Cross-architecture performance prediction (XAPP) using CPU code to predict GPU performance

GPUs have become prevalent and more general purpose, but GPU programming remains challenging and time consuming for the majority of programmers. In addition, it is not always clear which codes will benefit from getting ported to GPU. Therefore, having a tool to estimate GPU performance for a piece o...

Full description

Saved in:
Bibliographic Details
Published in:2015 48th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) pp. 725 - 737
Main Authors: Ardalani, Newsha, Lestourgeon, Clint, Sankaralingam, Karthikeyan, Xiaojin Zhu
Format: Conference Proceeding
Language:English
Published: ACM 01.12.2015
Subjects:
Cross-platform Prediction
GPU
Graphics processing units
Hardware
Kernel
Machine Learning
Performance Modeling
Prediction algorithms
Predictive models
Programming
Time measurement
ISSN:2379-3155
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:GPUs have become prevalent and more general purpose, but GPU programming remains challenging and time consuming for the majority of programmers. In addition, it is not always clear which codes will benefit from getting ported to GPU. Therefore, having a tool to estimate GPU performance for a piece of code before writing a GPU implementation is highly desirable. To this end, we propose Cross-Architecture Performance Prediction (XAPP), a machine-learning based technique that uses only single-threaded CPU implementation to predict GPU performance. Our paper is built on the two following insights: i) Execution time on GPU is a function of program properties and hardware characteristics. ii) By examining a vast array of previously implemented GPU codes along with their CPU counterparts, we can use established machine learning techniques to learn this correlation between program properties, hardware characteristics and GPU execution time. We use an adaptive two-level machine learning solution. Our results show that our tool is robust and accurate: we achieve 26.9% average error on a set of 24 real-world kernels. We also discuss practical usage scenarios for XAPP.
ISSN:2379-3155
DOI:10.1145/2830772.2830780