On the Scalability of Data Reduction Techniques in Current and Upcoming HPC Systems from an Application Perspective

Axel Huebl, Rene Widera, Felix Schmitt, Alexander Matthes, Norbert Podhorszki +3 more
6/1/2017
cs.PFphysics.comp-ph

Official code: ComputationalRadiationPhysics/picongpu (796 stars, last commit 2026-10-20).

Abstract

We implement and benchmark parallel I/O methods for the fully-manycore driven particle-in-cell code PIConGPU. Identifying throughput and overall I/O size as a major challenge for applications on today's and future HPC systems, we present a scaling law characterizing performance bottlenecks in state-of-the-art approaches for data reduction. Consequently, we propose, implement and verify multi-threaded data-transformations for the I/O library ADIOS as a feasible way to trade underutilized host-side compute potential on heterogeneous systems for reduced I/O latency.

View on arXivView PDF

Code Implementations(1)

ComputationalRadiationPhysics/picongpuOfficial100%

Performance-Portable Particle-in-Cell Simulations for the Exascale Era :sparkles:

796230Awk, C++Jul 30, 20132 days agoNOASSERTION
gpugpu-computinglaserparticle-acceleratorparticle-in-cell+5 more

Similar Papers

Grid: A next generation data parallel C++ QCD library

76% match1 repo1782015

Optimizing ML Workload Partitioning between CPUs and CIM Accelerators for Heterogeneous Computing

75% match2026

Blaze: Simplified High Performance Cluster Computing

74% match1 repo62019

Efficient Learned Data Compression via Dual-Stream Feature Decoupling

74% match1 repo22026

High-Performance Parallel Optimization of the Fish School Behaviour on the Setonix Platform Using OpenMP

74% match2025

LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication

74% match2024

Cite this paper

@article{huebl2017scalability,
  title  = {On the Scalability of Data Reduction Techniques in Current and Upcoming HPC Systems from an Application Perspective},
  author = {Axel Huebl and Rene Widera and Felix Schmitt and Alexander Matthes and Norbert Podhorszki and Jong Youl Choi and Scott Klasky and Michael Bussmann},
  year   = {2017},
  eprint = {1706.00522},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1706.00522}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1706.00522.svg)](https://codeofpaper.com/paper/1706.00522)

Discussion