SNN-MLIR: An MLIR Dialect for Compiling Neuromorphic SNNs from NIR to Bare-Metal C

• URL: http://arxiv.org/abs/2606.09213v1
• Date: Mon, 08 Jun 2026 08:47:48 GMT
• Title: SNN-MLIR: An MLIR Dialect for Compiling Neuromorphic SNNs from NIR to Bare-Metal C
• Abstract summary: Spiking neural networks (SNNs) are increasingly trained in a wide range of frameworks each with its own model format.<n>Neuromorphic Intermediate Representation (NIR) addresses this fragmentation by providing a common, framework-independent format for exchanging trained SNN models.<n>Snn-mlir is an outof-tree MLIR dialect for SNNs together with a NIR-MLIR-C compilation bridge.
• Score: 45.88028371034407
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spiking neural networks (SNNs) are increasingly trained in a wide range of frameworks (SnnTorch, Lava, Norse, and others) each with its own model format. The Neuromorphic Intermediate Representation (NIR) addresses this fragmentation by providing a common, framework-independent format for exchanging trained SNN models. NIR solves the exchange problem, but it stops there. It provides a description of a network, not a path to running one. Each backend is still left to implement deployment on its own, with no shared, transformable compiler representation in between. This paper presents snn-mlir, an outof-tree MLIR dialect for SNNs together with a NIR-MLIR-C compilation bridge. The dialect provides a small set of typepolymorphic operations that work identically on floating-point (f32/f64) and quantized data, so a single intermediate representation serves both simulation and hardware-oriented deployment. A Python front end reads any NIR file and emits dialect IR, automatically inserting rescaling operations to keep quantization scales consistent across layers. A reference lowering pass converts the dialect to standard linalg and arith operations, from which the toolchain produces self-contained, dependency free C11 code that compiles and runs on any C-capable CPU or embedded target. We evaluate numerical fidelity against reference outputs, portability across CPU targets, and the cost of quantization. The current scope is feedforward, fully-connected networks with a CPU backend. snn-mlir is released as open source under the Apache-2.0 license with LLVM-exception and it is already available on Github.

Related papers

• NNTile: a machine learning framework capable of training extremely large GPT language models on a single node [83.9328245724548]
  NNTile is based on a StarPU library, which implements task-based parallelism and schedules all provided tasks onto all available processing units.<n>It means that a particular operation, necessary to train a large neural network, can be performed on any of the CPU cores or GPU devices.
  arXiv  Detail & Related papers  (2025-04-17T16:22:32Z)
• NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks [2.6230959823681834]
  This work introduces NITRO-D, a new framework for training arbitrarily deep integer-only Convolutional Neural Networks (CNNs) NiTRO-D is the first framework in the literature enabling the training of integer-only CNNs without the need to introduce a quantization scheme.
  arXiv  Detail & Related papers  (2024-07-16T13:16:49Z)
• cito: An R package for training neural networks using torch [0.0]
  'cito' is a user-friendly R package for deep learning (DL) applications. It allows specifying DNNs in the familiar formula syntax used by many R packages. 'cito' includes many user-friendly functions for model plotting and analysis.
  arXiv  Detail & Related papers  (2023-03-16T18:54:20Z)
• Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharing [0.4129225533930965]
  Deep convolutional neural networks (DCNNs) have become the state-of-the-art (SOTA) approach for many computer vision tasks. Here, we suggest a simple way to reduce the number of trainable parameters and thus the memory footprint: sharing kernels between multiple convolutional layers.
  arXiv  Detail & Related papers  (2022-10-23T18:14:30Z)
• Signal Processing for Implicit Neural Representations [80.38097216996164]
  Implicit Neural Representations (INRs) encode continuous multi-media data via multi-layer perceptrons. Existing works manipulate such continuous representations via processing on their discretized instance. We propose an implicit neural signal processing network, dubbed INSP-Net, via differential operators on INR.
  arXiv  Detail & Related papers  (2022-10-17T06:29:07Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• Neural Architecture Search as Program Transformation Exploration [7.090165638014331]
  Compilers apply program transformations in order to exploit hardware parallelism and memory hierarchy. neural architecture search (NAS) techniques mutate networks by operations such as the grouping or bottlenecking of convolutions. In this work, we express such neural architecture operations as program transformations whose legality depends on a notion of representational capacity.
  arXiv  Detail & Related papers  (2021-02-12T16:11:05Z)
• Compiling ONNX Neural Network Models Using MLIR [51.903932262028235]
  We present a preliminary report on our onnx-mlir compiler, which generates code for the inference of deep neural network models. Onnx-mlir relies on the Multi-Level Intermediate Representation (MLIR) infrastructure recently integrated in the LLVM project.
  arXiv  Detail & Related papers  (2020-08-19T05:28:08Z)
• Efficient Integer-Arithmetic-Only Convolutional Neural Networks [87.01739569518513]
  We replace conventional ReLU with Bounded ReLU and find that the decline is due to activation quantization. Our integer networks achieve equivalent performance as the corresponding FPN networks, but have only 1/4 memory cost and run 2x faster on modern GPU.
  arXiv  Detail & Related papers  (2020-06-21T08:23:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.