Papers for

electronic design automation tool developers

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.

Agentic inference boosts verification code quality and cost efficiency

Inference-Time Scaling in Agentic Hardware Verification Workflows: A Multi-Strategy Characterization Across Protocol Complexity

Abstract: Inference-time scaling, allocating more compute during generation rather than pre-training, has demonstrated dramatic quality improvements for LLM reasoning tasks. Its behaviour in structured hardware verification code generation, where outputs must satisfy compiler correctness, protocol semantics, and functional coverage constraints simultaneously, is less understood. We present a systematic, simulator-grounded study of inference-time compute scaling for agentic UVM testbench synthesis targeting AMBA protocol bridges. Four inference strategies---zero-shot (\$0.04), raw-feedback iterative (\$0.81), structured inner-loop (\$0.95), and full dual-loop agentic synthesis (\$1.06)---are evaluated across four AMBA targets (Protocol Complexity Index 11.8--22.6) using the Protocol Verification Completeness (PVC) metric, functional coverage, and a six-class UVM error taxonomy (E1--E6). Our central finding is that structured diagnostic feedback acts as an inference-time compute multiplier: the structured inner loop yields roughly $15\times$ more PVC per inference dollar than raw EDA-tool feedback (marginal efficiency, S1$\to$S2 vs. S0$\to$S1). The mechanism is fault targeting, not token reduction: raw compiler feedback drives the testbench to compile but cannot surface functional protocol faults that leave the code syntactically valid, whereas structured E1--E6 bundles diagnose and resolve them. All outputs are judged by a cycle-accurate Mentor Questa toolchain rather than by model self-assessment; the dual-loop strategy reaches PVC $\geq$ 0.95 with zero scoreboard errors on every target, and the generated environments surfaced a latent RTL bug in two of the four reference designs. These results establish a principled compute-quality trade-off curve for LLM-aided verification environment generation and motivate inference-budget-aware deployment strategies for industrial EDA workflows.

Wed 18 NovHardware ArchitectureSoftware Engineering
The gist
Generating correct test environments for hardware verification is tricky because the code must work perfectly with complex protocols and compilers. The authors studied how increasing computing power during code generation—rather than before—affects quality and cost. They found that using structured feedback that targets specific types of errors is much more efficient than just relying on raw compiler messages. This better feedback helps find and fix subtle protocol bugs that look correct to the compiler but fail functionally. Their approach also uncovered hidden bugs in two test designs, showing real-world impact.
Open → 2611.23905v1

LLM speeds up analog circuit design with fast accurate models

NEMESIS2.0: LLM-Aided Netlist-Driven Performance Equation Modeling for Accelerated Analog Circuit Sizing

Abstract: This work presents NEMESIS2.0, an open-source LLM-aided framework that automatically derives equation-based performance models for analog circuits. The resulting equations provide fast, accurate surrogates for SPICE evaluation. To validate the method, equation-based models are developed for seven circuit test cases in a commercial 65nm CMOS technology, covering 15 metrics on five operational transconductance amplifier topologies, and six metrics on two dynamic comparator topologies. When tested on 1000 unseen variants of these seven designs, each corresponding to a different set of independently sampled transistor sizes, the accuracy is found to be within 5% of SPICE. To demonstrate use cases for NEMESIS2.0, the generated models are used as performance evaluators in multiple transistor sizers based on different population-based stochastic search optimizers. For each of the seven test cases, transistor sizing is performed for 100 different sets of performance specifications, with final SPICE simulation confirming that 83.3% of the resulting designs meet all specifications after a single sizing run. The rest fail to meet the specifications due to discrepancies between the model and SPICE, and require iterative resizing under tightened specifications; all such scenarios meet specifications within five iterations. Within the transistor sizers, this equation-based performance analysis evaluates ~400 design candidates per second, versus 0.14 candidates per second for SPICE-based evaluation, achieving 196-238x sizing runtime speedup, including final SPICE verification.

Fri 13 NovHardware Architecture
The gist
Designing analog circuits usually requires slow and complex simulations to check how well they work. This paper introduces NEMESIS2.0, a tool that uses large language models to create simple math equations that predict circuit performance much faster. The authors tested this on various amplifier and comparator circuits and found their equations matched detailed simulations within 5%. Using these models, they sped up the process of finding the right circuit parts by nearly 200 times while still meeting design requirements most of the time.
Open → 2611.18995v1

Graph reinforcement learning improves detailed chip placement layout

GPlaceRL: An Open-Source Graph Reinforcement Learning Framework for Detailed Placement

Abstract: Reinforcement learning (RL) has emerged as a promising approach for placement optimization, particularly when combined with graph neural networks (GNNs) that capture circuit connectivity. However, most learning-based placement approaches focus on floorplanning, macro placement, or global placement, while detailed placement refinement remains relatively unexplored. In this paper, we present GPlaceRL, an open-source graph reinforcement learning framework for detailed placement refinement. GPlaceRL represents legalized placements as graphs and provides a modular environment for studying graph encoders, policy architectures, reward formulations, and local placement actions. To demonstrate the capabilities of GPlaceRL, we conduct a systematic evaluation of proximal policy optimization (PPO) policies with graph attention network (GAT) encoders in a per-design optimization setting. Across five placement benchmarks, the best greedy evaluation results achieve HPWL improvements ranging from $3.27\%$ to $32.87\%$. The results highlight the importance of compact GAT architectures and flexible local action spaces for placement optimization. Overall, GPlaceRL provides a reproducible and extensible framework for systematic research on RL-based detailed placement refinement.

Mon 5 OctArtificial Intelligence
The gist
Placing electronic parts efficiently on a chip is important to make devices work better and use less power. The authors created a new software framework called GPlaceRL that uses a type of artificial intelligence called reinforcement learning with graph neural networks to improve the detailed placement of chip components. This approach treats the chip layout as a graph and tries different local moves to find better arrangements. Their tests showed the method can reduce wiring length by up to about 33%, which could help make chips faster and more efficient.
Open → 2610.06489v1