Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity

• URL: http://arxiv.org/abs/2502.01330v1
• Date: Mon, 03 Feb 2025 13:09:21 GMT
• Title: Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
• Authors: Alessandro Pierro, Steven Abreu, Jonathan Timcheck, Philipp Stratmann, Andreas Wild, Sumit Bam Shrestha,
• Abstract summary: Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. Unstructured sparsity offers a compelling solution, enabling substantial reductions in compute and memory requirements when accelerated by compatible hardware platforms. We find that highly sparse linear RNNs consistently achieve better efficiency-performance trade-offs than dense baselines.
• Score: 39.483346492111515
• License:
• Abstract: Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. These architectures hold promise for streaming applications at the edge, but deployment in resource-constrained environments requires hardware-aware optimizations to minimize latency and energy consumption. Unstructured sparsity offers a compelling solution, enabling substantial reductions in compute and memory requirements--when accelerated by compatible hardware platforms. In this paper, we conduct a scaling study to investigate the Pareto front of performance and efficiency across inference compute budgets. We find that highly sparse linear RNNs consistently achieve better efficiency-performance trade-offs than dense baselines, with 2x less compute and 36% less memory at iso-accuracy. Our models achieve state-of-the-art results on a real-time streaming task for audio denoising. By quantizing our sparse models to fixed-point arithmetic and deploying them on the Intel Loihi 2 neuromorphic chip for real-time processing, we translate model compression into tangible gains of 42x lower latency and 149x lower energy consumption compared to a dense model on an edge GPU. Our findings showcase the transformative potential of unstructured sparsity, paving the way for highly efficient recurrent neural networks in real-world, resource-constrained environments.

Related papers

• USEFUSE: Utile Stride for Enhanced Performance in Fused Layer Architecture of Deep Neural Networks [0.6435156676256051]
  This study presents the Sum-of-Products (SOP) units for convolution, which utilize low-latency left-to-right bit-serial arithmetic. An effective mechanism detects and skips inefficient convolutions after ReLU layers, minimizing power consumption. Two designs cater to varied demands: one focuses on minimal response time for mission-critical applications, and another focuses on resource-constrained devices with comparable latency.
  arXiv  Detail & Related papers  (2024-12-18T11:04:58Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity [0.0]
  Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference latency. We propose a solution to induce semi-structured activation sparsity exploitable through minor runtime modifications. Our approach yields a speed improvement of $1.25 times$ with a minimal accuracy drop of $1.1%$ for the ResNet18 model on the ImageNet dataset.
  arXiv  Detail & Related papers  (2023-09-12T22:28:53Z)
• Latency-aware Unified Dynamic Networks for Efficient Image Recognition [72.8951331472913]
  LAUDNet is a framework to bridge the theoretical and practical efficiency gap in dynamic networks. It integrates three primary dynamic paradigms-spatially adaptive computation, dynamic layer skipping, and dynamic channel skipping. It can notably reduce the latency of models like ResNet by over 50% on platforms such as V100,3090, and TX2 GPUs.
  arXiv  Detail & Related papers  (2023-08-30T10:57:41Z)
• Latency-aware Spatial-wise Dynamic Networks [33.88843632160247]
  We propose a latency-aware spatial-wise dynamic network (LASNet) for deep networks. LASNet performs coarse-grained spatially adaptive inference under the guidance of a novel latency prediction model. Experiments on image classification, object detection and instance segmentation demonstrate that the proposed framework significantly improves the practical inference efficiency of deep networks.
  arXiv  Detail & Related papers  (2022-10-12T14:09:27Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Architecture Aware Latency Constrained Sparse Neural Networks [35.50683537052815]
  In this paper, we design an architecture aware latency constrained sparse framework to prune and accelerate CNN models. We also propose a novel sparse convolution algorithm for efficient computation. Our system-algorithm co-design framework can achieve much better frontier among network accuracy and latency on resource-constrained mobile devices.
  arXiv  Detail & Related papers  (2021-09-01T03:41:31Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• From DNNs to GANs: Review of efficient hardware architectures for deep learning [0.0]
  Neural network and deep learning has been started to impact the present research paradigm. DSP processors are incapable of performing neural network, activation function, convolutional neural network and generative adversarial network operations. Different algorithms have been adapted to design a DSP processor compatible for fast performance in neural network, activation function, convolutional neural network and generative adversarial network.
  arXiv  Detail & Related papers  (2021-06-06T13:23:06Z)

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.