I/O has become one of the determining factors of HPC application performance. Understanding an application's I/O activity requires a multi-level view of the I/O function flow that includes high-level I/O libraries. We have developed a tracing framework, called Recorder, that captures I/O function calls at multiple layers of the parallel I/O stack without requiring source code modifications. In this paper, we show how Recorder's trace output can be used to investigate I/O activity and identify performance inefficiencies in two I/O benchmarks running on a leading edge HPC platform. Future work to organize and present the collected information more intuitively will further increase the value of Recorder's capabilities. We believe that a multi-level I/O tracing framework can provide key insights to end users and I/O library developers working to improve I/O on HPC platforms.

We present an auto-tuning system for optimizing I/O performance of HDF5 applications and demonstrate its value across platforms, applications, and at scale. The system uses a genetic algorithm to search a large space of tunable parameters and to identify effective settings at all layers of the parallel I/O stack. The parameter settings are applied transparently by the auto-tuning system via dynamically intercepted HDF5 calls.

Advanced instruments in a variety of scientific domains are collecting massive amounts of data that must be postprocessed and organized to support research activities. Astronomers have been pioneers in the use of databases to host sky survey data. Increasing data volumes from more powerful telescopes pose enormous challenges to state-ofthe- art database systems and data-loading techniques. In this paper we present SkyLoader, our novel framework for data loading that is being used to populate a multi-table, multi-terabyte database repository for the Palomar-Quest sky survey. SkyLoader consists of an efficient algorithm for bulk loading, an effective data structure to support data integrity, optimized parallelism, and guidelines for system tuning. Performance studies show the positive effects of these techniques, with load time for a 40-gigabyte data set reduced from over 20 hours to less than 3 hours. Our framework offers a promising approach for loading other large and complex scientific databases.

Complex, distributed applications pose new challenges for performance analysis and optimization. This paper outlines an online approach to performance analysis where developers are active participants, using integrated measurement and immersive performance visualization to tune parallel and distributed applications.

The modest I/O configurations and file system limitations of many current high-performance systems preclude solution of problems with large I/O needs. I/O hardware and file system parallelism is the key to achieving high performance. We analyze the I/O behavior of several versions of two scientific applications on the Intel Paragon XP/S. The versions involve incremental application code enhancements across multiple releases of the operating system. Studying the evolution of I/O access patterns underscores the interplay between application access patterns and file system features. Our results show that both small and large request sizes are common, that at present, application developers must manually aggregate small requests to obtain high disk transfer rates, that concurrent file accesses are frequent, and that appropriate matching of the application access pattern and the file system access mode can significantly increase application I/O performance. Based on these results, we describe a set of file system design principles.

Rapid increases in computing and communication performance are exacerbating the long-standing problem of performance-limited input/output. Indeed, for many otherwise scalable parallel applications. input/output is emerging as a major performance bottleneck. The design of scalable input/output systems depends critically on the input/output requirements and access patterns for this emerging class of large-scale parallel applications. However, hard data on the behavior of such applications is only now becoming available. In this paper, we describe the input-output requirements of three scalable parallel applications (electron scattering, terrain rendering, and quantum chemistry, on the Intel Paragon XP/S. As part of an ongoing parallel input/output characterization effort, we used instrumented versions of the application codes to capture and analyze input/output volume, request size distributions, and temporal request structure. Because complete traces of individual application input/output requests were captured, in-depth, off-line analyses were possible. In addition, we conducted informal interviews of the application developers to understand the relation between the codes' current and desired input/output structure. The results of our studies show a wide variety of temporal and spatial access patterns, including highly read-intensive and write-intensive phases, extremely large and extremely small request sizes, and both sequential and highly irregular access patterns. We conclude with a discussion of the broad spectrum of access patterns and their profound implications for parallel file caching and prefetching schemes.