HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks

• URL: http://arxiv.org/abs/2201.08022v5
• Date: Wed, 25 Oct 2023 09:18:47 GMT
• Title: HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks
• Abstract summary: Our multiplier achieves up to 50.24% higher accuracy than the best reproduced approximate multiplier in DNNs. Compared with an exact multiplier, our multiplier reduces the area, power consumption, and delay by 44.94%, 47.63%, and 16.78%, respectively.
• Score: 5.997295917769142
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose an optimization method for the automatic design of approximate multipliers, which minimizes the average error according to the operand distributions. Our multiplier achieves up to 50.24% higher accuracy than the best reproduced approximate multiplier in DNNs, with 15.76% smaller area, 25.05% less power consumption, and 3.50% shorter delay. Compared with an exact multiplier, our multiplier reduces the area, power consumption, and delay by 44.94%, 47.63%, and 16.78%, respectively, with negligible accuracy losses. The tested DNN accelerator modules with our multiplier obtain up to 18.70% smaller area and 9.99% less power consumption than the original modules.

Related papers

• E-ReCON: An Energy- and Resource-Efficient Precision-Configurable Sparse nvCIM Macro for Conventional and Spiking Neural Edge Inference [0.0]
  E-ReCON is a 16 Kb digital compute-in-memory (DCIM) macro based on a compact 3T1R ReRAM bitcell for edge-AI inference.<n>A novel interleaved 10T/28T adder tree is introduced, reducing transistor count and power consumption by 37% and 28%, respectively.<n>The proposed macro achieves a minimum latency of 0.48 ns, throughput of 2.31-3.1 TOPS, and energy efficiency of up to 419 TOPS/W.
  arXiv  Detail & Related papers  (2026-05-20T05:18:27Z)
• Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNs [0.0]
  We propose a soft sparsity'' paradigm using a hardware efficient Most Significant Bit proxy to skip negligible non-zero multiplications.<n>This method reduces ReLU MACs by 88.42% and Tanh MACs by 74.87% with zero accuracy loss--outperforming zero-skipping by 5x.
  arXiv  Detail & Related papers  (2026-03-10T17:59:10Z)
• Time-Series at the Edge: Tiny Separable CNNs for Wearable Gait Detection and Optimal Sensor Placement [3.7765281299298015]
  We study on-device time-series analysis for gait detection in Parkinson's disease (PD) from short windows of triaxial acceleration, targeting resource-latency wearables and edge nodes.<n>We compare magnitude thresholding to three 1D CNNs for time-series analysis: a literature baseline (separable convolutions) and two ultra-light models - one purely separable and one with residual connections.
  arXiv  Detail & Related papers  (2025-11-29T08:52:41Z)
• A Proximal Operator for Inducing 2:4-Sparsity [68.98036844970986]
  We derive a regularizer that exploits the local correlation of features to find better sparsity masks in trained models. We illustrate our method on toy problems and apply it to pruning entire large language models up to 70B parameters.
  arXiv  Detail & Related papers  (2025-01-29T22:05:17Z)
• Leveraging Highly Approximated Multipliers in DNN Inference [13.973803328588687]
  Our approach does not require retraining and significantly decreases the induced error due to approximate multiplications. Compared to the corresponding approximate designs without using our technique, our approach improves the accuracy by 1.9x on average.
  arXiv  Detail & Related papers  (2024-12-21T20:09:29Z)
• xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems [11.488297094967377]
  Ternary neural networks (TNNs) offer a superior accuracy-energy trade-off compared to binary neural networks. We present xTern, a lightweight extension of the RISC-V instruction set architecture targeted at accelerating TNN inference on general-purpose cores. Our results show that xTern enables RISC-V-based ultra-low-power edge AI platforms to benefit from the efficiency potential of TNNs.
  arXiv  Detail & Related papers  (2024-05-29T13:16:46Z)
• Instant Complexity Reduction in CNNs using Locality-Sensitive Hashing [50.79602839359522]
  We propose HASTE (Hashing for Tractable Efficiency), a parameter-free and data-free module that acts as a plug-and-play replacement for any regular convolution module. We are able to drastically compress latent feature maps without sacrificing much accuracy by using locality-sensitive hashing (LSH) In particular, we are able to instantly drop 46.72% of FLOPs while only losing 1.25% accuracy by just swapping the convolution modules in a ResNet34 on CIFAR-10 for our HASTE module.
  arXiv  Detail & Related papers  (2023-09-29T13:09:40Z)
• Ultra-low Power Deep Learning-based Monocular Relative Localization Onboard Nano-quadrotors [64.68349896377629]
  This work presents a novel autonomous end-to-end system that addresses the monocular relative localization, through deep neural networks (DNNs), of two peer nano-drones. To cope with the ultra-constrained nano-drone platform, we propose a vertically-integrated framework, including dataset augmentation, quantization, and system optimizations. Experimental results show that our DNN can precisely localize a 10cm-size target nano-drone by employing only low-resolution monochrome images, up to 2m distance.
  arXiv  Detail & Related papers  (2023-03-03T14:14:08Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Low Error-Rate Approximate Multiplier Design for DNNs with Hardware-Driven Co-Optimization [5.547686929207811]
  Two approximate 3*3 multipliers are proposed and the synthesis results of the ASAP-7nm process library justify that they can reduce the area by 31.38% and 36.17%. They can be aggregated with a 2*2 multiplier to produce an 8*8 multiplier with low error rate based on the distribution of DNN weights. We propose a hardware-driven software co-optimization method to improve the DNN accuracy by retraining.
  arXiv  Detail & Related papers  (2022-10-08T05:00:26Z)
• BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing [48.11023234245863]
  We propose a new framework called BottleFit, which includes a novel training strategy to achieve high accuracy even with strong compression rates. BottleFit achieves 77.1% data compression with up to 0.6% accuracy loss on ImageNet dataset. We show that BottleFit decreases power consumption and latency respectively by up to 49% and 89% with respect to (w.r.t.) local computing and by 37% and 55% w.r.t. edge offloading.
  arXiv  Detail & Related papers  (2022-01-07T22:08:07Z)
• Positive/Negative Approximate Multipliers for DNN Accelerators [3.1921317895626493]
  We present a filter-oriented approximation method to map the weights to the appropriate modes of the approximate multiplier. Our approach achieves 18.33% energy gains on average across 7 NNs on 4 different datasets for a maximum accuracy drop of only 1%.
  arXiv  Detail & Related papers  (2021-07-20T09:36:24Z)
• Control Variate Approximation for DNN Accelerators [3.1921317895626493]
  We introduce a control variate approximation technique for low error approximate Deep Neural Network (DNN) accelerators. Our approach significantly decreases the induced error due to approximate multiplications in inference, without requiring time-exhaustive retraining.
  arXiv  Detail & Related papers  (2021-02-18T22:11:58Z)
• Non-Parametric Adaptive Network Pruning [125.4414216272874]
  We introduce non-parametric modeling to simplify the algorithm design. Inspired by the face recognition community, we use a message passing algorithm to obtain an adaptive number of exemplars. EPruner breaks the dependency on the training data in determining the "important" filters.
  arXiv  Detail & Related papers  (2021-01-20T06:18:38Z)
• Bit Error Robustness for Energy-Efficient DNN Accelerators [93.58572811484022]
  We show that a combination of robust fixed-point quantization, weight clipping, and random bit error training (RandBET) improves robustness against random bit errors. This leads to high energy savings from both low-voltage operation as well as low-precision quantization.
  arXiv  Detail & Related papers  (2020-06-24T18:23:10Z)
• An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computing [13.266626571886354]
  This paper presents an accurate and robust embedded motor-imagery brain-computer interface (MI-BCI) The proposed novel model, based on EEGNet, matches the requirements of memory footprint and computational resources of low-power microcontroller units (MCUs) The scaled models are deployed on a commercial Cortex-M4F MCU taking 101ms and consuming 4.28mJ per inference for operating the smallest model, and on a Cortex-M7 with 44ms and 18.1mJ per inference for the medium-sized model.
  arXiv  Detail & Related papers  (2020-03-31T19:52:05Z)

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.