Search NASA⌕ Search

SEARCH · Search NASA

Results for “Virtual File Driver”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

HDF5 in the exascale era: Delivering efficient and scalable parallel I/O for exascale applications

Accurately modeling real-world systems requires scientific applications at exascale to generate massive amounts of data and manage data storage efficiently. However, parallel input and output (I/O) faces challenges due to new application workflows and the state-of-the-art memory, interconnect, and storage architectures considered in exascale designs. The storage hierarchy has expanded with node-local persistent memory, solid-state storage, and traditional disk and tape-based storage, thus requiring efficiency at each layer and much more efficient data movement among these layers. This paper discusses how the ExaHDF5 project improved the I/O performance and data management for exascale architectures by enhancing HDF5, a widely used parallel I/O library. The team developed an Asynchronous I/O Virtual Object Layer (VOL) connector that allowed overlapping I/O with computation. They also created a Cache VOL to complement asynchronous I/O by incorporating fast storage layers, such as burst buffer and node-local storage, into the parallel I/O workflow through caching and staging data. Additionally, the team enabled data aggregation and I/O at the node level by using a Subfiling Virtual File Driver (VFD). To demonstrate superior I/O performance with HDF5 at exascale, the ExaHDF5 team collaborated with several exascale applications. In this paper, we show I/O performance improvements for three applications: Cabana (a particle-based simulation library), EQSIM (a regional earthquake simulation software), and E3SM (a climate system modeling library).

Asynchronous I/Ol↗

GPU Direct I/O with HDF5

Exascale HPC systems are being designed with accelerators, such as GPUs, to accelerate parts of applications. In machine learning workloads as well as large-scale simulations that use GPUs as accelerators, the CPU (or host) memory is currently used as a buffer for data transfers between GPU (or device) memory and the file system. If the CPU does not need to operate on the data, then this is sub-optimal because it wastes host memory by reserving space for duplicated data. Furthermore, this “bounce buffer” approach wastes CPU cycles spent on transferring data. A new technique, NVIDIA GPUDirect Storage (GDS), can eliminate the need to use the host memory as a bounce buffer. Thereby, it becomes possible to transfer data directly between the device memory and the file system. This direct data path shortens latency by omitting the extra copy and enables higher-bandwidth. To take full advantage of GDS in existing applications, it is necessary to provide support with existing I/O libraries, such as HDF5 and MPI-IO, which are heavily used in applications. In this paper, we describe our effort of integrating GDS with HDF5, the top I/O library at NERSC and at DOE leadership computing facilities. We design and implement this integration using a HDF5 Virtual File Driver (VFD). The GDS VFD provides a file system abstraction to the application that allows HDF5 applications to perform I/O without the need to move data between CPUs and GPUs explicitly. We compare performance of the HDF5 GDS VFD with explicit data movement approaches and demonstrate superior performance with the GDS method.

Ravi, J↗

Universal Serial Bus Architecture for Removable Media (USB-ARM)

USB-ARM creates operating system drivers which sit between removable media and the user and applications. The drivers isolate the media and submit the contents of the media to a virtual machine containing an entire scanning system. This scanning system may include traditional anti-virus, but also allows more detailed analysis of files, including dynamic run-time analysis, helping to prevent "zero-day" threats not already identified in anti-virus signatures. Once cleared, the media is presented to the operating system, at which point it becomes available to users and applications.

Source record↗

Data and scripts associated with “Riverine dissolved organic matter transformations increase with watershed area, water residence time, and Damköhler numbers in nested watersheds” (v2)

This data package is associated with the publication “Riverine dissolved organic matter transformations increase with watershed area, water residence time, and Damköhler numbers in nested watersheds” submitted to Biogeochemistry by Ryan et al., 2024 (DOI: https://doi.org/10.1007/s10533-024-01169-5). This study aims to investigate fundamental and transferable drivers of dissolved organic matter (DOM) diversity across five nested watersheds within the contiguous United States. DOM diversity was explored using ultrahigh-resolution Fourier transform ion cyclotron resonance mass spectrometry (FTICR-MS). The samples and the unprocessed FTICR-MS data used in this study are publicly available on the Environmental System Science Data Infrastructure for a Virtual Ecosystem (ESS-DIVE) data repository (see DOIs below). The data for the Willamette, Gunnison, Connecticut, and Deschutes basins were collected as part of a collaboration between the Watershed Rules of Life (WROL) project and Worldwide Hydrobiogeochemistry Observation Network for Dynamic River Systems (WHONDRS). The data for the Yakima River basin (YRB) was collected by the PNNL River Corridor SFA. The raw, unprocessed FTICR-MS data with additional (meta)data can be found at doi:10.15485/1895159 for WROL samples and doi:10.15485/1898912 for YRB samples. This data package contains the processed data used in the associated manuscript. This package also contains ancillary geospatial, hydrological, and geochemical information that supports the interpretation of the FTICR-MS data within Ryan et al., 2024. This data package is associated with the GitHub repository found at https://github.com/WHONDRS-Hub/rcsfa-RC4-WROL-YRB_DOM_Diversity. This data package was originally published August 2024. It was updated January 2025 (modified files). See the change history in the readme more details. At the directory level, the data package is comprised of three folders: (1) data, (2) output, and (3) src; and five additional files including the data dictionary (file ending in "_dd.csv”) and file-level metadata (file ending in “_flmd.csv”). The “src” folder contains the scripts used to process the FTICR data, conduct the analyses, and produce the manuscript figures. The inputs for these scripts are in the “data” folder and the returned outputs in the “output” folder. Inputs include temporal and spatial metadata associated with the sampling efforts, processed FTICR data, and total and normalized putative biochemical transformations per sample. Outputs include cleaned and combined data presented as tables, descriptive statistics, and plots. The file-level metadata file lists all files contained in this data package and descriptions for each. The data dictionary describes the units and definitions for each tabular data column or row header.

54 ENVIRONMENTAL SCIENCES↗