Packet-Oriented Streamline Tracing on Modern SIMD Architectures

Hentschel, Bernd; Göbbert, Jens Henrik; Klemm, Michael; Springer, Paul; Schnorr, Andrea; Kuhlen, Torsten W.

Packet-Oriented Streamline Tracing on Modern SIMD Architectures

Files

043-052.pdf (18.34 MB)

Date

2015

Authors

Hentschel, Bernd
Göbbert, Jens Henrik
Klemm, Michael
Springer, Paul
Schnorr, Andrea
Kuhlen, Torsten W.

Publisher

The Eurographics Association

Abstract

The advection of integral lines is an important computational kernel in vector field visualization. We investigate how this kernel can profit from vector (SIMD) extensions in modern CPUs. As a baseline, we formulate a streamline tracing algorithm that facilitates auto-vectorization by an optimizing compiler. We analyze this algorithm and propose two different optimizations. Our results show that particle tracing does not per se benefit from SIMD computation. Based on a careful analysis of the auto-vectorized code, we propose an optimized data access routine and a re-packing scheme which increases average SIMD efficiency. We evaluate our approach on three different, turbulent flow fields. Our optimized approaches increase integration performance up to 5:6 over our baseline measurement. We conclude with a discussion of current limitations and aspects for future work.

        @inproceedings{10.2312:pgv.20151154
,
booktitle = {Eurographics Symposium on Parallel Graphics and Visualization
},
editor = {C. Dachsbacher and P. Navrátil
},
title = {{Packet-Oriented Streamline Tracing on Modern SIMD Architectures
}},
author = {Hentschel, Bernd and 
Göbbert, Jens Henrik and 
Klemm, Michael and 
Springer, Paul and 
Schnorr, Andrea and 
Kuhlen, Torsten W.
},
year = {2015
},
publisher = {The Eurographics Association
},
ISBN = {},
DOI = {10.2312/pgv.20151154
}
}