Publications

You can also find my articles on my Google Scholar profile.

Highlighted publications

A few recent pieces I am especially excited about.

arXiv 2025

Integrating Performance Tools in Model Reasoning for GPU Kernel Optimization

We train a large reasoning model for GPU kernel optimization and see impressive speedups on real scientific applications.

LLM4Code 2025

The Shortcomings of Code LLMs in Modeling Code Properties

A short paper demonstrating that graph representations of LLVM IR are much more effective and efficient at modeling certain code properties.

SC 2024

A Probabilistic Approach To Selecting Build Configurations in Package Managers

We utilize machine learning and probabilistic answer set programming to improve package configuration selection in Spack.

All publications

arXiv 2025

LLMs as Packagers of HPC Software

C. Melone, D. Nichols, K. Parasyris, T. Gamblin, H. Menon. LLMs as Packagers of HPC Software. arXiv. 2511.05626. 2025.

ICPP 2025

ParEval-Repo: A Benchmark Suite for Evaluating LLMs with Repository-level HPC Translation Tasks

J. H. Davis, D. Nichols, I. Khillan, A. Bhatele. ParEval-Repo: A Benchmark Suite for Evaluating LLMs with Repository-level HPC Translation Tasks. ICPP 2025.

arXiv 2025

Modeling Code: Is Text All You Need?

D. Nichols, K. Parasyris, H. Menon, B. R. Bartoldson, G. Georgakoudis, T. Ben-Nun, A. Bhatele. Modeling Code: Is Text All You Need? arXiv. 2507.11467. 2025.

ISC 2025

HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages

A. Chaturvedi*, D. Nichols*, S. Singh, A. Bhatele. HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages. ISC 2025.

LLM4HPC 2025

Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions

K. Teranishi, H. Menon, W. F Godoy, P. Balaprakash, D. Bau, T. Ben-Nun, A. Bhatele, F. Franchetti, M. Franusich, T. Gamblin, G. Georgakoudis, T. Goldstein, A. Guha, S. Hahn, C. Iancu, Z. Jin, T. Jones, T. Meng Low, H. Mankad, N. Rao Miniskar, M. Alaul Haque Monil, D. Nichols, K. Parasyris, S. Pophale, P. Valero-Lara, J. S. Vetter, S. Williams, A. Young. Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions. LLM4HPC 2025.

CCGrid 2025

xAMM: "Attention" to Details Improve Cross-Platform Prediction Accuracy

A. R. Dhakal, T. Z. Islam, A. Dey, T. Patki, D. Nichols, A. Bhatele, J.-S. Yeom. xAMM: "Attention" to Details Improve Cross-Platform Prediction Accuracy. CCGrid 2025.

COMPSAC 2024

Relative Performance Prediction Using Few-Shot Learning

A. Dey, A. Dhakal, T. Islam, JS. Yeom, T. Patki, D. Nichols, A. Movsesyan, A. Bhatele. Relative Performance Prediction Using Few-Shot Learning. COMPSAC 2024.

HPDC 2024

Can Large Language Models Write Parallel Code?

D. Nichols, J. H. Davis, Z. Xie, A. Rajaram, A. Bhatele. Can Large Language Models Write Parallel Code?. HPDC 2024.

ISC 2024

HPC-Coder: Modeling Parallel Programs using Large Language Models

D. Nichols, A. Marathe, H. Menon, T. Gamblin, A. Bhatele. ISC 2024.

arXiv 2024

Performance-Aligned LLMs for Generating Fast Code

D. Nichols, P. Polasam, H. Menon, A. Marathe, T. Gamblin, A. Bhatele. Performance-Aligned LLMs for Generating Fast Code. arXiv. cs.DC. 2404.18864. 2024.

MSR 2024

Learning to Predict and Improve Build Successes in Package Ecosystems

H. Menon^∗, D. Nichols^∗, A. Bhatele, T. Gamblin. Learning to Predict and Improve Build Successes in Package Ecosystems. MSR 2024. * Authors contributed equally.

arXiv 2024

Automated Programmatic Performance Analysis of Parallel Programs

O. Cankur, A. Tomar, D. Nichols, C. Scully-Allison, K. E. Isaacs, A. Bhatele. Automated Programmatic Performance Analysis of Parallel Programs. arXiv. 2401.13150. 2024.

IPDPS 2024

Predicting Cross-Architecture Performance of Parallel Programs

D. Nichols, A. Movsesyan, J-S Yeom, D. Milroy, T. Patki, A. Sarkar, A. Bhatele. Predicting Cross-Architecture Performance of Parallel Programs. IPDPS 2024.

IPDPS 2023