# DLVM: A modern compiler infrastructure for deep learning systems

arXiv: https://arxiv.org/abs/1711.03016 · HTML: https://mlsanity.com/paper/1711.03016/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2017.

## Built on by (most cited first, 4 of 4)

- [Astra: A Multi-Agent System for GPU Kernel Performance Optimization](https://mlsanity.com/paper/2509.07506/) (2025)
- [ThunderKittens: Simple, Fast, and Adorable AI Kernels](https://mlsanity.com/paper/2410.20399/) (2024)
- [A Data-Centric Optimization Framework for Machine Learning](https://mlsanity.com/paper/2110.10802/) (2021)
- [A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimization](https://mlsanity.com/paper/2601.12698/) (2026)

## Abstract (arXiv)

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.