Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference

• URL: http://arxiv.org/abs/2509.17970v3
• Date: Sun, 28 Sep 2025 11:28:58 GMT
• Title: Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference
• Abstract summary: High latency and energy overhead are inevitable on resource-constrained devices.<n>To address this challenge, most researchers focus on the dynamic voltage and frequency scaling (DVFS) technique.<n>In this paper, we first investigate the impact of joint memory frequency and computing frequency scaling on the inference time and energy consumption.
• Score: 9.303797341103534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) have been widely applied in diverse applications, but the problems of high latency and energy overhead are inevitable on resource-constrained devices. To address this challenge, most researchers focus on the dynamic voltage and frequency scaling (DVFS) technique to balance the latency and energy consumption by changing the computing frequency of processors. However, the adjustment of memory frequency is usually ignored and not fully utilized to achieve efficient DNN inference, which also plays a significant role in the inference time and energy consumption. In this paper, we first investigate the impact of joint memory frequency and computing frequency scaling on the inference time and energy consumption with a model-based and data-driven method. Then by combining with the fitting parameters of different DNN models, we give a preliminary analysis for the proposed model to see the effects of adjusting memory frequency and computing frequency simultaneously. Finally, simulation results in local inference and cooperative inference cases further validate the effectiveness of jointly scaling the memory frequency and computing frequency to reduce the energy consumption of devices.

Related papers

• Joint Optimization of Memory and Computing Frequency for Energy-Efficient DNN Inference [9.303797341103534]
  Deep neural network (DNN) inference on mobile devices often incurs high latency and energy consumption due to limited computing and memory resources.<n>We consider the impact of memory frequency and computing frequency on DNN inference time, and jointly optimize these two together with communication resources for energy-efficient inference.<n>Our proposed algorithm significantly reduces the energy consumption of devices by up to 10.4% compared to other methods.
  arXiv  Detail & Related papers  (2026-08-14T01:25:00Z)
• Adaptive-Frequency Resonate-and-Fire Neurons for Spectral Estimation of Streaming Radar Signals [5.2855426312680995]
  We propose a neuromorphic-inspired signal processing method based on adaptive resonate-and-fire neurons.<n>The proposed model operates in a sample-by-sample fashion, resulting in memory requirements that scale with the number of tracked targets.<n>Results on simulated and experimental data demonstrate that the method can successfully track multiple targets.
  arXiv  Detail & Related papers  (2026-06-11T16:06:48Z)
• Prefill vs. Decode Bottlenecks: SRAM-Frequency Tradeoffs and the Memory-Bandwidth Ceiling [5.606289163036201]
  Energy consumption dictates the cost and environmental impact of deploying Large Language Models.<n>This paper investigates the impact of on-chip size and operating frequency on the energy efficiency and performance of LLM inference.
  arXiv  Detail & Related papers  (2025-12-26T15:42:29Z)
• Vacuum Spiker: A Spiking Neural Network-Based Model for Efficient Anomaly Detection in Time Series [0.4129847064263055]
  Anomaly detection is a key task across domains such as industry, healthcare, and cybersecurity.<n>This paper introduces the textitVacuum Spiker algorithm, a novel Spiking Neural Network-based method for anomaly detection in time series.<n>It incorporates a new detection criterion that relies on global changes in neural activity rather than reconstruction or prediction error.
  arXiv  Detail & Related papers  (2025-10-08T11:43:54Z)
• SPJFNet: Self-Mining Prior-Guided Joint Frequency Enhancement for Ultra-Efficient Dark Image Restoration [3.2735437407166414]
  Current dark image restoration methods suffer from severe efficiency bottlenecks.<n>We propose an Efficient Self-Mining Prior-Guided Joint Frequency Enhancement Network (SPJFNet)
  arXiv  Detail & Related papers  (2025-08-06T03:06:29Z)
• Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons [69.73249913506042]
  This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons to process time-domain signals directly.<n>By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity.<n> Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs.
  arXiv  Detail & Related papers  (2025-06-24T21:14:59Z)
• Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks under Latency Constraint [6.6947001137138455]
  We propose an approach involving Proportional Layer Skipping (PLS) and adjusts Frequency Scaling (FS)<n>PLS reduces computational complexity by selectively bypassing network layers, whereas frequency scaling the frequency of the processor to optimize energy use under latency constraints.<n>Experiments on ResNet-152 with the CIFAR-10 dataset demonstrated significant reductions in computational demands and energy consumption with minimal accuracy loss.
  arXiv  Detail & Related papers  (2025-03-31T12:40:11Z)
• Neuromorphic Split Computing with Wake-Up Radios: Architecture and Design via Digital Twinning [97.99077847606624]
  This work proposes a novel architecture that integrates a wake-up radio mechanism within a split computing system consisting of remote, wirelessly connected, NPUs. A key challenge in the design of a wake-up radio-based neuromorphic split computing system is the selection of thresholds for sensing, wake-up signal detection, and decision making.
  arXiv  Detail & Related papers  (2024-04-02T10:19:04Z)
• Low-Frequency Load Identification using CNN-BiLSTM Attention Mechanism [0.0]
  Non-intrusive Load Monitoring (NILM) is an established technique for effective and cost-efficient electricity consumption management. This paper presents a hybrid learning approach, consisting of a convolutional neural network (CNN) and a bidirectional long short-term memory (BILSTM) CNN-BILSTM model is adept at extracting both temporal (time-related) and spatial (location-related) features, allowing it to precisely identify energy consumption patterns at the appliance level.
  arXiv  Detail & Related papers  (2023-11-14T21:02:27Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels [52.60092598312894]
  We propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. Our proposed solution results in minimal energy consumption and $CO$ emission compared to the considered baselines.
  arXiv  Detail & Related papers  (2021-06-02T07:36:27Z)
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
  This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain. In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden. Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
  arXiv  Detail & Related papers  (2021-03-15T12:54:26Z)
• Compute and memory efficient universal sound source separation [23.152611264259225]
  We provide a family of efficient neural network architectures for general purpose audio source separation. The backbone structure of this convolutional network is the SUccessive DOwnsampling and Resampling of Multi-Resolution Features (SuDoRM-RF) Our experiments show that SuDoRM-RF models perform comparably and even surpass several state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2021-03-03T19:16:53Z)
• Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference [56.24109486973292]
  We study the interplay between pruning and quantization during the training of neural networks for ultra low latency applications. We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task.
  arXiv  Detail & Related papers  (2021-02-22T19:00:05Z)

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.