# GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Units

arXiv: https://arxiv.org/abs/2502.06921 · HTML: https://mlsanity.com/paper/2502.06921/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 19 of 19)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://mlsanity.com/paper/2402.07630/) (2024)
- [GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning](https://mlsanity.com/paper/2405.20139/) (2024)
- [AEGNN: Asynchronous Event-based Graph Neural Networks](https://mlsanity.com/paper/2203.17149/) (2022)
- [EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks](https://mlsanity.com/paper/1909.00155/) (2019)
- [Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks](https://mlsanity.com/paper/1705.01626/) (2017)
- [Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions](https://mlsanity.com/paper/2009.06435/) (2020)
- [Towards Efficient Graph Convolutional Networks for Point Cloud Handling](https://mlsanity.com/paper/2104.05706/) (2021)
- [G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency](https://mlsanity.com/paper/2109.08983/) (2021)
- [EvGNN: An Event-driven Graph Neural Network Accelerator for Edge Vision](https://mlsanity.com/paper/2404.19489/) (2024)
- [Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms](https://mlsanity.com/paper/2303.10875/) (2023)
- [FlexNN: A Dataflow-aware Flexible Deep Learning Accelerator for Energy-Efficient Edge Devices](https://mlsanity.com/paper/2403.09026/) (2024)
- [Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems](https://mlsanity.com/paper/2404.05605/) (2024)
- [NITRO: LLM Inference on Intel Laptop NPUs](https://mlsanity.com/paper/2412.11053/) (2024)

## Built on by (most cited first, 2 of 2)

- [GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search](https://mlsanity.com/paper/2512.11856/) (2025)
- [KATANA: A Fast, Low-Power Mapping of Kalman Filters onto Edge NPUs for Real-Time Tracking](https://mlsanity.com/paper/2606.14992/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) are vital for learning from graph-structured data, enabling applications in network analysis, recommendation systems, and speech analytics. Deploying them on edge devices like client PCs and laptops enhances real-time processing, privacy, and cloud independence. GNNs aid Retrieval-Augmented Generation (RAG) for Large Language Models (LLMs) and enable event-based vision tasks. However, irregular memory access, sparsity, and dynamic structures cause high latency and energy overhead on resource-constrained devices. While modern edge processors integrate CPUs, GPUs, and NPUs, NPUs designed for data-parallel tasks struggle with irregular GNN computations. We introduce GraNNite, the first hardware-aware framework optimizing GNN execution on commercial-off-the-shelf (COTS) SOTA DNN accelerators via a structured three-step methodology: (1) enabling NPU execution, (2) optimizing performance, and (3) trading accuracy for efficiency gains. Step 1 employs GraphSplit for workload distribution and StaGr for static aggregation, while GrAd and NodePad handle dynamic graphs. Step 2 boosts performance using EffOp for control-heavy tasks and GraSp for sparsity exploitation. Graph Convolution optimizations PreG, SymG, and CacheG reduce redundancy and memory transfers. Step 3 balances quality versus efficiency, where QuantGr applies INT8 quantization, and GrAx1, GrAx2, and GrAx3 accelerate attention, broadcast-add, and SAGE-max aggregation. On Intel Core Ultra AI PCs, GraNNite achieves 2.6X to 7.6X speedups over default NPU mappings and up to 8.6X energy gains over CPUs and GPUs, delivering 10.8X and 6.7X higher performance than CPUs and GPUs, respectively, across GNN models.