PipeGNN: A Bandwidth-Efficient GNN Accelerator with Node-Level Pipelined Push Execution
Open Access
- 13 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 23 (4) , 1-24
Abstract
Graph Neural Networks (GNNs) have become a fundamental tool for learning over graph-structured data. Under the message-passing framework, mainstream GNN models alternate between feature transformation and neighborhood aggregation. Fusing these two phases into a node-level pipelined push dataflow, in which each node’s transformed feature streams directly into aggregation, establishes a single-pass I/O target that reads each input tensor exactly once per layer. No existing hardware sustains this dataflow at full concurrency. Prior fusion accelerators fall short of this target in three ways: designs that gather the raw input features for aggregation or write transformed features off-chip incur redundant traffic, designs that stream transformed features on-chip still keep the two phases as separate matrix kernels without a unified execution granularity, and the designs that aggregate at message granularity serialize per-destination aggregation or allocate state that does not scale to large graphs. We propose PipeGNN, a bandwidth-efficient GNN accelerator whose streaming microarchitecture sustains this dataflow as a fully concurrent pipeline within a fixed on-chip buffer budget. PipeGNN decouples execution from topological boundaries by aligning execution granularity with both memory burst size and aggregation compute throughput, and resolves four coupled microarchitectural barriers through coordinated mechanisms: compute-aligned edge batching, contention-aware message reduction, adaptive cross-batch scheduling, and tiered state residency. Evaluated across diverse GNN workloads, PipeGNN achieves geometric mean speedups of 10.1× over AWB-GCN and 12.2× over FlowGNN, and 2.4× to 46.9× over a GPU baseline across graph scales, reduces off-chip traffic by 2.69× over AWB-GCN and 5.93× over FlowGNN, and improves energy efficiency by 56.81× over AWB-GCN and 1.53× over FlowGNN, with a 154× traffic reduction and a 116.81× energy reduction against HyGCN.Keywords
Funding Information
- National Natural Science Foundation of China (62032001 NSFC (Key Program) and Grant No. 62472436)
- Foundation of Key Laboratory KL (WDZC20245250110 KL)
This publication has 23 references indexed in Scilit:
- A comprehensive survey on graph neural network acceleratorsFrontiers of Computer Science, 2024
- NeuraChip: Accelerating GNN Computations with a Hash-based Decoupled Spatial Accelerator2024
- BeaconGNN: Large-Scale GNN Acceleration with Out-of-Order Streaming In-Storage Computing2024
- MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization2024
- FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inference2023
- GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks2023
- GCNAX: A Flexible and Energy-efficient Accelerator for Graph Convolutional Neural Networks2021
- DRAMsim3: A Cycle-Accurate, Thermal-Capable DRAM SimulatorIEEE Computer Architecture Letters, 2020
- HyGCN: A GCN Accelerator with Hybrid Architecture2020
- DeepGCNs: Can GCNs Go As Deep As CNNs?2019