On the Anatomy of Predictive Models for Accelerating GPU Convolution Kernels and Beyond

Efficient HPC libraries often expose multiple tunable parameters, algorithmic implementations, or a combination of them, to provide optimized routines. The optimal parameters and algorithmic choices may depend on input properties such as the shapes of the matrices involved in the operation. Traditio...

Full description

Saved in:
Bibliographic Details
Published in:ACM transactions on architecture and code optimization 2021-01, Vol.18 (1), p.1-24
Main Authors: Labini, Paolo Sylos, Cianfriglia, Marco, Perri, Damiano, Gervasi, Osvaldo, Fursin, Grigori, Lokhmotov, Anton, Nugteren, Cedric, Carpentieri, Bruno, Zollo, Fabiana, Vella, Flavio
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Efficient HPC libraries often expose multiple tunable parameters, algorithmic implementations, or a combination of them, to provide optimized routines. The optimal parameters and algorithmic choices may depend on input properties such as the shapes of the matrices involved in the operation. Traditionally, these parameters are manually tuned or set by auto-tuners. In emerging applications such as deep learning, this approach is not effective across the wide range of inputs and architectures used in practice. In this work, we analyze different machine learning techniques and predictive models to accelerate the convolution operator and GEMM. Moreover, we address the problem of dataset generation, and we study the performance, accuracy, and generalization ability of the models. Our insights allow us to improve the performance of computationally expensive deep learning primitives on high-end GPUs as well as low-power embedded GPU architectures on three different libraries. Experimental results show significant improvement in the target applications from 50% up to 300% compared to auto-tuned and high-optimized vendor-based heuristics by using simple decision tree- and MLP-based models.
ISSN:1544-3566
1544-3973
DOI:10.1145/3434402