Corpus ID: 119120115

Relay: A High-Level IR for Deep Learning

@article{Roesch2019RelayAH,
  title={Relay: A High-Level IR for Deep Learning},
  author={Jared Roesch and Steven Lyubomirsky and Marisa Kirisame and J. Pollock and Logan Weber and Ziheng Jiang and T. Chen and T. Moreau and Zachary Tatlock},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.08368}
}
  • Jared Roesch, Steven Lyubomirsky, +6 authors Zachary Tatlock
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • Frameworks for writing, compiling, and optimizing deep learning (DL) models have recently enabled progress in areas like computer vision and natural language processing. Extending these frameworks to accommodate the rapidly diversifying landscape of DL models and hardware platforms presents challenging tradeoffs between expressiveness, composability, and portability. We present Relay, a new intermediate representation (IR) and compiler framework for DL models. The functional, statically-typed… CONTINUE READING
    5 Citations
    Enhancing the interoperability between deep learning frameworks by model conversion
    • 1
    • PDF
    Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference
    • 3
    • PDF
    Ansor : Generating High-Performance Tensor Programs for Deep Learning
    • 8
    • PDF
    Dynamic Tensor Rematerialization
    • 1
    • PDF

    References

    SHOWING 1-10 OF 39 REFERENCES
    ONNC: A Compilation Framework Connecting ONNX to Proprietary Deep Learning Accelerators
    • Wei-Fen Lin, Der-Yu Tsai, +4 authors Luis Hsu
    • Computer Science
    • 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)
    • 2019
    • 10
    • Highly Influential
    • PDF
    Glow: Graph Lowering Compiler Techniques for Neural Networks
    • 101
    • Highly Influential
    • PDF
    Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
    • 189
    • PDF
    Caffe: Convolutional Architecture for Fast Feature Embedding
    • 12,573
    • PDF
    AutoGraph: Imperative-style Coding with Graph-based Performance
    • 20
    • PDF
    Diesel: DSL for linear algebra and neural net computations on GPUs
    • 28
    Deep Learning with Dynamic Computation Graphs
    • 98
    • Highly Influential
    • PDF
    Quantizing deep convolutional networks for efficient inference: A whitepaper
    • 247
    • PDF
    TensorFlow: A system for large-scale machine learning
    • 8,885
    • PDF