# Stardust: Compiling Sparse Tensor Algebra to a Reconfigurable Dataflow Architecture

arXiv: https://arxiv.org/abs/2211.03251 · HTML: https://mlsanity.com/paper/2211.03251/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2022.

## Built on by (most cited first, 3 of 3)

- [AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization](https://mlsanity.com/paper/2511.15915/) (2025)
- [FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow](https://mlsanity.com/paper/2511.04768/) (2025)
- [Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism](https://mlsanity.com/paper/2511.07776/) (2025)

## Abstract (arXiv)

We introduce Stardust, a compiler that compiles sparse tensor algebra to reconfigurable dataflow architectures (RDAs). Stardust introduces new user-provided data representation and scheduling language constructs for mapping to resource-constrained accelerated architectures. Stardust uses the information provided by these constructs to determine on-chip memory placement and to lower to the Capstan RDA through a parallel-patterns rewrite system that targets the Spatial programming model. The Stardust compiler is implemented as a new compilation path inside the TACO open-source system. Using cycle-accurate simulation, we demonstrate that Stardust can generate more Capstan tensor operations than its authors had implemented and that it results in 138× better performance than generated CPU kernels and 41× better performance than generated GPU kernels.