# Seer: Predictive Runtime Kernel Selection for Irregular Problems

arXiv: https://arxiv.org/abs/2403.17017 · HTML: https://mlsanity.com/paper/2403.17017/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2024.

## Built on by (most cited first, 1 of 1)

- [Spectral Analysis for Sparse Matrix Computation: Insights and Potential](https://mlsanity.com/paper/2608.29362/) (2026)

## Abstract (arXiv)

Modern GPUs are designed for regular problems and suffer from load imbalance when processing irregular data. Prior to our work, a domain expert selects the best kernel to map fine-grained irregular parallelism to a GPU. We instead propose Seer, an abstraction for producing a simple, reproduceable, and understandable decision tree selector model which performs runtime kernel selection for irregular workloads. To showcase our framework, we conduct a case study in Sparse Matrix Vector Multiplication (SpMV), in which Seer predicts the best strategy for a given dataset with an improvement of 2× over the best single iteration kernel across the entire SuiteSparse Matrix Collection dataset.