GPU Performance Estimation using Software Rasterization and Machine Learning

This paper introduces a predictive modeling framework to estimate the performance of GPUs during pre-silicon design. Early-stage performance prediction is useful when simulation times impede development by rendering driver performance validation, API conformance testing and design space explorations...

Full description

Saved in:
Bibliographic Details
Published in:ACM transactions on embedded computing systems 2017-10, Vol.16 (5s), p.1-21
Main Authors: O'neal, Kenneth, Brisk, Philip, Abousamra, Ahmed, Waters, Zack, Shriver, Emily
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:This paper introduces a predictive modeling framework to estimate the performance of GPUs during pre-silicon design. Early-stage performance prediction is useful when simulation times impede development by rendering driver performance validation, API conformance testing and design space explorations infeasible. Our approach builds a Random Forest regression model to analyze DirectX 3D workload behavior when executed by a software rasterizer, which we have extended with a workload characterizer to collect further performance information via program counters. In addition to regression models, this work produces detailed feature rankings which can provide valuable architectural insight, and accurate performance estimates for an Intel integrated Skylake generation GPU. Our models achieve reasonable out-of-sample-error rates of 14%, with an average simulation speedup of 327x.
ISSN:1539-9087
1558-3465
DOI:10.1145/3126557