NeuroComp: A Cross-Platform Compiler for Efficient SNN Deployment on Neuromorphic Hardware
Open Access
- 5 September 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 23 (4) , 1-26
Abstract
Spiking Neural Networks (SNNs) offer substantial energy efficiency advantages, yet deploying them across diverse neuromorphic hardware remains challenging. Existing toolchains exhibit a critical tradeoff: platform-specific frameworks lack portability, while low-level programming interfaces demand extensive hardware expertise and produce non-portable code. Furthermore, conventional deep learning compilers fail to handle the unique temporal dynamics of SNNs and the idiosyncratic constraints of neuromorphic architectures. To bridge this gap, we present NeuroComp , a cross-platform compiler that automatically generates functionally correct and high-performance code for heterogeneous neuromorphic backends. Our core insight is that the diverse execution behaviors of neuromorphic hardware can be universally modeled as parallelizable scalar computations expressible via nested loops. Building on this, NeuroComp introduces a unified multi-level loop abstraction to systematically align SNN computational semantics with hardware capacities. To efficiently navigate the vast implementation space, we propose a decoupled two-stage scheduling strategy. The first stage performs batch partitioning to guarantee functional correctness and strict architectural compliance, while the second stage optimizes inter-batch execution orders for maximum data reuse, guided by lightweight, hardware-specific cost models and heuristic pruning. We evaluate NeuroComp on three representative architectural paradigms: an instruction-extended CPU, a dedicated accelerator, and a many-core hardware. Experimental results demonstrate that NeuroComp consistently achieves competitive performance compared to meticulously hand-optimized implementations and significantly outperforms existing generic automated compilers, effectively minimizing development effort while unlocking cross-platform portability.Keywords
This publication has 30 references indexed in Scilit:
- LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks2024
- Spiking neural networks for autonomous driving: A reviewEngineering Applications of Artificial Intelligence, 2024
- RV-SCNN: A RISC-V Processor With Customized Instruction Set for SNN and CNN Inference Acceleration on Edge PlatformsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024
- Hierarchical Mapping of Large-Scale Spiking Convolutional Neural Networks Onto Resource-Constrained Neuromorphic ProcessorIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023
- Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Back to Homogeneous Computing: A Tightly-Coupled Neuromorphic Processor With Neuromorphic ISAIEEE Transactions on Parallel and Distributed Systems, 2023
- The operating system of the neuromorphic BrainScaleS-1 systemNeurocomputing, 2022
- Darwin-S: A Reference Software Architecture for Brain-Inspired ComputersComputer, 2022
- LSMCore: A 69k-Synapse/mm2 Single-Core Digital Neuromorphic Processor for Liquid State MachineIEEE Transactions on Circuits and Systems I: Regular Papers, 2022
- Cognitive computing programming paradigm: A Corelet Language for composing networks of neurosynaptic cores2013