10 citations · 10 across the 8 of their papers we have counts for
11 papers
Twist, Don't Tilt: Trajectory-Exact Constrained Decoding for Masked Diffusion Models
Aditya Thimmaiah, Lara Marinov, Jayanth Srinivasa +3
Constrained decoding for Masked Diffusion Language Models (MDLMs) aims to ensure that generated outputs satisfy a specified structure or syntax constraint. MDLMs generate outputs b…
Interactive Debugger for Performance Portable Python HPC Kernels
Ivan Grigorik, Gabriel Kosmacher, George Biros +1
We propose PKDB, the first interactive debugger for GPU and multithreaded low-level kernels written in Python. Python is widely used in high performance computing (HPC), with frame…
CROCODIL: Cross-Model Code Editing with LLMs
Linghan Zhong, Aditya Thimmaiah, Jayanth Srinivasa +2
Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants. Different developers may pr…
Predicting Program Exit Code with LLMs and Programming Language Semantics
Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa +2
Large language models (LLMs) have shown proficiency in various software engineering tasks, such as code generation and translation. However, a key limitation in their performance m…
MGQL: An Executable, Small-Step Semantics of GQL
Aditya Thimmaiah, Tong-Nong Lin, Milos Gligoric
ISO Graph Query Language (GQL) is the first international standard for property graph-based graph query languages, standardized as ISO/IEC 39075 in 2024. However, ISO/IEC 39075 cod…
Understanding and Finding JIT Compiler Performance Bugs
Zijian Yi, Cheng Ding, August Shi +1
Just-in-time (JIT) compilers are key components for many popular programming languages with managed runtimes (e.g., Java and JavaScript). JIT compilers perform optimizations and ge…
VLCs: Managing Parallelism with Virtualized Libraries
Yineng Yan, William Ruys, Hochan Lee +11
As the complexity and scale of modern parallel machines continue to grow, programmers increasingly rely on composition of software libraries to encapsulate and exploit parallelism.…
LLMs Lean on Priors, Not Programming Language Semantics
Aditya Thimmaiah, Jiyang Zhang, Jayanth Srinivasa +2
Recent work asks whether large language models (LLMs) condition their reasoning on explicit rules rather than statistical regularities from pretraining. Program execution provides…
A Portable Multi-GPU Solver for Collisional Plasmas with Coulombic Interactions
James Almgren-Bell, Nader Al Awar, Dilip S Geethakrishnan +2
We study parallel particle-in-cell (PIC) methods for low-temperature plasmas (LTPs), which discretize kinetic formulations that capture the time evolution of the probability densit…
Java JIT Testing with Template Extraction
Zhiqiang Zang, Fu-Yao Yu, Aditya Thimmaiah +2
We present LeJit, a template-based framework for testing Java just-in-time (JIT) compilers. Like recent template-based frameworks, LeJit executes a template -- a program with holes…
Object Graph Programming
Aditya Thimmaiah, Leonidas Lampropoulos, Christopher J. Rossbach +1
We introduce Object Graph Programming (OGO), which enables reading and modifying an object graph (i.e., the entire state of the object heap) via declarative queries. OGO models the…