Supercharge Compiler Engineering with LLMs
This program is tentative and subject to change.
The field of compiler engineering has long relied on deep human expertise and painstaking manual effort for tasks like finding subtle bugs or optimizing performance. This labour-intensive process, however, fundamentally limits the pace of development and analysis. This talk presents our recent work on how Large Language Models (LLMs) can fundamentally supercharge this process, allowing engineers to operate with unprecedented speed and efficiency. We will demonstrate how LLMs can intelligently (1) generate candidates for missed peephole optimizations and (2) implement language-specific transformations to automate the debugging workflow.
Lecturer (Assistant Professor) at Monash University. PhD from UWaterloo and HKUST.
This program is tentative and subject to change.
Sat 18 OctDisplayed time zone: Perth change
13:45 - 15:30 | Programming Language & CompilerSponsor Invited Talks at Peony NE Chair(s): Zhiyang Chen University of Toronto 13:45 - 15:45 (Instead of 15:30), 30 min each talk | ||
13:45 26mTalk | Programming Language Design for GPU Systems Sponsor Invited Talks Michel Steuwer Technische Universität Berlin | ||
14:11 26mTalk | CStar: Unifying Programming and Verification in C Sponsor Invited Talks Di Wang Peking University | ||
14:37 26mTalk | Supercharge Compiler Engineering with LLMs Sponsor Invited Talks Yongqiang Tian Monash University | ||
15:03 26mTalk | Python, Is It Being Killed by Incremental Improvements? Sponsor Invited Talks Stefan Marr University of Kent | ||
