# Can Large Language Models Predict Parallel Code Performance?

arXiv: https://arxiv.org/abs/2505.03988 · HTML: https://mlsanity.com/paper/2505.03988/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 8 of 8)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [The Effect of Sampling Temperature on Problem Solving in Large Language Models](https://mlsanity.com/paper/2402.05201/) (2024)
- [Performance-Aligned LLMs for Generating Fast Code](https://mlsanity.com/paper/2404.18864/) (2024)
- [Forecasting GPU Performance for Deep Learning Training and Inference](https://mlsanity.com/paper/2407.13853/) (2024)
- [HPC-Coder: Modeling Parallel Programs using Large Language Models](https://mlsanity.com/paper/2306.17281/) (2023)
- [Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C++](https://mlsanity.com/paper/2307.07686/) (2023)
- [A Model Is Not Built By A Single Prompt: LLM-Based Domain Modeling With Question Decomposition](https://mlsanity.com/paper/2410.09854/) (2024)

## Built on by (most cited first, 4 of 4)

- [Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation](https://mlsanity.com/paper/2512.03086/) (2025)
- [Counting Without Running: Evaluating LLMs' Reasoning About Code Complexity](https://mlsanity.com/paper/2512.04355/) (2025)
- [ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation](https://mlsanity.com/paper/2601.04327/) (2026)
- [ZeroDVFS: Zero-Shot LLM-Guided Core and Frequency Allocation for Embedded Platforms](https://mlsanity.com/paper/2601.08166/) (2026)

## Abstract (arXiv)

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? For this study, we build a balanced dataset of 340 GPU kernels, obtained from HeCBench benchmark and written in CUDA and OpenMP, along with their ground-truth labels obtained via empirical GPU profiling. We evaluate LLMs across four scenarios: (1) with access to profiling data of the kernel source, (2) zero-shot with source code only, (3) few-shot with code and label pairs, and (4) fine-tuned on a small custom dataset. Our results show that state-of-the-art LLMs have a strong understanding of the Roofline model, achieving 100% classification accuracy when provided with explicit profiling data. We also find that reasoning-capable LLMs significantly outperform standard LLMs in zero- and few-shot settings, achieving up to 64% accuracy on GPU source codes, without profiling information. Lastly, we find that LLM fine-tuning will require much more data than what we currently have available. This work is among the first to use LLMs for source-level roofline performance prediction via classification, and illustrates their potential to guide optimization efforts when runtime profiling is infeasible. Our findings suggest that with better datasets and prompt strategies, LLMs could become practical tools for HPC performance analysis and performance portability.