to differential topologies, although the transfer fidelity depends on the choice of pretraining topologies. Our demonstrations suggest that the proposed model can potentially serve as a basis for AMS CMOS circuit design automation.

Wed 14 OctMachine Learning
The gist
Designing analog circuits is complex because it involves many variables that affect circuit performance. The authors created CktHGVAE, a special AI model that learns from transistor-level circuit details and their operational states. This model can predict how circuits behave without detailed simulations and help quickly find designs that meet specific requirements. It also works well on different circuit types without retraining, showing potential for speeding up analog circuit design.
Open → 2610.19508v1

Adaptive transistor sizing finds better designs using shape of solution space

ATLAS: Adaptive TDA-guided Landscape-Aware Transistor Sizing

Abstract: Analog transistor sizing, finding design parameters that simultaneously satisfy multiple performance specifications, is a labor-intensive bottleneck in circuit design. To support analog circuit experts, various automation methods have been proposed, including Bayesian optimization (BO), reinforcement learning (RL), and others. Yet existing methods are oblivious to the topological structure of a feasible design space, which can fragment into disconnected regions due to operating-regime transitions, conflicting specification trade-offs, and nonconvex device physics. This topological blindness causes the optimizer to converge within a single feasible region while missing others that may contain superior designs. To address this limitation, we propose ATLAS. a BO framework utilizing Topological Data Analysis (TDA). At each iteration, a Mapper graph is constructed over a surrogate-predicted feasible region to estimate connected regions, enabling topology-aware exploration from the very first iteration without any observed feasible points. A topological sensitivity score classifies candidates as bridge, frontier, or interior points, injecting a targeted exploration bonus into the acquisition function. Experiments on four analog circuit benchmarks in the GF180 and SKY130 processes demonstrate that \coin finds feasible designs with significantly fewer simulations than baselines, including RL and BO methods. To the best of our knowledge, this is the first work to apply topological data analysis to analog circuit design automation. The official implementation is publicly available on https://github.com/youngmin0oh/atlas.

Wed 7 OctHardware Architecture
The gist
Designing analog circuits is hard because many good solutions exist but are scattered in groups that don’t connect smoothly. The authors created a method called ATLAS that looks at the overall shape and structure of all possible good designs instead of just searching randomly. This helps find better circuit setups faster by jumping between different groups of good designs. They tested ATLAS on real circuit problems and showed it needed fewer tries than older methods to find working designs.
Open → 2610.10985v1

FeFET-based voltage-to-time converter reduces offset in 28-nm CMOS

A FeFET Voltage-to-Time Converter with Offset Trim by Programmed Multilevel State in 28-nm CMOS

Abstract: The offset and gain of voltage-to-time converters (VTCs) in time-domain circuits vary with process, supply, and temperature. This work presents a VTC whose nonvolatile input-referred offset trim is the programmed multilevel state of the ferroelectric field-effect transistor (FeFET) that converts the input. Fabricated in 28-nm CMOS, the 6.07-$μ$m$^2$ VTC consists of a current-starved inverter with the FeFET and a parallel NMOS leaker in its tail, a capacitor bank, and a following inverter. The programmed state shifts the transfer curve onto the input range, leaving the gain to the capacitor bank and the leaker bias. Measured at 10~MS/s, centered states weaken the second harmonic from $-$12.5~dB in the low-threshold state to $-$32.2~dB and lower the static integral nonlinearity (INL) at 5~bit from 2.42 to 0.92~LSB. Post-layout simulations indicate that the proposed VTC can operate at 500~MS/s, drawing 2.0~$μ$W from a 0.9-V supply, with nearly unchanged distortion and gain up to 700~MS/s. Across simulated process corners and $\pm$10\,\% supply variation, the input-referred offset is calibrated to within 10~mV and the gain to within 4\,\% of nominal by adjusting the programmed state and leaker bias.

Sun 4 OctEmerging Technologies
The gist
Voltage-to-time converters turn electrical voltage signals into time signals but often suffer from inaccuracies due to manufacturing differences, temperature, and power changes. The authors designed a converter that uses a special type of memory transistor, a FeFET, to store correction information and improve accuracy permanently. This design adjusts its own internal settings to reduce errors, resulting in more precise readings. Their chip operates efficiently in a modern 28-nanometer chip technology and shows promising speed and power performance in simulations.
Open → 2610.05016v1

Open-source analog circuit benchmark tests model design skills

SGAnalog: An End-to-End Circuit Benchmark from Open-Source Silicon Tapeouts

Abstract: Existing analog integrated circuit design benchmarks make two questions hard to answer: whether a model has learned transferable circuit skills rather than recalled familiar examples, and whether its output works under defined process and test conditions. We introduce a benchmark built from human-designed, open-source circuits associated with Tiny Tapeout manufacturing shuttles. The collection contains 273 topologically distinct top-level designs. Every source is retrieved at the revision recorded for its shuttle submission and processed in a fixed containerized environment. The pipeline exports each eligible schematic image and its SPICE netlist from the same source file, giving transcription an exact structural reference. Commit dates support model-specific training-cutoff analysis, while author testbenches provide the simulation context for sizing. The benchmark evaluates schematic-to-netlist transcription and device sizing. Across seven models on a fixed set of 66 transcription tasks, the strongest model reaches 56.1% exact graph isomorphism, and six of seven models drop sharply from the small to the medium tier. For one frontier model, removing author-chosen labels reduces exact matches while preserving aggregate structural F1, suggesting that labels can aid connectivity tracing. On the 17 sizing tasks, the leading model converges on all 17 proposals and reaches 91.2 out of 100 against the human reference, while the two newest Claude models refuse 4 and 11 of the same prompts they transcribe without objection; a proposal without sizes scores zero. The two tasks produce different model rankings, exposing distinct visual and design capabilities and, in one family, a policy rather than capability limit.

Fri 2 OctArtificial IntelligenceHardware Architecture
The gist
Designing analog circuits involves creating detailed schematics and choosing the right device sizes. Existing benchmarks don't clearly show if computer models truly understand these tasks or just memorize examples, and whether their outputs work under realistic conditions. The authors created a new benchmark using many real human-made circuits from open-source chip projects, allowing precise checks of both the schematic-to-netlist conversion and device sizing. They tried several models and found big differences in how well each handled different tasks, highlighting distinct skills needed for visual understanding and design optimization.
Open → 2610.03934v1

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

Lightweight AI tool analyzes analog circuit layouts with conversation

Inspector: Conversational and Lightweight Analyzer of Analog Circuit Layouts Using LLM and CNNs

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 a novel framework that combines fine-tuned LLMs and CNNs to analyze GDSII files of analog circuits, enabling a conversational interface between the tool and the designers. Experimental results using thousands of analog designs across four realistic tasks demonstrate that the proposed solution outperforms state-of-the-art general-purpose massive VLMs by a significant margin (up to 81%), thus providing a lightweight solution to the problem of GDSII analysis.

Mon 28 SeptMachine LearningComputer Vision and Pattern Recognition
The gist
Analyzing the detailed physical designs of analog circuits is complicated but essential for ensuring circuits work well. The authors developed a new tool that uses two types of artificial intelligence—language models and image-recognition models—to understand and analyze these complex circuit designs directly from industry-standard files. This tool can chat with designers, making the interaction easier and more intuitive. Tests on thousands of circuit designs show it performs much better than existing general AI models while being more lightweight.
Open → 2609.34976v1

Analog circuit yield improves faster with new simulation method

Simulation-Efficient Analog Circuit Yield Optimization via Monte Carlo Zeroth-Order Gradient Estimation

Abstract: Yield optimization under process variation is expensive because each candidate design must be evaluated across many Monte Carlo SPICE samples. The resulting finite-sample yield is also piecewise constant in the design parameters, providing little local information for optimization. We introduce zeroth-order Monte Carlo stochastic gradient descent (ZO-MC-SGD), a black-box method that converts continuous specification margins into stochastic descent directions. Each update evaluates opposite design perturbations under shared process samples, allowing a small simulation batch to estimate a local direction without differentiating SPICE or fitting a global surrogate model. A Spearman rank-correlation test checks that the margin-based loss orders designs consistently with empirical yield. We prove that the estimator is unbiased for a Gaussian-smoothed surrogate and derive variance and sample-complexity bounds with no explicit dependence on process dimension. Across five analog circuit benchmarks with up to 30 design variables and 42 process variables, ZO-MC-SGD reaches a mean yield of 0.95 on four circuits within 50--200 simulations and the empirical yield ceiling on the fifth. Relative to the best of five black-box and learning-based baselines, it reduces the required simulation budget by up to a factor of eight.

Fri 25 SeptComputational Engineering, Finance, and Science
The gist
Optimizing how well circuits perform despite manufacturing differences is usually very slow because each design is tested many times in computer simulations. The authors developed a new way to guess which direction improves circuit yield using fewer simulations by comparing slight design changes under the same test conditions. Their method doesn't require complicated math inside the simulation software or building approximate models. They showed it works well on several example circuits, needing fewer simulations than existing methods to reach high yield.
Open → 2609.30678v1

Analog hardware fabric cost driven by composability not computation

Composability rather than computation sets the cost of an analog EML hardware fabric

Abstract: The operator eml(x, y) = exp(x) - ln(y) with the constant 1 generates the elementary functions, a continuous counterpart to NAND. Whether it yields a useful fabric had not been asked of hardware. We ask in network models, circuit simulation and SkyWater 130 nm layout. Four bipolar junctions evaluate the operator for 13 fJ, beating a width-matched digital datapath by 4-134x. The fabric assembled from them is not cheap: it loses to resource-matched baselines, and over the reals its grammar excludes trigonometry. Amplifiers holding those junctions' operating points take 74.5% of a cell's current, so a cell costs 3000 times what they spend. Extracted non-idealities cost 2.6x when a cell must hold a value and nothing when it need only be repeatable. Sharing them across cells recovers two of the three orders. The premise was that a universal primitive licenses a uniform machine. It survives in the primitive and fails in the machine.

Tue 15 SeptEmerging TechnologiesHardware Architecture
The gist
The paper explores a special computing operation called eml that combines exponential and logarithm functions, which could replace traditional digital logic circuits in analog hardware. The authors show that individual components using this operation can be very energy efficient. However, building complex systems from these components is much less efficient due to the need for many amplifiers and limitations in the types of functions that can be performed. In other words, while the basic building block is promising, putting many together to form a working machine is costly and less practical.
Open → 2609.17903v1

Neuromorphic hardware explores true power-law memory scaling limits

Fractional-order hardware for neuromorphic computing: Is the order really the problem?

Abstract: Does a neuromorphic system need a true power-law memory kernel, and if so, can anyone build one? Neuromorphic systems process signals spanning many timescales at once, from milliseconds to tens of seconds. Integer-order circuits buy each additional timescale with an additional state variable. Fractional-order dynamics offer a different bargain: one operator whose power-law kernel carries a continuum of timescales, tuned by one parameter, the order alpha. A fractional derivative is non-local, so evaluating it costs storage and arithmetic that grow with the retained history, where an integer-order derivative costs a constant. This review organizes the hardware literature around that cost. We derive the retained history needed to hold the truncation error below a tolerance epsilon, show that it scales as epsilon^(-1/alpha), and set beside it a second and independent limit on the direct form: in fixed point the weights themselves underflow, so word length caps the usable history however long the buffer is. The two limits move at very different rates with the order, and where they cross decides whether a word length can serve an order at all. We use both to sort published hardware into three strategies, note a fourth the numerical literature has developed and this hardware has not, and survey digital, analog and device work. Along the way we ask whether the field is worried about the right obstacle. It is not. Fabricated constant-phase devices already span the orders two groups identify as task-optimal, so the order gap has largely closed, leaving a residual gap near 0.1 and at the lower order describing cortical adaptation. What remains is a frequency-band gap of about three decades at the low end. That corner is not empty, since double-layer electrodes work there, but every device in it is discrete, and no integrable thin-film element has been characterized there.

Wed 9 SeptEmerging TechnologiesNeural and Evolutionary Computing
The gist
Neuromorphic systems mimic brain functions by handling signals over many timescales, which is tricky with traditional circuits. The authors investigate special fractional-order circuits that use one setting to cover many timescales but require managing growing memory for past signals. They analyze hardware designs, showing that the practical limits hinge on how long past data is stored and precision limits in representing numbers. They conclude the main challenge is not the fractional order parameter itself but covering low-frequency signal ranges with suitable devices.
Open → 2609.10882v1

Fast methods simulate nonlinear circuits for advanced energy computing

Fast simulation of nonlinear deep resistive networks for energy-based computation

Abstract: Deep resistive networks are electronic energy-based systems in which computation is performed by the steady-state voltages of nonlinear circuits. Nonlinear devices enable expressive input-output transformations, but make the circuit equilibria costly to compute during simulation and training. Recent coordinate-descent solvers have achieved large speedups over SPICE-class circuit simulators, but only for nonlinearities modeled as ideal-diode models. This mathematical simplification is not sufficient for practical analog circuits. Here we extend coordinate-descent simulation to realistic monotone nonlinearities, including Shockley diodes, antiparallel diode pairs, and piecewise-linear current-voltage characteristics. With neighboring voltages fixed, each node update remains a scalar Kirchhoff-law solve. Single-exponential characteristics admit closed-form Lambert-(W) updates, while more general monotone characteristics can be handled with scalar root-finding methods. Across networks with one to three hidden layers and hidden widths from 64 to 1024, the solver reproduces matched SPICE steady-state voltages with relative $L_1$ errors below $1.1\times10^{-4}$ for 90% of validation samples, while achieving speedups up to $(1.7\times10^3)$. We further train a $1568\times100\times20$ double-Shockley network on MNIST, reaching about 3.0% test error and reducing the per-epoch training time by roughly $4.4\times10^2$. Together, these results establish a practical route to the circuit-level design and training of large-scale analog energy-based systems incorporating realistic nonlinear devices.

Mon 7 SeptEmerging Technologies
The gist
Simulating nonlinear electronic circuits is usually slow because of complex device behavior. The authors improved simulation methods to work with more realistic circuit parts like real diodes, making simulations much faster but still accurate. Their approach works for large circuit networks and helps train energy-based analog computing systems efficiently. This advancement opens the door to designing and training big analog computer circuits that use actual components.
Open → 2609.07356v1