The Deep Learning Compiler: A Comprehensive Survey

Abstract

The difficulty of deploying various deep learning (DL) models on diverse DL hardware has boosted the research and development of DL compilers in the community. Several DL compilers have been proposed from both industry and academia such as Tensorflow XLA and TVM. Similarly, the DL compilers take the DL models described in different DL frameworks as input, and then generate optimized codes for diverse DL hardware as output. However, none of the existing survey has analyzed the unique design architecture of the DL compilers comprehensively. In this paper, we perform a comprehensive survey of existing DL compilers by dissecting the commonly adopted design in details, with emphasis on the DL oriented multi-level IRs, and frontend/backend optimizations. Specifically, we provide a comprehensive comparison among existing DL compilers from various aspects. In addition, we present detailed analysis on the design of multi-level IRs and illustrate the commonly adopted optimization techniques. Finally, several insights are highlighted as the potential research directions of DL compiler. This is the first survey paper focusing on the design architecture of DL compilers, which we hope can pave the road for future research towards DL compiler.

Cited by in corpus (8)

• Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices
• Understanding Performance Problems in Deep Learning Systems
• Fuzzing Deep Learning Compilers with HirGen
• Real-time Graph Building on FPGAs for Machine Learning Trigger Applications in Particle Physics
• CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Accelerators
• Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning & HPC Workloads
• Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras
• Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems