paper-with-me

홈 › Papers

LLMPerf: GPU Performance Modeling meets Large Language Models

2025-03-14 · Khoi N. M. Nguyen, Hoang Duy Nguyen Do, Huyen Thao Le, Thanh Tuan Dao

Performance modeling, a pivotal domain in program cost analysis, currently relies on manually crafted models constrained by various program and hardware limitations, especially in the intricate landscape of GPGPU. Meanwhile, Large Language Models (LLMs) have demonstrated their effectiveness in addressing diverse programming challenges. Our work establishes a connection between LLMs and performance modeling, employing the LLM as a performance estimator. Through experimental exploration with carefully designed large-scale OpenCL datasets, we highlight the potential capability as well as the main difficulties of using LLMs in handling performance modeling tasks for OpenCL device source programs. As the first study for this line of work, our LLM-based performance model achieves a mean absolute percentage error of $24.25\%$ for a large-scale generated validation set. On a set of publicly available OpenCL programs, our model achieves a mean absolute percentage error of $46.1\%$.

📄 PDF Abstract BibTeX arXiv:2503.11244

Code (1)

Fsoft-AIC/LLM-Perfomance-Modeling 공식 구현

Tasks

GPU

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation

2025-02-18 · Zhiyuan Liu, Yanchen Luo, Han Huang, Enzhi Zhang 외

3D molecule generation is crucial for drug discovery and material design. While prior efforts focus on 3D diffusion models for their benefits in modeling continuous 3D conformers, they overlook the advantages of 1D SELFI…

3D Generation3D Molecule GenerationDrug DiscoveryLanguage Modeling+2

When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute

2021-02-24 · EMNLP 2021 11 · Tao Lei

Large language models have become increasingly difficult to train because of the growing computation time and cost. In this work, we present SRU++, a highly-efficient architecture that combines fast recurrence and attent…

GPULanguage ModelingLanguage ModellingMachine Translation

When Large Language Model Meets Optimization

2024-05-16 · Sen Huang, Kaixiang Yang, Sheng Qi, Rui Wang

Optimization algorithms and large language models (LLMs) enhance decision-making in dynamic environments by integrating artificial intelligence with traditional techniques. LLMs, with extensive domain knowledge, facilita…

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+1

Trained on 100 million words and still in shape: BERT meets British National Corpus

2023-03-17 · David Samuel, Andrey Kutuzov, Lilja Øvrelid, Erik Velldal

While modern masked language models (LMs) are trained on ever larger corpora, we here explore the effects of down-scaling training to a modestly-sized but representative, well-balanced, and publicly available English tex…

Language ModelingLanguage Modelling

A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions

2025-08-12 · Ziyang Xiao, Jingrong Xie, Lilin Xu, Shisi Guan 외 arxiv

By virtue of its great utility in solving real-world problems, optimization modeling has been widely employed for optimal decision-making across various sectors, but it requires substantial expertise from operations rese…