DLVM: A modern compiler framework for neural network DSLs

Abstract

Deep learning software demands reliability and performance. 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 framework… (More)

Topics

5 Figures and Tables

Slides referencing similar topics