Performance Analysis and Automatic Tuning of Hash Aggregation on GPUs

Viktor Rosenfeld, Sebastian Bress, Steffen Zeuch, Tilmann Rabl, Volker Markl
DFKI, Berlin
Data Management on New Hardware workshop at the ACM SIGMOD (DaMoN ’19), 2019


   title={Performance Analysis and Automatic Tuning of Hash Aggregation on GPUs},

   author={Rosenfeld, Viktor and Bre{ss}, Sebastian and Zeuch, Steffen and Rabl, Tilmann and Markl, Volker},



Download Download (PDF)   View View   Source Source   



Hash aggregation is an important data processing primitive which can be significantly accelerated by modern graphics processors (GPUs). Previous work derived heuristics for GPU-accelerated hash aggregation from the study of a particular GPU. In this paper, we examine the influence of different execution parameters on GPUaccelerated hash aggregation on four NVIDIA and two AMD GPUs based on six different microarchitectures. While we are able to replicate some of the previous results, our main finding is that optimal execution parameters are highly GPU-dependent. Most importantly, execution parameters optimized for a specific GPU are up to 21× slower on other GPUs. Given this hardware dependency, we present an algorithm to optimize execution parameters at runtime. On GPUs with low runtime variation, our algorithm finds execution parameters that are less than 4% slower than the optimum on average and less than 18% slower in the worst case.
Rating: 2.0/5. From 1 vote.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: