Modern GPUs evolve rapidly, yet production compilers still rely on hand-crafted register allocation heuristics that require substantial retuning for each hardware generation.We introduce VERILOCC, a framework that combines large language models (LLMs) with formal compiler techniques to enable generalizable and verifiable register allocation across GPU architectures.VERILOCC fine-tunes an LLM to translate intermediate representations (MIRs) into target-specific register assignments, aided by static analysis for cross-architecture normalization and generalization and a verifierguided regeneration loop to ensure correctness.Evaluated on matrix multiplication (GEMM) and multi-head attention (MHA), VERILOCC achieves 85-99% single-shot accuracy and near-100% [email protected] study shows that VERILOCC discovers more performant assignments than expert-tuned libraries, outperforming rocBLAS by over 10% in runtime.

Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g., SQL injection vulnerabilities) and maintainability (e.g., missing type annotations). Existing methods, such as supervised fine-tuning and rule-based post-processing, rely on labor-intensive annotations or brittle heuristics, limiting their scalability and effectiveness. We propose REAL (Reinforcement rEwards from Automated anaLysis), a reinforcement learning framework that trains LLMs to generate production-quality code using program analysis–guided feedback. Specifically, REAL integrates two automated signals: (1) static analyzers detecting security and maintainability defects and (2) unit tests ensuring functional correctness. Unlike prior work, our framework is prompt-agnostic and reference-free, enabling scalable supervision without manual intervention. Experiments across multiple datasets and model scales demonstrate that REAL outperforms state-of-the-art methods in simultaneous assessments of functionality and code quality. Our work bridges the gap between rapid prototyping and production-ready code, enabling LLMs to deliver both speed and quality.

Security for applications running on mobile devices is important. In this paper we present ExpressOS, a new OS for enabling high-assurance applications to run on commodity mobile devices securely. Our main contributions are a new OS architecture and our use of formal methods for proving key security invariants about our implementation. In our use of formal methods, we focus solely on proving that our OS implements our security invariants correctly, rather than striving for full functional correctness, requiring significantly less verification effort while still proving the security relevant aspects of our system.

Diagnosing problems in networks is a time-consuming and error-prone process. Existing tools to assist operators primarily focus on analyzing control plane configuration. Configuration analysis is limited in that it cannot find bugs in router software, and is harder to generalize across protocols since it must model complex configuration languages and dynamic protocol behavior.

Computer systems often fail due to many factors such as software bugs or administrator errors. Diagnosing such production run failures is an important but challenging task since it is difficult to reproduce them in house due to various reasons: (1) unavailability of users' inputs and file content due to privacy concerns; (2) difficulty in building the exact same execution environment; and (3) non-determinism of concurrent executions on multi-processors.