User-Defined Functions for HDF5

TL;DR

This paper introduces an infrastructure for HDF5 that allows user-defined functions to be embedded and executed dynamically during dataset access, enabling flexible data processing and extension.

Contribution

It presents a novel architecture for integrating user-defined functions into HDF5 files, supporting on-demand data processing, security, and hardware acceleration.

Findings

Enables on-the-fly dataset population with UDFs

Supports hardware accelerators and computational storage

Demonstrates extended use cases for scientific data

Abstract

Scientific datasets are known for their challenging storage demands and the associated processing pipelines that transform their information. Some of those processing tasks include filtering, cleansing, aggregation, normalization, and data format translation -- all of which generate even more data. In this paper, we present an infrastructure for the HDF5 file format that enables dataset values to be populated on the fly: task-related scripts can be attached into HDF5 files and only execute when the dataset is read by an application. We provide details on the software architecture that supports user-defined functions (UDFs) and how it integrates with hardware accelerators and computational storage. Moreover, we describe the built-in security model that limits the system resources a UDF can access. Last, we present several use cases that show how UDFs can be used to extend scientific datasets in ways that go beyond the original scope of this work.