English

Seer: Predictive Runtime Kernel Selection for Irregular Problems

Distributed, Parallel, and Cluster Computing 2024-03-27 v1

Abstract

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×\times over the best single iteration kernel across the entire SuiteSparse Matrix Collection dataset.

Keywords

Cite

@article{arxiv.2403.17017,
  title  = {Seer: Predictive Runtime Kernel Selection for Irregular Problems},
  author = {Ryan Swann and Muhammad Osama and Karthik Sangaiah and Jalal Mahmud},
  journal= {arXiv preprint arXiv:2403.17017},
  year   = {2024}
}
R2 v1 2026-06-28T15:33:06.742Z