mlsanityData to 7 Oct 2026

CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework

arXiv 2206.10620 ↗First posted 21 Jun 2022cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

There is a growing demand for shifting the delivery of AI capability from data centers on the cloud to edge or end devices, exemplified by the fast emerging real-time AI-based apps running on smartphones, AR/VR devices, autonomous vehicles, and various IoT devices. The shift has however been seriously hampered by the large growing gap between DNN computing demands and the computing power on edge or end devices. This article presents the design of XGen, an optimizing framework for DNN designed to bridge the gap. XGen takes cross-cutting co-design as its first-order consideration. Its full-stack AI-oriented optimizations consist of a number of innovative optimizations at every layer of the DNN software stack, all designed in a cooperative manner. The unique technology makes XGen able to optimize various DNNs, including those with an extreme depth (e.g., BERT, GPT, other transformers), and generate code that runs several times faster than those from existing DNN frameworks, while delivering the same level of accuracy.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 21 Jun 2022.

Builds on

20 of 37 references.

References · 20

  1. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  2. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  3. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  4. 2014cuDNN: Efficient Primitives for Deep Learningcited by 240
  5. 2020The Computational Limits of Deep Learningcited by 188
  6. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 161
  7. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 116
  8. 2015Fast Algorithms for Convolutional Neural Networkscited by 102
  9. 2015Fast ConvNets Using Group-wise Brain Damagecited by 81
  10. 2020PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruningcited by 75
  11. 2021DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusioncited by 56
  12. 2019PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devicescited by 48
8 more
  1. 2020Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruningcited by 39
  2. 2017Exploring the Regularity of Sparse Structure in Convolutional Neural Networkscited by 37
  3. 2020YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Designcited by 24
  4. 2020RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognitioncited by 19
  5. 2020NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Accelerationcited by 16
  6. 2021GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsitycited by 10
  7. 2020RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devicescited by 4
  8. 2021Enabling Level-4 Autonomous Driving on a Single 1k Off-the-Shelf Cardcited by 1

Built on by

Not cited yet.