Large language models (LLMs) hold promise for automating integrated circuit (IC) engineering using register transfer level (RTL) hardware description languages (HDLs) like Verilog. However, challenges remain in ensuring the quality of Verilog generation. Complex designs often fail in a single generation due to the lack of targeted decoupling strategies, and evaluating the correctness of decoupled sub-tasks remains difficult. While the chain-of-thought (CoT) method is commonly used to improve LLM reasoning, it has been largely ineffective in automating IC design workflows, requiring manual intervention. The key issue is controlling CoT reasoning direction and step granularity, which do not align with expert RTL design knowledge. This paper introduces VeriBToT, a specialized LLM reasoning paradigm for automated Verilog generation. By integrating Top-down and design-for-verification (DFV) approaches, VeriBToT achieves self-decoupling and self-verification of intermediate steps, constructing a Backtrack Tree of Thought with formal operators. Compared to traditional CoT paradigms, our approach enhances Verilog generation while optimizing token costs through flexible modularity, hierarchy, and reusability.

Integrated circuit (IC) designs require transforming high-level specifications into physical layouts, demanding extensive expertise and specialized tools, as well as months of time and numerous iterations. While Machine Learning (ML) has shown promise in various research domains, the lack of large-scale, open datasets limits its application in chip design. To address this limitation, we introduce CircuitNet 3.0, a large-scale, comprehensive, and open-source dataset curated to facilitate the evaluation of ML models on challenging timing and power prediction tasks. Starting with a diverse set of 8,659 validated open-source designs, we employ a systematic framework to generate over 15,000 instances. Through specialized syntax-tree mutation strategies and principled, task-oriented filtering methodology, we enrich each design with multi-modal information spanning multiple design stages, including complete design flow documentation, register-transfer-level (RTL) designs and corresponding netlists, detailed physical layouts, and comprehensive performance metrics. The experimental results convincingly demonstrate that ML models leveraging multi-stage, multi-modal circuit representations significantly improve performance over existing open-source datasets in electronic design automation (EDA) tasks, paving the way for efficient and accessible circuit representation learning. The dataset and codes are available in https://anonymous.4open.science/r/ICLR26-CircuitNet3-272B.

The decomposition-based chiplet design paradigm, which breaks monolithic system-on-chips (SoCs) into smaller chiplets, has proved effective in reducing costs and accelerating development. The vast design space of multichiplet systems necessitates automated techniques to maximize their benefits while minimizing overheads. However, current chiplet decomposition flows lack support for exploring reusable chiplets, missing opportunities to efficiently amortize nonrecurring engineering (NRE) costs. To fully unleash the economic potential of chiplets, we propose Chipletizer 2.0, a cost-driven framework that guides SoC decomposition and enables chiplet reuse across a line of products. This early-stage chiplet planning framework determines critical system parameters involving the partition, floorplan, and die-to-die (D2D) interface, based on user-specified optimization goals. Experimental results demonstrate that, compared with the existing chiplet decomposition techniques, our proposed framework achieves significant cost improvements on realistic product lines with acceptable overheads.

LLMs can generate SystemVerilog assertions (SVAs) from natural language specs, but single-pass outputs often lack functional coverage due to limited IC design understanding. We propose CoverAssert, an iterative framework that clusters semantic and AST-based structural features of assertions, maps them to specifications, and uses functional coverage feedback to guide LLMs in prioritizing uncovered points. Experiments on four open-source designs show that integrating CoverAssert with AssertLLM and Spec2Assertion improves average improvements of 9.57

The rapid advancement of deep learning has presented significant energy efficiency challenges to the conventional von Neumann architecture. In-memory computing (IMC) architectures based on emerging non-volatile memory (eNVM) are widely regarded as a promising solution for accelerating neural network training due to their high parallelism and low power consumption. However, the intrinsic non-idealities of eNVM devices can cause conductance updates to deviate from target values, thereby limiting the performance of on-chip training. To address this challenge, this paper presents a Non-ideality Optimized eNVM Accelerator (NOVA) architecture for on-chip training. Specifically, we first fabricate a two-dimensional (2D) ferroelectric field-effect transistor (FeFET) and develop a conductance modulation behavioral model calibrated with experimental data. Building upon this device model, we propose, for the first time, a Non-ideality Avoidance Training (NAT) algorithm tailored for eNVM devices, which mitigates accuracy degradation by guiding weight convergence toward the most stable conductance regions of eNVM devices. Experimental results demonstrate that, even under severe device asymmetry, NAT improves the accuracy by an average of 15.1% over the baseline methods across multiple benchmark tasks. Meanwhile, the NOVA achieves an average energy efficiency gain of approximately 33.58× compared with the peak energy efficiency of graphics processing units (GPUs).

Large Language Models have emerged as powerful tools for automating Register-Transfer Level (RTL) code generation, yet they face critical limitations: existing approaches typically fail to simultaneously optimize functional correctness and hardware efficiency metrics such as Power, Performance, and Area (PPA). Methods relying on supervised fine-tuning commonly produce functionally correct but suboptimal designs due to the lack of inherent mechanisms for learning hardware optimization principles. Conversely, external post-processing techniques aiming to refine PPA performance after generation often suffer from inefficiency and do not improve the LLMs’ intrinsic capabilities.To overcome these challenges, we propose ChipSeek, a novel hierarchical reward based reinforcement learning framework designed to encourage LLMs to generate RTL code that is both functionally correct and optimized for PPA metrics. Our approach integrates direct feedback from EDA simulators and synthesis tools into a hierarchical reward mechanism, facilitating a nuanced understanding of hardware design trade-offs. Through Curriculum-Guided Dynamic Policy Optimization (CDPO), ChipSeek enhances the LLM’s ability to generate high-quality, optimized RTL code. Evaluations on standard benchmarks demonstrate ChipSeek’s superior performance, achieving state-of-the-art functional correctness and PPA performance. Furthermore, it excels in specific optimization tasks, consistently yielding highly efficient designs when individually targeting fine-grained optimization goals such as power, delay, and area. The artifact is open-source in https://github.com/rong-hash/chipseek.

This chapter focuses on automatic test pattern generation (ATPG). Historically, ATPG has focused on a set of faults derived from a gate-level fault model. For a given target fault, ATPG consists of two phases: fault activation and fault propagation. The objective of ATPG is to find an input sequence that, when applied to the circuit, enables testers to distinguish between the correct circuit behavior and the faulty circuit behavior caused by a particular fault. Effectiveness of ATPG is measured by the fault coverage achieved for the fault model and the number of generated vectors, which should be directly proportional to test application time. ATPG efficiency is another important consideration. The chapter describes circuit-based Boolean satisfiability techniques for solving circuit-oriented problems. It presents advanced ATPG research topics, such as for delay faults, crosstalk, and power supply noise. The chapter discusses ATPG for design applications including logic optimization and design verification.

Despite significant evolution of CUDA programming and domain-specific libraries, effectively utilizing GPUs with massively parallel engines remains difficult. Large language models (LLMs) show strong potential in generating optimized CUDA code from sequential code. However, using LLMs in practice faces two major challenges: cloud-based APIs pose risks of code leakage, and local deployment is often computationally expensive and inefficient. These drawbacks have spurred interest in small language models (SLMs), which are more lightweight and privacy-friendly. Encouragingly, recent studies show that SLMs can achieve performance comparable to LLMs on specific tasks. While SLMs can match LLMs on domain-specific tasks, their limited reasoning abilities lead to suboptimal performance in complex CUDA generation according to our experiments. To bridge this gap, we propose ReGraphT, a training-free, retrieval-augmented generation framework that transfers LLM-level reasoning to smaller models. ReGraphT organizes CUDA optimization trajectories into a structured reasoning graph, modeling the combined CUDA optimizations as state transitions, and leverages Monte Carlo Graph Search (MCGS) for efficient exploration. We also present a CUDA-specific benchmark with difficulty tiers defined by reasoning complexity to evaluate models more comprehensively. Experiments show that ReGraphT outperforms HPC-specific fine-tuned models and other retrieval-augmented approaches, achieving an average 2.33× speedup on CUDAEval and ParEval. When paired with DeepSeek-Coder-V2-Lite-Instruct and Qwen2.5-Coder-7B-Instruct, ReGraphT enables SLMs to approach LLM-level performance without the associated privacy risks or excessive computing overhead.

Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have made these devices increasingly susceptible to soft errors. While prior work has examined GPU reliability, most studies have focused on general-purpose applications or conventional neural networks mostly used for vision tasks such as classification and detection. In contrast, systematic analysis of modern large-scale LLMs remains limited, despite their rapid adoption in diverse application scenarios. Given the unique characteristics of LLMs, their resilience to soft errors may differ substantially from earlier models. To bridge this gap, we conduct the first instruction-level fault injection study of LLM inference. Our approach reveals reliability characteristics from multiple perspectives, highlighting the effects of model architecture, parameter scale, and task complexity. These findings provide new insights into LLM reliability and inform the design of more effective fault tolerance mechanisms.

Fully homomorphic encryption (FHE) enables computation on encrypted data, but its long ciphertext dataflow and high-dimensional modular arithmetic make it vulnerable to silent data corruption caused by transient hardware faults. Existing protection methods either target dedicated accelerators or impose substantial execution, modular-arithmetic, and memory-access overheads on CPUs. This work presents an efficient fault-tolerance scheme for CPU-based CKKS computation. It checks the input-output consistency of polynomial operators while reducing protection overhead at three levels. First, modulus-aware bucket checksum exploits wide CPU accumulators to reduce expensive modular reductions. Second, dataflow-fused in-operator checking embeds checksum accumulation into operator dataflows, avoiding separate scans of long ciphertext polynomials. Third, cross-operator check fusion eliminates redundant checksum computations between adjacent operators while preserving end-to-end checking invariants. We implement the scheme in OpenFHE and evaluate it on representative encrypted applications and ciphertext primitives under random single-bit transient faults. It achieves a 100 percent empirical detection rate across 150,000 non-crashing corrupted-result cases and maintains application accuracy close to the fault-free baseline over a wide range of fault rates. The scheme incurs only 6.0 percent to 8.4 percent runtime overhead, averaging 6.8 percent, and reduces average protection overhead by 4.9 times compared with direct checksum-based protection.

As the automotive industry advances toward intelligent systems, the risk of chip failures in automotive applications has grown. Functional safety has thus become essential to ensure the reliability of automotive-grade chips. Sequential circuit fault simulation is a key part of functional safety and a major bottleneck in safety verification. The concurrent fault simulation (CFS) method is the most widely used algorithm for this purpose and is adopted in the leading commercial tool Z01X. While recent academic efforts have primarily extended CFS to the RTL level simulation, the fundamental gate level CFS algorithm has seen little improvement, despite its critical role in simulation performance. Two main issues in concurrent fault simulation are inefficient storage and computation of logic values, and performance limitations in its core component, the concurrent fault list. To address these issues, we propose a dual optimization strategy: (1) a bit-compression method that reduces memory overhead and enables fully O(1) time gate evaluation, and (2) a scan list-based concurrent fault list implementation that improves efficiency with low time/space complexity and superior space locality. Experimental results show that our method achieves an average speedup of 6.10× over commercial tool Z01X, with gains exceeding 3× on large circuits, and 2.58× over academic simulator VISION, proving its strong practical value.

As integrated circuit technologies continue to scale toward advanced process nodes, the continual reduction in node capacitance and supply voltage has made digital systems increasingly vulnerable to soft errors. Although traditional full-chip hardening methods can improve reliability, they often incur unacceptable area and power overhead, making selective hardening a more practical engineering solution. However, existing approaches typically rely on time-consuming fault-injection simulation to determine hardening locations through vulnerability analysis, and still depend heavily on manual strategy selection and RTL modification during the hardening stage, making them ill-suited for efficient automated reliability optimization at early design stages. To address these challenges, this paper proposes FT-Pilot, a GNN-guided LLM framework for automatic RTL soft-error hardening. The framework first employs a GNN to identify critical vulnerable assets directly at the RTL level, and then introduces an LLM-driven rewriting engine composed of an analyzer and a rewriter, which performs RTL-level fault-tolerant code rewriting with the support of dual-knowledge-base retrieval-augmented generation and an automatic repair mechanism. Experimental results show that the proposed framework can automatically generate hardened RTL designs that are syntactically correct, functionally correct, and synthesizable across multiple benchmark circuits, while significantly reducing output error rates under soft-error scenarios. This work provides a practical automated path toward shift-left reliability optimization at the RTL level.

While leveraging LLMs to automatically generate SystemVerilog assertions (SVAs) from natural language specifications holds great potential, existing techniques face a key challenge: LLMs often lack sufficient understanding of IC design, leading to poor assertion quality in a single pass. Therefore, verifying whether the generated assertions effectively cover the functional specifications and designing feedback mechanisms based on this coverage remain significant hurdles. To address these limitations, this paper introduces CoverAssert, a novel iterative framework for optimizing SVA generation with LLMs. The core contribution is a lightweight mechanism for matching generated assertions with specific functional descriptions in the specifications. CoverAssert achieves this by clustering the joint representations of semantic features of LLM-generated assertions and structural features extracted from abstract syntax trees (ASTs) about signals related to assertions, and then mapping them back to the specifications to analyze functional coverage quality. Leveraging this capability, CoverAssert constructs a feedback loop based on functional coverage to guide LLMs in prioritizing uncovered functional points, thereby iteratively improving assertion quality. Experimental evaluations on four open-source designs demonstrate that integrating CoverAssert with state-of-the-art generators, AssertLLM and Spec2Assertion, achieves average improvements of 9.57

Boolean equivalence allows Boolean networks with identical functionality to exhibit diverse graph structures. This gives more room for exploration in logic optimization, while also posing a challenge for tasks involving consistency between Boolean networks. To tackle this challenge, we introduce BoolSkeleton, a novel Boolean network skeletonization method that improves the consistency and reliability of design-specific evaluations. BoolSkeleton comprises two key steps: preprocessing and reduction. In preprocessing, the Boolean network is transformed into a defined Boolean dependency graph, where nodes are assigned the functionality-related status. Next, the homogeneous and heterogeneous patterns are defined for the node-level pattern reduction step. Heterogeneous patterns are preserved to maintain critical functionality-related dependencies, while homogeneous patterns can be reduced. Parameter K of the pattern further constrains the fanin size of these patterns, enabling fine-tuned control over the granularity of graph reduction. To validate BoolSkeleton’s effectiveness, we conducted four analysis/downstream tasks around the Boolean network: compression analysis, classification, critical path analysis, and timing prediction, demonstrating its robustness across diverse scenarios. Furthermore, it improves above 55% in the average accuracy compared to the original Boolean network for the timing prediction task. These experiments underscore the potential of BoolSkeleton to enhance design consistency in logic synthesis.

Formal verification with interactive theorem provers can provide strong correctness guarantees for register transfer level designs, but applying it to existing SystemVerilog code requires substantial manual effort in semantic modeling and proof construction. This paper presents Rtl2lean, a framework that automatically translates RTL designs into executable Lean 4 models and builds a hierarchical theorem library for subsequent verification. The generated model represents hardware execution as a pure state transition function, while a four layer theorem framework captures combinational semantics, sequential updates, single cycle behavior, and reachability and invariants. When a high level property cannot be discharged by the existing theorem base, an LLM based proving loop proposes intermediate lemmas from the current proof context and Lean feedback. Only lemmas accepted by the Lean kernel are added to the reusable lemma pool. Experiments on six SystemVerilog designs generate 403 theorems, all of which are successfully checked by Lean. Among 358 foundational lemmas, 287 are available for automatic reuse, yielding a reusable lemma ratio of 80.2 percent. The results demonstrate that Rtl2lean can construct machine checked RTL proof libraries with low checking overhead and substantial cross property lemma reuse.

This is a corrigendum for the article “A data-centric chip design agent framework for Verilog code generation” published in ACM Trans. Des. Autom. Electron Syst. 30, 6, Article 93 (October 2025), 27 pages.

Computer system architecture serves as a crucial bridge between software applications and the underlying hardware, encompassing components like compilers, CPUs, coprocessors, and RTL designs. Its development, from early mainframes to modern domain-specific architectures, has been driven by rising computational demands and advancements in semiconductor technology. However, traditional paradigms in computer system architecture design are confronting significant challenges, including a reliance on manual expertise, fragmented optimization across software and hardware layers, and high costs associated with exploring expansive design spaces. While automated methods leveraging optimization algorithms and machine learning (ML) have improved efficiency, they remain constrained by a single-stage focus, limited data availability, and a lack of comprehensive human domain knowledge. The emergence of large language models (LLMs) offers transformative opportunities for the design of computer system architecture and search paradigms. By leveraging the capabilities of LLMs in areas such as code generation, data analysis, and performance modeling, the traditional manual design process can be transitioned to a machine-based automated design approach. To harness this potential, we present the large processor chip model (LPCM), an LLM-driven framework aimed at achieving end-to-end automated computer system architecture design. The development of LPCM is structured into three levels: (1) human-centric, which assists in code generation and parameter tuning; (2) agent-orchestrated, facilitating cross-layer optimization through toolchain integration (e.g., LLVM, Gem5) and the autonomous execution of subtasks; and (3) model-governed, achieving full automation through the synthesis of hardware-software co-design, simulation, and iterative refinement. This paper utilizes 3D Gaussian splatting (3D GS) as a representative workload and employs the concept of software-hardware collaborative design to examine the implementation of the LPCM at Level 1, demonstrating the effectiveness of the proposed approach. Furthermore, this paper provides an in-depth discussion on the pathway to implementing Level 2 and Level 3 of the LPCM, along with an analysis of the existing challenges.

Fully Homomorphic Encryption (FHE) is rapidly emerging as a promising foundation for privacy-preserving cloud services, enabling computation directly on encrypted data. As FHE implementations mature and begin moving toward practical deployment in domains such as secure finance, biomedical analytics, and privacy-preserving AI, a critical question remains insufficiently explored: how reliable is FHE computation on real hardware? This question is especially important because, compared with plaintext computation, FHE incurs much higher computational overhead, making it more susceptible to transient hardware faults. Moreover, data corruptions are likely to remain silent: the FHE service has no access to the underlying plaintext, causing unawareness even though the corresponding decrypted result has already been corrupted. To this end, we conduct a comprehensive evaluation of SDCs in FHE ciphertext computation. Through large-scale fault-injection experiments, we characterize the vulnerability of FHE to transient faults, and through a theoretical analysis of error-propagation behaviors, we gain deeper algorithmic insight into the mechanisms underlying this vulnerability. We further assess the effectiveness of different fault-tolerance mechanisms for mitigating these faults.

Test point insertion (TPI) is an effective design-for-test (DFT) technique for improving circuit testability. However, conventional TPI is typically applied after logic synthesis and often incurs area and timing overhead. Technology mapping, a critical phase in logic synthesis that converts technology-independent logic networks into standard-cell implementations, provides an opportunity to address this limitation earlier in the design flow. Nevertheless, existing technology mapping methods do not consider testability and are thus not well-suited for TPI. This paper proposes a novel testability-driven technology mapping method to improve the efficiency of TPI. Test point analysis is performed on the And-Inverter Graph (AIG), and the resulting information is used to guide the subsequent TPI-oriented matching stage. Delay-oriented and area-oriented matching are then applied to further optimize timing and area in the final netlist. Experimental results demonstrate that the proposed approach achieves testability comparable to that of the conventional method while requiring fewer test points and a smaller area. For automatic test pattern generation (ATPG) pattern count reduction, it reduces the test point count by an average of 23.65% and the area by an average of 2.80%. For logic built-in self-test (LBIST) test coverage improvement, it achieves average reductions of 20.02% in test point count and 3.47% in area.