# Learning Intermediate Representations using Graph Neural Networks for NUMA and Prefetchers Optimization

arXiv: https://arxiv.org/abs/2203.00611 · HTML: https://mlsanity.com/paper/2203.00611/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 59 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Learning to Represent Programs with Graphs](https://mlsanity.com/paper/1711.00740/) (2017)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [A Convolutional Attention Network for Extreme Summarization of Source Code](https://mlsanity.com/paper/1602.03001/) (2016)
- [Neural Code Comprehension: A Learnable Representation of Code Semantics](https://mlsanity.com/paper/1806.07336/) (2018)
- [ProGraML: Graph-based Deep Learning for Program Optimization and Analysis](https://mlsanity.com/paper/2003.10536/) (2020)
- [Advancements in Image Classification using Convolutional Neural Network](https://mlsanity.com/paper/1905.03288/) (2019)
- [Structured Generative Models of Natural Source Code](https://mlsanity.com/paper/1401.0514/) (2014)
- [funcGNN: A Graph Neural Network Approach to Program Similarity](https://mlsanity.com/paper/2007.13239/) (2020)

## Built on by (most cited first, 9 of 9)

- [The Landscape and Challenges of HPC Research and LLMs](https://mlsanity.com/paper/2402.02018/) (2024)
- [Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation](https://mlsanity.com/paper/2305.05779/) (2023)
- [Performance Optimization using Multimodal Modeling and Heterogeneous GNN](https://mlsanity.com/paper/2304.12568/) (2023)
- [AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs](https://mlsanity.com/paper/2310.04047/) (2023)
- [Heterogeneous Graph Neural Networks for Software Effort Estimation](https://mlsanity.com/paper/2206.11023/) (2022)
- [PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis](https://mlsanity.com/paper/2306.00210/) (2023)
- [Power Constrained Autotuning using Graph Neural Networks](https://mlsanity.com/paper/2302.11467/) (2023)
- [MIREncoder: Multi-modal IR-based Pretrained Embeddings for Performance Optimizations](https://mlsanity.com/paper/2407.02238/) (2024)
- [Accelerating Transfer-Learning-Based Autotuning with Predictive LLVM IR Performance Ranking](https://mlsanity.com/paper/2609.15807/) (2026)

## Abstract (arXiv)

There is a large space of NUMA and hardware prefetcher configurations that can significantly impact the performance of an application. Previous studies have demonstrated how a model can automatically select configurations based on the dynamic properties of the code to achieve speedups. This paper demonstrates how the static Intermediate Representation (IR) of the code can guide NUMA/prefetcher optimizations without the prohibitive cost of performance profiling. We propose a method to create a comprehensive dataset that includes a diverse set of intermediate representations along with optimum configurations. We then apply a graph neural network model in order to validate this dataset. We show that our static intermediate representation based model achieves 80% of the performance gains provided by expensive dynamic performance profiling based strategies. We further develop a hybrid model that uses both static and dynamic information. Our hybrid model achieves the same gains as the dynamic models but at a reduced cost by only profiling 30% of the programs.