Towards Efficient I/O Pipelines Using Accumulated Compression
Authors:
- 18 December 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 256-265
Abstract
High-Performance Computing (HPC) workloads generate large volumes of data at high-frequency during their execution, which needs to be captured concurrently at scale. These workloads exploit accelerators such as GPU for faster performance. However, the limited onboard high-bandwidth memory (HBM) on the GPU, and slow device-to-host memory PCIe interconnects lead to I/O overheads during application execution, thereby exacerbating their overall runtime. To overcome the aforementioned limitations, techniques such as compression and asynchronous transfers have been used by data management runtimes. However, compressing small blocks of data leads to a significant runtime penalty on the application. In this paper, we design and develop strategies to optimize the trade-off between compressing checkpoints instantly and enqueuing transfers immediately versus accumulating snapshots and delaying compression to achieve faster compression throughput. Our evaluations on synthetic and real-life workloads for different systems and workload configurations demonstrate 1.3 × to 8.3 × speedup compared to the existing checkpoint approaches.Keywords
Funding Information
- U.S. Department of Energy (DOE)
- National Science Foundation (2106634/2106635)
This publication has 25 references indexed in Scilit:
- A compression-based memory-efficient optimization for out-of-core GPU stencil computationThe Journal of Supercomputing, 2023
- Towards Efficient Cache Allocation for High-Frequency Checkpointing2022
- Reducing Memory Requirements of Quantum Optimal Control2022
- Accelerating GPU-Based Out-of-Core Stencil Computation with On-the-Fly Compression2022
- Checkpoint Restart Support for Heterogeneous HPC Applications2020
- MLBS: Transparent Data Caching in Hierarchical Storage for Out-of-Core HPC Applications2019
- A Case for Portability and Reproducibility of HPC Containers2019
- Deep Learning Accelerated Light Source Experiments2019
- Workflows for Performance Predictable and Reproducible HPC Applications2019
- ADIOS Visualization Schema: A First Step Towards Improving Interdisciplinary Collaboration in High Performance Computing2013