Accelerating Flash-X Simulations with Asynchronous I/O

Conference · Tue Nov 01 04:00:00 EDT 2022

DOI:https://doi.org/10.1109/PDSW56643.2022.00008· OSTI ID:1959631

Jain, Rajeev ^[1]; Tang, Houjun ^[2]; Dhruv, Akash ^[1]; Harris, Austin ^[3]; Byna, Suren ^[4]

---

1. Argonne National Laboratory (ANL)
2. Lawrence Berkeley Laboratory, CA
3. ORNL
4. Lawrence Berkeley National Laboratory (LBNL)

Most high-fidelity physics simulation codes, such as Flash-X, need to save intermediate results (checkpoint files) to restart or gain insights into the evolution of the simulation. These simulation codes save such intermediate files synchronously, where computation is stalled while the data is written to storage. Depending on the problem size and computational requirements, this file write time can be a substantial portion of the total simulation time. In order to hide the I/O latency of checkpointing, asynchronous I/O methods have been introduced. These methods use background threads for performing I/O while the main threads continue with the simulation. The usage of background threads can compete for resources on the node as well as with communication. In this paper, we evaluate the overheads and the overall benefit of asynchronous I/O in HDF5 to simulations. Results from real-world high-fidelity simulations on the Summit supercomputer show that I/O operation is overlapped with application communication or computation or both, effectively hiding some or all of the I/O latency. Our evaluation shows that while using asynchronous I/O adds overhead to the application, the I/O time reduction is more significant, resulting in overall up to 1.5X performance speedup.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE; USDOE Office of Science (SC)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1959631
• Country of Publication: United States
• Language: English