TVM: An Automated End-to-End Optimizing Compiler for Deep Learning

TL;DR

TVM is an automated compiler that optimizes deep learning workloads across diverse hardware platforms, reducing manual effort and achieving performance comparable to hand-tuned libraries.

Contribution

It introduces a novel, learning-based cost modeling approach and graph-level optimizations for portable, high-performance deep learning compilation.

Findings

Performance competitive with state-of-the-art libraries

Effective on CPUs, GPUs, and FPGAs

Open source and in production use

Abstract

There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries and optimize for a narrow range of server-class GPUs. Deploying workloads to new platforms -- such as mobile phones, embedded devices, and accelerators (e.g., FPGAs, ASICs) -- requires significant manual effort. We propose TVM, a compiler that exposes graph-level and operator-level optimizations to provide performance portability to deep learning workloads across diverse hardware back-ends. TVM solves optimization challenges specific to deep learning, such as high-level operator fusion, mapping to arbitrary hardware primitives, and memory latency hiding. It also automates optimization of low-level programs to hardware characteristics by employing a novel, learning-based cost modeling method for rapid exploration of code optimizations. Experimental results show that TVM delivers performance across hardware back-ends that are competitive with state-of-the-art, hand-tuned libraries for low-power CPU, mobile GPU, and server-class GPUs. We also demonstrate TVM's ability to target new accelerator back-ends, such as the FPGA-based generic deep learning accelerator. The system is open sourced and in production use inside several major companies.