CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution
Not on the map. Why?
Abstract (arXiv)
Mobile devices run deep learning models for various purposes, such as image classification and speech recognition. Due to the resource constraints of mobile devices, researchers have focused on either making a lightweight deep neural network (DNN) model using model pruning or generating an efficient code using compiler optimization. Surprisingly, we found that the straightforward integration between model compression and compiler auto-tuning often does not produce the most efficient model for a target device. We propose CPrune, a compiler-informed model pruning for efficient target-aware DNN execution to support an application with a required target accuracy. CPrune makes a lightweight DNN model through informed pruning based on the structural information of subgraphs built during the compiler tuning process. Our experimental results show that CPrune increases the DNN execution speed up to 2.73x compared to the state-of-the-art TVM auto-tune while satisfying the accuracy requirement.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 4 Jul 2022.
Builds on
30 of 50 references.
References · 30
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2018DARTS: Differentiable Architecture Searchcited by 1,798
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
- 2016Pruning Filters for Efficient ConvNetscited by 1,143
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
- 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
- 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
- 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 378
- 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
- 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
18 more
- 2016Dynamic Network Surgery for Efficient DNNscited by 233
- 2020Ansor: Generating High-Performance Tensor Programs for Deep Learningcited by 201
- 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 179
- 2018NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applicationscited by 147
- 2020Sparse GPU Kernels for Deep Learningcited by 141
- 2018Learning to Optimize Tensor Programscited by 140
- 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 134
- 2018A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multiplierscited by 120
- 2018Glow: Graph Lowering Compiler Techniques for Neural Networkscited by 75
- 2021Convolutional Neural Network Pruning with Structural Redundancy Reductioncited by 73
- 2018NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Visioncited by 68
- 2019PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devicescited by 50
- 2020Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networkscited by 28
- 2020Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Surveycited by 26
- 2018Relay: A New IR for Machine Learning Frameworkscited by 24
- 2020NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Accelerationcited by 16
- 2021NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimizationcited by 13
- 2020An Introduction to Neural Architecture Search for Convolutional Networkscited by 10
Built on by
Citing papers per year: 2023: 2.
2 papers.