Papers for

chip design 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.

Microarchitecture aware assertion generation improves cpu verification

MicroAssert: Microarchitecture-Aware Structured Assertion Generation for CPU Verification

Abstract: Automatic assertion generation reduces manual verification effort, yet existing approaches struggle to capture microarchitectural behaviors and cross-region interactions in CPUs. We present MicroAssert, a microarchitecture-aware framework that identifies functional regions directly from RTL and generates local and composite assertions through structured contracts and deterministic verification primitives. Coverage-guided feedback further improves verification completeness by progressively expanding proof-relevant RTL coverage. Evaluated on five open-source RISC-V CPUs against three existing assertion generation approaches, MicroAssert achieves 100% syntax correctness and complete branch, statement, and toggle coverage, with an average proven rate of 74.82% and Proof Core coverage of 90.96%. Mutation testing further demonstrates its advantage, achieving an average error detection rate of 28.73%, 1.99 to 3.51 times higher than existing methods. These results demonstrate the effectiveness of microarchitecture-aware assertion generation.

Wed 18 NovHardware ArchitectureSoftware Engineering
The gist
Verifying that computer processors work correctly is very complicated because of their detailed internal structure. The authors present MicroAssert, a new method that understands the processor's inner parts to automatically create checks that confirm the processor behaves as expected. MicroAssert improves test coverage and detects errors more effectively than earlier methods. This helps make sure CPUs are reliable without as much manual effort.
Open → 2611.24872v1

Knowledge driven AI speeds microchip architecture design space search

KD-DSE: A Knowledge-Driven LLM Framework for Fast Microarchitecture Design Space Exploration

Abstract: Domain-specific architectures have made design space exploration (DSE) a bottleneck of processor design, yet each candidate costs a full simulation, so exhaustive search is out of reach. Surrogate models need thousands of simulations before they predict reliably, and LLM agents that search directly hallucinate, lack cold-start architectural knowledge, and follow a fixed per-round policy. We present KD-DSE, a knowledge- driven LLM framework for fast microarchitecture DSE. KD- DSE couples a five-state constrained agent with real gem5- McPAT evaluation, retrieves architect-curated guidance from an Architecture Knowledge Base conditioned on the current search state and bottleneck diagnosis, and allocates its budget with a diagnosis-guided two-phase exploration strategy. On a 29- parameter out-of-order core with a budget of 18 simulations, KD-DSE achieves about 4.8% higher hypervolume and about 21.7% lower ADRS than the state-of-the-art MicroEvo, and the ablation attributes the gain chiefly to the Knowledge Base. These results indicate that constraining LLM reasoning and grounding it in architectural knowledge can drive fast and effective microarchitecture DSE. The code will be open-sourced upon acceptance.

Tue 17 NovHardware Architecture
The gist
Designing computer processors involves testing many chip configurations, which takes a lot of time because each test is slow. The authors created KD-DSE, a system that uses artificial intelligence guided by expert knowledge to pick smarter tests and make better decisions during design. This means it can find good processor designs faster and with fewer tests than existing methods. Their results showed a significant improvement using real simulations and architectural insights.
Open → 2611.22411v1

Prism enhances chip designs by cutting power delay and size costs

PRISM: Preference-based Reward and Uncertainty-Integrated Synthesis Minimization for RTL PPA Optimization

Abstract: This paper introduces a budget-aware, multi-objective framework (called PRISM) for RTL optimization that improves power, performance, and area (PPA) while sharply limiting expensive commercial synthesis tool calls. Starting from a synthesizable baseline and functional testbench, the method iterates through LLM-driven rewrite generation, fast compile/simulation equivalence filtering, low-cost proxy feature extraction, and selective commercial synthesis tool (Synopsys Design Compiler (DC)) evaluation. To prioritize which candidates deserve high-quality synthesis, we train a preference-based reward model using pairwise ranking supervision derived from commercial synthesis tool outcomes, and combine ensemble uncertainty with a diversity-aware acquisition rule to avoid early bias and redundant evaluations. A key advantage is that PRISM maintains a best-tradeoff set G of non-dominated designs throughout the run: G preserves the best solutions found so far, is fed back into generation and refinement, and enables consistent, cumulative improvements rather than repeatedly restarting from the baseline. Across RTLLM v2.0 modules, the approach consistently yields post-synthesis gains under fixed commercial synthesis tool call budgets, and ablations confirm that reward-guided selection and candidate dropping are central to sample-efficient progress. PRISM efficacy is evaluated across multiple technology nodes (7 nm, 15 nm, and 45 nm) using identical pipelines without retraining.

Sun 8 NovHardware ArchitectureSoftware Engineering
The gist
Improving computer chip designs can be slow and expensive because of the testing needed after each change. The authors introduce PRISM, a system that smartly picks and tests design tweaks using AI to reduce costly full evaluations. PRISM learns which changes will likely improve chip power, speed, and size while avoiding wasted effort on less promising options. It keeps track of the best designs found so far, helping it get steadily better without starting over each time. The method worked well on multiple chip types and technology sizes without needing to relearn.
Open → 2611.11051v1

Agentic LLM agents improve black-box optimization across domains

A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization

Abstract: Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large language model (LLM) agents offer a new way to approach BBO by combining task semantics, computation, optimization tools, and feedback-driven decision making, showing great potential due to the integration with mathematically rigorous tools. However, existing agentic BBO studies use different task domains and system configurations, making their results difficult to compare and the effects of individual design choices hard to isolate. We therefore introduce AgenticBBO-Bench, a cross-domain benchmark for agentic BBO spanning synthetic functions, hyperparameter optimization, database tuning, chip design, and molecular design under a unified finite-budget evaluation protocol. In our experiments, agentic BBO achieves higher family-averaged scores than direct LLM-based methods in all five domains and outperforms the best numerical optimizers in four. We further study three factors shaping agent performance: optimization tools, task information and prior knowledge, and the role of the LLM during search. Our results show that additional numerical tools do not consistently improve performance, task semantics are broadly useful while more specific priors are less reliable, and numerical optimizers can effectively absorb gains from search trajectories established by the agent. Finally, we introduce a five-task frontier challenge within AgenticBBO-Bench and evaluate seven LLMs under the Codex agent harness, where GPT-6 Astra and DeepSeek-V4.1-Flash lie on the Pareto frontier of performance and cost among the evaluated models. Our code is available at https://github.com/lamda-bbo/agentic-bbo.

Thu 8 OctMachine LearningArtificial IntelligenceNeural and Evolutionary Computing
The gist
Black-box optimization means finding the best solution when you can only check results, and checking is expensive. The authors studied how large language model (LLM) agents can help solve these problems by combining language understanding with math tools. They created a benchmark that tests these agents on different tasks like tuning databases and designing molecules. Their tests showed that agentic LLMs generally do better than direct LLM methods and even beat some traditional numeric optimizers. They also found that the usefulness of math tools and task knowledge varies, and some of the gains come from combining LLM strategies with good numeric optimizers.
Open → 2610.12183v1

Exactly checking clock tree timings to improve chip scheduling precision

Beyond No-Good Benders Cuts: Exact Realizability for Discretely Tunable Clock Trees

Abstract: Useful-skew schedules can satisfy timing constraints yet remain unrealizable by a fixed clock tree with discrete tuning choices. We formulate this mismatch as exact membership in a finite relative-latency set and develop a checkable feedback interface between the scheduler and the tree model. Arithmetic certificates explain unrealizable targets, while tree-specific contraction reduces the structural size of the exact relations projected onto selected sinks. These relations become realizability cuts that can exclude more candidates than a no-good on the same certificate support, including discrete holes that linear inequalities cannot separate. Controlled experiments confirm fewer oracle calls and faster projection construction. They also expose important limits: globally minimum certificates can cost more than they save, compact arithmetic feedback can fail on non-parity obstructions, and direct monolithic optimization remains faster on the tested additive models. The contribution is an exact, independently verifiable scheduler--tree interface, rather than a claim of universal solver acceleration or physical signoff.

Tue 6 OctHardware Architecture
The gist
Designing computer chips involves making sure signals reach different parts at the right times using clock trees. Sometimes, schedules that look good on paper can't actually be built with the available hardware settings. The authors created a method to precisely verify if a given timing plan can be realized by the clock tree setup. Their approach can explain when and why a timing plan is impossible and can improve scheduling by avoiding impossible cases earlier. They also show limits where their method may be slower or less compact than traditional optimization.
Open → 2610.07600v1

Analog design agents improve long task success with reference circuits

Long-Horizon Analog Design Bench: Benchmarking Agents on Hours-Long Analog and Mixed-Signal Circuit Design Tasks

Abstract: Coding agents now sustain hours-long, tool-driven loops, yet their ability to carry long-horizon analog and mixed-signal circuits to electrical specification remains unmeasured. We introduce Analog Design Bench, a long-horizon agentic benchmark of 50 transistor-level design tasks contributed by 17 chip designers. Agents work with an open-source simulator, while an isolated verifier evaluates the submitted circuit using specification-based electrical tests. We evaluate 15 agent configurations across 2,250 two-hour attempts and observe full-specification pass rates from 8.0% to 78.0%. Coding-benchmark performance correlates with analog results but leaves much of the performance spread unexplained. Our failure analysis shows that most unsuccessful submissions have no recorded legality rejection but fail electrical acceptance, identifying electrical closure as the dominant endpoint challenge. We test time, reasoning effort, agent harness, and supplied design knowledge as interventions. Longer budgets and higher reasoning effort improve performance, while general skill documents provide little benefit and sometimes reduce performance. Supplying a task-matched reference topology, an idealized form of circuit-IP retrieval, raises DeepSeek V4 Pro by 18.7 percentage points and mainly accelerates GPT-5.6 Sol.

Sun 27 SeptArtificial Intelligence
The gist
Designing analog circuits can take many hours, and it's not clear how well AI tools handle such long projects. The authors created a benchmark with 50 complex circuit tasks from real designers to test AI agents over hours-long attempts. They found that success rates vary widely and that providing example reference circuits helps agents complete designs faster and more accurately. This work sheds light on the challenges of automated analog circuit design and ways to improve tool performance.
Open → 2609.33356v1

PlaceReasoner Beta improves macro placement in chip design using reasoning

PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking

Abstract: Automated macro placement remains a fundamental challenge in VLSI physical design. Despite decades of research, existing approaches predominantly optimize hand-crafted proxy objectives, such as estimated wirelength, and typically produce placements through one-shot numerical optimization, limiting their ability to incorporate visual layout context, codified design expertise, and downstream physical-design feedback in a unified loop. We present PlaceReasoner-Beta, a verifier-guided multi-agent framework that reformulates macro placement as a closed-loop reasoning problem rather than black-box optimization. A vision-language model (VLM) planner generates candidate placements from the floorplan image, macro specifications, and connectivity structure; a geometric verifier enforces physical legality and expert placement principles; a physical verifier refines candidates using early implementation feedback; and a post-route optimizer further improves promising layouts using final PPA. To enable reproducible evaluation, we introduce PlaceReasoner-Bench, a fully open end-to-end benchmark built from open RTL designs, EDA tools, and technology libraries. It comprises 8 designs at two aspect ratios, yielding 16 tasks with fixed floorplans and I/O assignments, so methods differ only in macro positions and orientations and are evaluated using routed PPA and DRC rather than pre-route proxies. Across the benchmark, PlaceReasoner-Beta achieves the best timing among DRC-clean methods on all square tasks, reducing post-route TNS by 61.2% at 1:1 and 53.0% at 2:1 relative to the classical baseline field. It also shortens routed wirelength on most designs despite never explicitly optimizing it, demonstrating that reasoning over spatial structure under physical-design feedback can improve end-to-end layout quality beyond proxy-objective optimization.

Fri 18 SeptArtificial Intelligence
The gist
Designing the layout of computer chips is tricky, especially deciding where to place large parts called macros. Existing methods optimize simple estimates but often miss the bigger picture of design rules and feedback from later steps. The authors propose PlaceReasoner-Beta, which uses a reasoning loop involving visual understanding, rules checking, and feedback to create better layouts. They tested it on various chip designs and found it improves timing and wiring without focusing directly on those metrics.
Open → 2609.21263v1

AutoTrans automates secure RISC-V assertion translation with AI help

AutoTrans: AI-Assisted Automatic Translation of Security Assertions for RISC-V Processors

Abstract: Reusing a set of verified security assertions across RISC-V processor targets remains one of the most expensive bottlenecks in hardware security verification. Manual translation takes hours per assertion. Raw LLM translation is fast but unreliable, introducing signal hallucination, where the model invents port names absent from the target RTL and produces outputs that may vary across model updates or even within the same model version. This paper presents AutoTrans, an automated framework that addresses the above shortcomings. First, a new lightweight Regular Expression-based System Verilog signal extractor is proposed to identify the signals for generating security assertions. This step is necessary to prevent signal hallucination. Second, a template is introduced to create prompt and pinned inference parameters that guarantee a byte-identical prompt assembly on every run, making the pipeline output resilient to model updates. Moreover, the introduced template for LLM prompting is capable of generating security assertions from English-only security descriptions of RISC-V processors, with no manual authoring. Third, a formal verification process (JasperGold FPV) is integrated, which guarantees that the generated security assertions verify the security of the RISC-V processor rather than silently entering the result set. The workflow is applied on Deepseek V4 to translate security assertions from one RISC-V to another (e.g., for IBEX from NS31A RISC-V). The experiment shows that AutoTrans achieves 78\% Auto Translation Acceptance Rate (TAR) automatically and without human intervention and 100\% Final TAR after refinement by humans.

Wed 9 SeptCryptography and SecurityHardware Architecture
The gist
Translating security checks from one RISC-V processor to another is usually slow and error-prone when done by hand. The authors built AutoTrans, a tool that uses AI combined with careful signal detection and prompt control to automatically generate these security assertions reliably. It also verifies the generated assertions formally to ensure they really check security. Tests show AutoTrans works well on real processors, needing little or no human fixes after AI translation.
Open → 2609.10057v1