mlsanityData to 7 Oct 2026

Glow: Graph Lowering Compiler Techniques for Neural Networks

arXiv 1805.00907 ↗First posted 2 May 2018cs.PLcited by 73

Not on the map. Why?

Abstract (arXiv)

This paper presents the design of Glow, a machine learning compiler for heterogeneous hardware. It is a pragmatic approach to compilation that enables the generation of highly optimized code for multiple targets. Glow lowers the traditional neural network dataflow graph into a two-phase strongly-typed intermediate representation. The high-level intermediate representation allows the optimizer to perform domain-specific optimizations. The lower-level instruction-based address-only intermediate representation allows the compiler to perform memory-related optimizations, such as instruction scheduling, static memory allocation and copy elimination. At the lowest level, the optimizer performs machine-specific code generation to take advantage of specialized hardware features. Glow features a lowering phase which enables the compiler to support a high number of input operators as well as a large number of hardware targets by eliminating the need to implement all operators on all targets. The lowering phase is designed to reduce the input space and allow new hardware backends to focus on a small number of linear algebra primitives.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 17; 2022: 19; 2023: 8; 2024: 8; 2025: 7; 2026: 13.

73 papers.

Sort:

By area:

  1. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  2. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  3. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  4. 2021GSPMD: General and Scalable Parallelization for ML Computation Graphscited by 109
  5. 2023Full Stack Optimization of Transformer Inference: a Surveycited by 79
  6. 2025Astra: A Multi-Agent System for GPU Kernel Performance Optimizationcited by 46
  7. 2024ThunderKittens: Simple, Fast, and Adorable AI Kernelscited by 34
  8. 2024Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlappingcited by 22
  9. 2022On-device Training: A First Overview on Existing Systemscited by 18
  10. 2021LazyTensor: combining eager execution with domain-specific compilerscited by 11
  11. 2022Learning to Reverse DNNs from AI Programs Automaticallycited by 11
  12. 2021UNIT: Unifying Tensorized Instruction Compilationcited by 10
38 more
  1. 2021MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworkscited by 9
  2. 2021Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterioncited by 9
  3. 2022Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutationcited by 9
  4. 2021Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Modelscited by 7
  5. 2022Federated Remote Physiological Measurement with Imperfect Datacited by 7
  6. 2022Decompiling x86 Deep Neural Network Executablescited by 7
  7. 2021Swift for TensorFlow: A portable, flexible platform for deep learningcited by 6
  8. 2022Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deploymentcited by 6
  9. 2022Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systemscited by 6
  10. 2022Demand Layering for Real-Time DNN Inference with Minimized Memory Usagecited by 6
  11. 2021Bring Your Own Codegen to Deep Learning Compilercited by 5
  12. 2025From Tiny Machine Learning to Tiny Deep Learning: A Surveycited by 5
  13. 2021NullaNet Tiny: Ultra-low-latency DNN Inference Through Fixed-function Combinational Logiccited by 4
  14. 2022MSRL: Distributed Reinforcement Learning with Dataflow Fragmentscited by 4
  15. 2024Deep Learning Library Testing: Definition, Methods and Challengescited by 4
  16. 2021A Data-Centric Optimization Framework for Machine Learningcited by 3
  17. 2022Benchmarking the Linear Algebra Awareness of TensorFlow and PyTorchcited by 3
  18. 2022Memory Planning for Deep Neural Networkscited by 3
  19. 2022Memory Safe Computations with XLA Compilercited by 3
  20. 2024CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Acceleratorscited by 3
  21. 2024MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programmingcited by 3
  22. 2026A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimizationcited by 3
  23. 2021Automated Backend-Aware Post-Training Quantizationcited by 2
  24. 2021Collage: Seamless Integration of Deep Learning Backends with Automatic Placementcited by 2
  25. 2022CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Executioncited by 2
  26. 2023An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUscited by 2
  27. 2023Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executablescited by 2
  28. 2026Hexagon-MLIR: An AI Compilation Stack For Qualcomm's Neural Processing Units (NPUs)cited by 2
  29. 2021Compiler Toolchains for Deep Learning Workloads on Embedded Platformscited by 1
  30. 2021Pre-Quantized Deep Learning Models Codified in ONNX to Enable Hardware/Software Co-Designcited by 1
  31. 2022ByteComp: Revisiting Gradient Compression in Distributed Trainingcited by 1
  32. 2023OpenHLS: High-Level Synthesis for Low-Latency Deep Neural Networks for Experimental Sciencecited by 1
  33. 2023Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generationcited by 1
  34. 2023LoopTune: Optimizing Tensor Computations with Reinforcement Learningcited by 1
  35. 2024Proteus: Preserving Model Confidentiality during Graph Optimizationscited by 1
  36. 2024OpTC -- A Toolchain for Deployment of Neural Networks on AURIX TC3xx Microcontrollerscited by 1
  37. 2024Scorch: A Library for Sparse Deep Learningcited by 1
  38. 2025DiTOX: Fault Detection and Localization in the ONNX Optimizercited by 1

50 most cited of 73 All 73 (JSON)