Seer: Predictive Runtime Kernel Selection for Irregular Problems

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, a...

Full description

Bibliographic Details

Published in:	Proceedings / International Symposium on Code Generation and Optimization pp. 133 - 142
Main Authors:	Swann, Ryan, Osama, Muhammad, Sangaiah, Karthik, Mahmud, Jalal
Format:	Conference Proceeding
Language:	English
Published:	IEEE 02.03.2024
Subjects:	GPU Kernel Kernel Predictor Load Balancing Load modeling Optimization Parallel processing Runtime Sparse Linear Algebra Sparse matrices Vectors
ISSN:	2643-2838
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!