Many scientific applications that run on today’s multiprocessors, such as weather forecasting and seismic analysis, are bottlenecked by their file-I/O needs. Even if the multiprocessor is configured with sufficient I/O hardware, the file-system software often fails to provide the available bandwidth to the application. Although libraries and enhanced file-system interfaces can make a significant improvement, we believe that fundamental changes are needed in the file-server software. We propose a new technique, disk-directed I/O, to allow the disk servers to determine the flow of data for maximum performance. Our simulations show that tremendous performance gains are possible. Indeed, disk-directed I/O provided consistent high performance that was largely independent of data distribution, obtained up to 93 % of peak disk bandwidth, and was as much as 16 times faster than traditional parallel file systems.

Most current multiprocessor le systems are designed to use multiple disks in parallel, using the high aggregate bandwidth to meet the growing I/O requirements of parallel scienti c applications. Many multiprocessor le systems provide applications with a conventional Unix-like interface, allowing the application to access multiple disks transparently. Thisinterface conceals the parallelism within the le system, increasing the ease of programmability, but making it di cult or impossible for sophisticated programmers and libraries to use knowledge about their I/O needs to exploit that parallelism. In addition to providing an insu cient interface, most current multiprocessor le systems are optimized for a di erent workload than they are being asked to support. We introduce Galley, a new parallel le system that is intended to e ciently support realistic scienti c multiprocessor workloads. We discuss Galley's le structure and application interface, as well as the performance advantages o ered by that interface. 1

Rapid increases in computing and comm unication 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. Ho wever, 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 e ort, we used instrumented versions of the application codes to capture

Multiprocessors have permitted astounding increases in computational performance, but many cannot meet the intense I/O requirements of some scientific applications. An important component of any solution to this I/O bottleneck is a parallel file system that can provide high-bandwidth access to tremendous amounts of data in parallel to hundreds or thousands of processors. Most successful systems are based on a solid understanding of the expected workload, but thus far there have been no comprehensive workload characterizations of multiprocessor le systems. This paper presents the results of a three week tracing study in which all file-related activity on a massively parallel computer was recorded. Our instrumentation di ers from previous efforts in that it collects information about every I/O request and about the mix of jobs running in a production environment. We also present the results of a trace-driven caching simulation and recommendations for designers of multiprocessor file systems.

As the I/O needs of parallel scienti c applications increase, le systems for multiprocessors are being designed to provide applications with parallel access to multiple disks. Many parallel le systems present applications with a conventional Unix-like interface that allows the application to access multiple disks transparently. By tracing all the activity of a parallel le system in a production, scienti c computing environment, we show that many applications exhibit highly regular, but non-consecutive I/O access patterns. Since the conventional interface does not provide an e cient method of describing these patterns, we present three extensions to the interface that support strided, nested-strided, and nestedbatched I/O requests. We show how these extensions can be used to express common access patterns. 1

As parallel computers are increasingly used to run scienti c applications with large data sets, and as processor speeds continue to increase, it becomes more important to provide fast, e ective parallel le systems for data storage and for temporary les. In an earlier work we demonstrated that a technique we call disk-directed I/O has the potential to provide consistent high performance for large, collective, structured I/O requests. In this paper we expand on this potential by demonstrating the ability of a disk-directed I/O system to read irregular subsets of data from a le, and to lter and distribute incoming data according to data-dependent functions. 1

New le systems are critical to obtain good I/O performance on large multiprocessors. Several researchers have suggested the use of collective le-system operations, in which all processes in an application cooperate in each I/O request. Others have suggested that the traditional lowlevel interface (read, write, seek) be augmented with various higher-level requests (e.g., read matrix), allowing the programmer to express a complex transfer in a single (perhaps collective) request. Collective, high-level requests permit techniques like two-phase I/O and disk-directed I/O to signi cantly improve performance over traditional le systems and interfaces. Neither of these techniques have been tested on anything other than simple benchmarks that read or write matrices. Many applications, however, intersperse computation and I/O to work with data sets that cannot t in main memory. In this paper, we present the results of experiments with an \out-of-core " LU-decomposition program, comparing a traditional interface and le system with a system that has a high-level, collective interface and disk-directed I/O. We found that a collective interface was awkward in some places, and forced additional synchronization. Nonetheless, disk-directed I/O was able to obtain much better performance than the traditional system.

Scientific applications are increasingly being implemented on massively parallel supercomputers. Many of these applications have intense I/O demands, as well as massive computational requirements. This paper is essentially an annotated bibliography of papers and other sources of information about scientific applications using parallel I/O. It will be updated periodically.

As the I/O needs of parallel scientific applications increase, file systems for multiprocessors are being designed to provide applications with parallel access to multiple disks. Many parallel file systems present applications with a conventional Unix-like interface that allows the application to access multiple disks transparently. This interface conceals the parallelism within the file system, which increases the ease of programmability, but makes it difficult or impossible for sophisticated programmers and libraries to use knowledge about their I/O needs to exploit that parallelism. Furthermore, most current parallel file systems are optimized for a different workload than they are being asked to support. We introduce Galley, a new parallel file system that is intended to efficiently support realistic parallel workloads. Initial experiments, reported in this paper, indicate that Galley is capable of providing high-performance I/O to applications that access data in patterns that have been observed to be common.

As the I/O needs of parallel scienti c applications increase, le systems for multiprocessors are being designed to provide applications with parallel access to multiple disks. Many parallel le systems present applications with a conventional Unix-like interface that allows the application to access multiple disks transparently. By tracing all the activity of a parallel le system in a production, scienti c computing environment, we show that many applications exhibit highly regular, but non-consecutive I/O access patterns. Since the conventional interface does not provide an e cient method of describing these patterns, we present an extension which supports strided and nested-strided I/O requests. 1