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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / International Symposium on Code Generation and Optimization S. 133 - 142
Hauptverfasser: Swann, Ryan, Osama, Muhammad, Sangaiah, Karthik, Mahmud, Jalal
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 02.03.2024
Schlagworte:
GPU
Kernel
Kernel Predictor
Load Balancing
Load modeling
Optimization
Parallel processing
Runtime
Sparse Linear Algebra
Sparse matrices
Vectors
ISSN:2643-2838
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:2643-2838
DOI:10.1109/CGO57630.2024.10444812