mlsanityData to 7 Oct 2026

Cortex: A Compiler for Recursive Deep Learning Models

arXiv 2011.01383 ↗First posted 2 Nov 2020cs.LG cs.DCcited by 16

Not on the map. Why?

Abstract (arXiv)

Optimizing deep learning models is generally performed in two steps: (i) high-level graph optimizations such as kernel fusion and (ii) low level kernel optimizations such as those found in vendor libraries. This approach often leaves significant performance on the table, especially for the case of recursive deep learning models. In this paper, we present Cortex, a compiler-based approach to generate highly-efficient code for recursive models for low latency inference. Our compiler approach and low reliance on vendor libraries enables us to perform end-to-end optimizations, leading to up to 14X lower inference latencies over past work, across different backends.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 4; 2023: 4; 2024: 1; 2025: 2; 2026: 1.

16 papers.

Sort:

  1. 2021DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusioncited by 56
  2. 2022TensorIR: An Abstraction for Automatic Tensorized Program Optimizationcited by 38
  3. 2022Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programscited by 28
  4. 2021The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Paddingcited by 17
  5. 2022Query Processing on Tensor Computation Runtimescited by 12
  6. 2023Relax: Composable Abstractions for End-to-End Dynamic Machine Learningcited by 12
  7. 2023DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimizationcited by 9
  8. 2025Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilerscited by 6
  9. 2021A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunitiescited by 5
  10. 2024SoD2: Statically Optimizing Dynamic Deep Neural Networkcited by 4
  11. 2025Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computationcited by 3
  12. 2021Collage: Seamless Integration of Deep Learning Backends with Automatic Placementcited by 2
4 more
  1. 2023ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machinescited by 1
  2. 2023ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Timecited by 1
  3. 2022ALT: Boosting Deep Learning Performance by Breaking the Wall between Graph and Operator Level Optimizationscited by 0
  4. 2026DuplexCadence: Exact State and Execution from a Speech Model's Declared Timelinescited by 0