Work

Can Large Language Models Predict Parallel Code Performance?

Year: 2025

Type: conference-paper

Abstract: Accurate determination of the performance of parallel GPU code typically requires execution-time profiling on target hardware - an increasingly prohibitive step due to limited access to high-end GPUs. This paper explores whether Large Language Models (LLMs) can offer an alternative approach for GPU performance prediction without relying on hardware. We frame the problem as a roofline classification task: given the source code of a GPU kernel and the hardware specifications of a target GPU, can an LLM predict whether the GPU kernel is compute-bound or bandwidth-bound?

Source: ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC)

DOI: 10.1145/3731545.3743645

Authors: Gregory Bolet, Giorgis Georgakoudis, Harshitha Menon, Konstantinos Parasyris, Niranjan Hasabnis, Hayden Estes, Kirk Cameron, Gal Oren

Institutions: Virginia Tech, Lawrence Livermore National Laboratory, Stanford University

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4414210334

FWCI: 2.717

Cites: 23

Cited by: 3

Related to: