7 citations · 13 across the 15 of their papers we have counts for
15 papers
Tensor Seeks Layout: Formalizing Layout Selection for ML Compilers
Clemens Eisenhofer, Yuwen Jia, Daniel Kroening +1
Modern machine learning compilers select tensor memory layouts to minimize execution cost under hardware constraints. Layout selection is global: an operator may be fastest under o…
A Barrier-Free Synchronization Algorithm for Multi-Engine AI Accelerators
Chungha Sung, Nikil V. Shyamsunder, Hanliang Zhang +2
Multi-engine AI accelerators such as AWS Trainium comprise specialized compute engines that execute in parallel, and the compiler must synchronize the data dependencies between the…
Mostly Automatic Translation of Language Interpreters from C to Safe Rust
Bo Wang, Brandon Paulsen, Joey Dodds +3
Translating C programs to safe Rust is challenging owing to significant differences in typing constraints, ownership, and borrowing rules. Interpreter programs are particularly imp…
Axon: A Synthesizing Superoptimizer for Tensor Programs
Akash Kothari, Shaowei Zhu, Daniel Kroening +1
Writing high performance kernels for AI accelerators requires deep expertise in tiling, instruction selection, data layout, and operator fusion placing a significant burden on prog…
EventADL: Open-Box Anomaly Detection and Localization Framework for Events in Cloud-Based Service Systems
Luan Pham, Victor Nicolet, Joey Dodds +2
Anomaly detection and localization (ADL) is critical for maintaining reliability and availability in cloud systems. Recent ADL developments focus on metric and log data, leaving ev…
ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories
Ali Reza Ibrahimzada, Brandon Paulsen, Daniel Kroening +1
Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effo…
Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents
Zhenning Yang, Hui Guan, Victor Nicolet +4
Cloud infrastructure is managed through a mix of interfaces -- traditionally, cloud consoles, command-line interfaces (CLI), and SDKs are the tools of choice. Recently, Infrastruct…
Hypergraph-Guided Regex Filter Synthesis for Event-Based Anomaly Detection
Margarida Ferreira, Victor Nicolet, Luan Pham +4
We propose HyGLAD, a novel algorithm that automatically builds a set of interpretable patterns that model event data. These patterns can then be used to detect event-based anomalie…
MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
Ali Reza Ibrahimzada, Brandon Paulsen, Reyhaneh Jabbarvand +2
Code translation transforms source code from one programming language (PL) to another. Validating the functional equivalence of translation and repairing, if necessary, are critica…
The Secrets Must Not Flow: Scaling Security Verification to Large Codebases (extended version)
Linard Arquint, Samarth Kishor, Jason R. Koenig +3
Existing program verifiers can prove advanced properties about security protocol implementations, but are difficult to scale to large codebases because of the manual effort require…
Program Synthesis from Partial Traces
Margarida Ferreira, Victor Nicolet, Joey Dodds +1
We present the first technique to synthesize programs that compose side-effecting functions, pure functions, and control flow, from partial traces containing records of only the si…
Scalable, Validated Code Translation of Entire Projects using Large Language Models
Hanliang Zhang, Cristina David, Meng Wang +2
Large language models (LLMs) show promise in code translation due to their ability to generate idiomatic code. However, a significant limitation when using LLMs for code translatio…
Quantifying the benefits of code hints for refactoring deprecated Java APIs
Cristina David, Pascal Kesseli, Daniel Kroening +1
When done manually, refactoring legacy code in order to eliminate uses of deprecated APIs is an error-prone and time-consuming process. In this paper, we investigate to which degre…
VERT: Verified Equivalent Rust Transpilation with Large Language Models as Few-Shot Learners
Aidan Z. H. Yang, Yoshiki Takashima, Brandon Paulsen +2
Rust is a programming language that combines memory safety and low-level control, providing C-like performance while guaranteeing the absence of undefined behaviors by default. Rus…
Towards Translating Real-World Code with LLMs: A Study of Translating to Rust
Hasan Ferit Eniser, Hanliang Zhang, Cristina David +5
Large language models (LLMs) show promise in code translation - the task of translating code written in one programming language to another language - due to their ability to write…