6 papers
Correct but Slow: An Empirical Study of the GPU Kernel Evaluation Gap in Modern Domain-Specific Languages
Tingxi Li, Ravishka Rathnasuriya, Wei Yang
The paper empirically investigates why GPU kernels written in modern DSLs like Triton and TileLang can be functionally correct yet dramatically slower than library implementations,…
Characterizing Real-World Bugs in Tile Programs for Automated Bug Detection
Ravishka Rathnasuriya, Zihe Song, Nidhi Majoju +4
Tile-based programming frameworks are increasingly adopted to write high-performance GPU kernels in domains such as deep learning and scientific computing. While these frameworks e…
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines
Tingxi Li, Mingfang Ji, Ravishka Shemal Rathnasuriya +3
Modern machine learning deployments increasingly compose specialized models into dynamic inference pipelines, where upstream components produce intermediate predictions that determ…
Tunable Luttinger liquid and correlated insulating states in one-dimensional moiré superlattices
Jiajun Chen, Bosai Lyu, Liguo Wang +23
Two-dimensional moiré superlattices have been extensively studied, and a variety of correlated phenomena have been observed. However, their lower-dimensional counterpart, one-dime…
Efficiency Robustness of Dynamic Deep Learning Systems
Ravishka Rathnasuriya, Tingxi Li, Zexin Xu +4
Deep Learning Systems (DLSs) are increasingly deployed in real-time applications, including those in resourceconstrained environments such as mobile and IoT devices. To address eff…