DeepAI AI Chat
Log In Sign Up

DLVM: A modern compiler infrastructure for deep learning systems

by   Richard Wei, et al.
University of Illinois at Urbana-Champaign

Deep learning software demands reliability and performance. However, many of the existing deep learning frameworks are software libraries that act as an unsafe DSL in Python and a computation graph interpreter. We present DLVM, a design and implementation of a compiler infrastructure with a linear algebra intermediate representation, algorithmic differentiation by adjoint code generation, domain-specific optimizations and a code generator targeting GPU via LLVM. Designed as a modern compiler infrastructure inspired by LLVM, DLVM is more modular and more generic than existing deep learning compiler frameworks, and supports tensor DSLs with high expressivity. With our prototypical staged DSL embedded in Swift, we argue that the DLVM system enables a form of modular, safe and performant frameworks for deep learning.


page 2

page 3


A Modular Benchmarking Infrastructure for High-Performance and Reproducible Deep Learning

We introduce Deep500: the first customizable benchmarking infrastructure...

LoopStack: a Lightweight Tensor Algebra Compiler Stack

We present LoopStack, a domain specific compiler stack for tensor operat...

A Modern Compiler for the French Tax Code

In France, income tax is computed from taxpayers' individual returns, us...

High Performance Code Generation in MLIR: An Early Case Study with GEMM

This article is primarily meant to present an early case study on using ...

nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

Homomorphic encryption (HE)--the ability to perform computations on encr...

NOELLE Offers Empowering LLVM Extensions

Modern and emerging architectures demand increasingly complex compiler a...