Web 3.0, built on blockchain technology, prioritizes user privacy and autonomy, presenting new opportunities for financial systems while also complicating the regulation of illicit activities. In this study, we present a novel infrastructure named Pseudo Fine-tuning (PFT) that provides account matching services to combat financial crimes on account-based blockchains such as money laundering through coin-mixing services. The significance of PFT lies in overcoming the need for real labels to fine-tune language models for account matching, given the limited availability of labeled account pairs for the task. Specifically, our design involves (1) crafting pseudo-labeled pairs from transactions of an account across different periods, and (2) fine-tuning language models to distill knowledge from pseudo pairs, which is transferable to the target task. We provide an in-depth analysis to investigate the inherent knowledge acquired during the PFT process and the conditions conducive to its effectiveness. Comprehensive experiments on real-world datasets collected from coin-mixing services and ENS name services, corroborate that the framework delivers pronounced enhancements over state-of-the-art approaches. Our implementation is released at https://github.com/git-disl/PFT .

Cache systems are widely used to speed up data retrieving. Modern HPC, data analytics, and AI/ML workloads generate vast, multi-dimensional datasets, and those data are accessed via complex queries. However, the probability of requesting the exact same data across different queries is low, leading to limited performance improvement when a traditional key-value cache is applied. In this paper, we present Mosaic-Cache, a proactive and general caching framework that enables applications with efficient partial overlapped data reuse through novel overlap-aware cache interfaces for fast content-level reuse. The core components include a metadata manager leveraging customizable indexing for fast overlap lookups, an adaptive fetch planner for dynamic cache-to-storage decisions, and an async merger to reduce cache fragmentation and redundancy. Evaluations on real-world HPC datasets show that Mosaic-Cache improves overall performance by up to 4.1× over traditional key-value-based cache while adding minimal overhead in worst-case scenarios.

Large-scale simulations or scientific experiments produce petabytes of data per run. This poses massive challenges for I/O and storage when scientific analysis workflows are run manually offline. Unsupervised deep learning-based techniques to extract patterns and non-linear relations from these large amounts of data provide a way to build scientific understanding from raw data, reducing the need for manual pre-selection of analysis steps, but require exascale compute and memory to process the full dataset available. In this paper, we demonstrate a heterogeneous streaming workflow in which plasma simulation data is streamed directly to a Machine Learning (ML) application training a model on the simulation data in-transit, completely circumventing the capacity-constrained filesystem bottleneck. This workflow employs openPMD to provide a high level interface to describe scientific data and also uses ADIOS2, to transfer volumes of data that exceed the capabilities of the filesystem. We employ experience replay to avoid catastrophic forgetting in learning from this non-steady state process in a continual manner and adapt it to improve model convergence while learning in-transit. As a proof-of-concept, we approach the ill-posed inverse problem of predicting particle dynamics from radiation in a particle-incell (PIConGPU) simulation of the Kelvin-Helmholtz instability (KHI). We detail hardware-software co-design challenges as we scale PIConGPU to full Frontier, the Top-1 system as of June 2024 Top500 list.

The ever-increasing volume of data produced by HPC simulations necessitates scalable methods for data exploration and knowledge extraction. Scientific data analysis often involves complex queries across distributed datasets, requiring manipulation of multiple primary variables and generating derived data that needs to be handled efficiently, creating challenges for applications that need to parse many large datasets. Relying on individual applications to handle all intermediate data generally leads to redundant computations across studies and unnecessary data transfers. In this paper, we investigate the performance of different approaches where applications define derived variables as quantities of interest (QoIs) and offload the computation and transfer of these QoIs to the I/O library. This significantly reduces redundancy and optimizes data movement across the distributed storage and processing infrastructure by allowing control over when and where derived variables are computed. We present a detailed analysis of the performance-storage trade-offs associated with different solutions and showcase results for our study on two large-scale datasets created from climate and combustion simulations.

The FAIR principles for scientific data (Findable, Accessible, Interoperable, Reusable) are also relevant to other digital objects such as research software and scientific workflows that operate on scientific data. The FAIR principles can be applied to the data being handled by a scientific workflow as well as the processes, software, and other infrastructure which are necessary to specify and execute a workflow. The FAIR principles were designed as guidelines, rather than rules, that would allow for differences in standards for different communities and for different degrees of compliance. There are many practical considerations which impact the level of FAIR-ness that can actually be achieved, including policies, traditions, and technologies. Because of these considerations, obstacles are often encountered during the workflow lifecycle that trace directly to shortcomings in the implementation of the FAIR principles. Here, we detail some cases, without naming names, in which data and workflows were Findable but otherwise lacking in areas commonly needed and expected by modern FAIR methods, tools, and users. We describe how some of these problems, all of which were overcome successfully, have motivated us to push on systems and approaches for fully FAIR workflows.

Solid state storage systems have been very effectively used in small devices; however, their effectiveness for large systems such as supercomputers is not yet proven. Recently, for the first time, a new supercomputer is being deployed with an all-flash storage as its main file system. In this work, we report our preliminary study of the I/O performance on this supercomputer named Perlmutter. We are able to achieve 1.4 TB/s with the default file configuration on the system. This default configuration outperforms dozens of other choices tested, though the current observed performance is still pretty far from the theoretical peak performance of 5 TB/s.

Due to the system scaling,transient errorscaused by external noise, e.g., heat fluxes and particle strikes, have become a growing concern for the current and upcoming exa-scale high-performance-computing (HPC) systems. Applications running on these systems are expected to experience transient errors more frequently than ever before, which will either lead them to generate incorrect outputs or cause them to crash. However, since such errors are still quite rare as compared to no-fault cases, desirable solutions call for low/no-overhead systems that do not compromise the performance under no-fault conditions and also allow very fast fault recovery to minimize downtime. In this article, we presentIterPro, a light-weight compiler-assisted resilience technique to quickly and accurately recover processes from transient-error-induced crashes. During the compilation of applications,IterProconstructs a set of recovery kernels for crash-prone instructions. These recovery kernels are executed to repair the corrupted process states on-the-fly upon occurrences of errors, enabling applications to continue their executions instead of being terminated. When constructing recovery kernels,IterProexploits side effects introduced by induction variable based code optimization techniques based on loop unrolling and strength reduction to improve its recovery capability. To this end, two new code transformation passes are introduced to expose the side effects for resilience purposes. We evaluatedIterProwith 4 scientific workloads as well as the NPB benchmarks suite. During their normal execution,IterProincurs almostzeroruntime overhead and a small, fixed27MBmemory overhead. Meanwhile,IterProcan recover on an average 83.55 percent of crash-causing errors within dozens of milliseconds with negligible downtime. We also evaluatedIterProwith parallel jobs running on 3072 cores and showed thatIterProcan successfully mask the impact of crash-causing errors by providing almost uninterrupted execution. Finally, we present our preliminary evaluation result for BLAS, which shows thatIterProis capable of recovering failures in libraries with a very high coverage rate of 83 percent and negligible overheads. With such an effective recovery mechanism,IterProcould tremendously mitigate the overheads and resource requirements of the resilience subsystem in future exa-scale systems.

The FAIR principles of open science (Findable, Accessible, Interoperable, and Reusable) have had transformative effects on modern large-scale computational science. In particular, they have encouraged more open access to and use of data, an important consideration as collaboration among teams of researchers accelerates and the use of workflows by those teams to solve problems increases. How best to apply the FAIR principles to workflows themselves, and software more generally, is not yet well understood. We argue that the software engineering concept of technical debt management provides a useful guide for application of those principles to workflows, and in particular that it implies reusability should be considered as ‘first among equals’. Moreover, our approach recognizes a continuum of reusability where we can make explicit and selectable the tradeoffs required in workflows for both their users and developers.To this end, we propose a new abstraction approach for reusable workflows, with demonstrations for both synthetic workloads and real-world computational biology workflows. Through application of novel systems and tools that are based on this abstraction, these experimental workflows are refactored to rightsize the granularity of workflow components to efficiently fill the gap between end-user simplicity and general customizability. Our work makes it easier to selectively reason about and automate the connections between trade-offs across user and developer concerns when exposing degrees of freedom for reuse. Additionally, by exposing fine-grained reusability abstractions we enable performance optimizations, as we demonstrate on both institutional-scale and leadership-class HPC resources.

Part of the promise of exascale computing and the next generation of scientific simulation codes is the ability to bring together time and spatial scales that have traditionally been treated separately. This enables creating complex coupled simulations and in situ analysis pipelines, encompassing such things as "whole device" fusion models or the simulation of cities from sewers to rooftops. Unfortunately, the HPC analysis tools that have been built up over the preceding decades are ill suited to the debugging and performance analysis of such computational ensembles. In this paper, we present a new vision for performance measurement and understanding of HPC codes, MonitoringAnalytics (MONA). MONA is designed to be a flexible, high performance monitoring infrastructure that can perform monitoring analysis in place or in transit by embedding analytics and characterization directly into the data stream, without relying upon delivering all monitoring information to a central database for post-processing. It addresses the trade-offs between the prohibitively expensive capture of all performance characteristics and not capturing enough to detect the features of interest. We demonstrate several uses of MONA; capturing and indexing multi-executable performance profiles to enable later processing, extraction of performance primitives to enable the generation of customizable benchmarks and performance skeletons, and extracting communication and application behaviors to enable better control and placement for the current and future runs of the science ensemble. Relevant performance information based on a system for MONA built from ADIOS and SOSflow technologies is provided for DOE science applications and leadership machines.

As processors continue to boost the system performance with higher circuit density, shrinking process technology and near-threshold voltage (NTV) operations, they are projected to be more vulnerable to transient faults, which have become one of the major concerns for future extreme-scale HPC systems. Despite being relatively infrequent, crashes due to transient faults are incredibly disruptive, particularly for massively parallel jobs on supercomputers where they potentially kill the entire job, requiring an expensive rerun or restart from a checkpoint.

With the growing computational complexity of science and the complexity of new and emerging hardware, it is time to re-evaluate the traditional monolithic design of computational codes. One new paradigm is constructing larger scientific computational experiments from the coupling of multiple individual scientific applications, each targeting their own physics, characteristic lengths, and/or scales. We present a framework constructed by leveraging capabilities such as in-memory communications, workflow scheduling on HPC resources, and continuous performance monitoring. This code coupling capability is demonstrated by a fusion science scenario, where differences between the plasma at the edges and at the core of a device have different physical descriptions. This infrastructure not only enables the coupling of the physics components, but it also connects in situ or online analysis, compression, and visualization that accelerate the time between a run and the analysis of the science content. Results from runs on Titan and Cori are presented as a demonstration.

Applications running on future high performance computing (HPC) systems are more likely to experience transient faults due to technology scaling trends with respect to higher circuit density, smaller transistor size and near-threshold voltage (NTV) operations. A transient fault could corrupt application state without warning, possibly leading to incorrect application output. Such errors are called silent data corruptions (SDCs).

Nonvolatile memory technologies (NVRAM) with larger capacity relative to DRAM and faster persistence relative to block-based storage technologies are expected to play a crucial role in accelerating I/O performance for HPC scientific workflows. Typically, a scientific workflow includes a simulation process (producer of data) and an analytics application process (consumer of data) that stream, share, and exchange data supported by an underlying OS-level file system. However, using an OS-level file system for data sharing adds substantial software overheads due to frequent system calls, journaling (for crash-consistency) cost, and file-system metadata update cost. To overcome these challenges, we design NVStream- a lightweight user-level data management system that exploits NVRAMs byte addressability and fast persistence to support streaming I/O in scientific workflows. First, NVStream reduces I/O-related software overheads by designing a memory-based persistent object store and log-structured heap manager that exploit NVRAM's large capacity. Second, NVStream incorporates a hardware-assisted non-temporal stores for crash-consistent updates at near hardware data copy (memory copy) speeds. Finally, NVStream reduces data written to NVRAM with a delta compression, which further reduces I/O cost for workflows with higher write locality. The evaluation of NVStream using I/O benchmarks and scientific applications demonstrates 10X reduction in I/O compared to NVRAM-optimized file systems and also guaranteeing crash-consistent data movement.

One of the core issues across computer and computational science today is adapting to, managing, and learning from the influx of "Big Data". In the commercial space, this problem has led to a huge investment in new technologies and capabilities that are well adapted to dealing with the sorts of human-generated logs, videos, texts, and other large-data artifacts that are processed and resulted in an explosion of useful platforms and languages (Hadoop, Spark, Pandas, etc.). However, translating this work from the enterprise space to the computational science and HPC community has proven somewhat difficult, in part because of some of the fundamental differences in type and scale of data and timescales surrounding its generation and use. We describe a forward-looking research and development plan which centers around the concept of making Input/Output (I/O) intelligent for users in the scientific community, whether they are accessing scalable storage or performing in situ workflow tasks. Much of our work is based on our experience with the Adaptable I/O System (ADIOS 1.X), and our next generation version of the software ADIOS 2.X [1].

As the memory and storage hierarchy get deeper and more complex, it is important to have new benchmarks and evaluation tools that allow us to explore the emerging middleware solutions to use this hierarchy. Skel is a tool aimed at automating and refining this process of studying HPC I/O performance. It works by generating application I/O kernel/benchmarks as determined by a domain-specific model. This paper provides some techniques for extending Skel to address new situations and to answer new research questions. For example, we document use cases as diverse as using Skel to troubleshoot I/O performance issues for remote users, refining an I/O system model, and facilitating the development and testing of a mechanism for runtime monitoring and performance analytics. We also discuss data oriented extensions to Skel to support the study of compression techniques for Exascale scientific data management.

In HPC applications, it is widely understood that in situ systems will play a significant role in next generation systems. The rate that next-generation leadership machines will be able to generate data will exceed the bandwidths of the planned I/O systems, leading to a need for in situ processing of the resulting data to reduce it. There have been a number of techniques proposed for in situ workflow systems; we are concerned here specifically with the needs of publish/subscribe or streaming-based approaches, which allow the in situ system to be composed of completely separate executables running concurrently on the hardware. In this paper we introduce an abstract known as a Weir. A weir is a useful mechanism to control state in a point to point streaming workflow in the absence of a third party publish subscribe system.

In-situ analysis on the output data of scientific simulations has been made necessary by ever-growing output data volumes and increasing costs of data movement as supercomputing is moving towards exascale. With hardware accelerators like GPUs becoming increasingly common in high end machines, new opportunities arise to co-locate scientific simulations and online analysis performed on the scientific data generated by the simulations. However, the asynchronous nature of GPGPU programming models and the limited context-switching capabilities on the GPU pose challenges to co-locating the scientific simulation and analysis on the same GPU. This paper dives deeper into these challenges to understand how best to co-locate analysis with scientific simulations on the GPUs in HPC clusters. Specifically, our 'Landrush' approach to GPU sharing proposes a solution that utilizes idle cycles on the GPU to provide an improved time-to-answer, that is, the total time to run the scientific simulation and analysis of the generated data. Landrush is demonstrated with experimental results obtained from leadership high-end applications on ORNL's Titan supercomputer, which show that (i) GPU-based scientific simulations have varying degrees of idle cycles to afford useful analysis task co-location, and (ii) the inability to context switch on the GPU at instruction granularity can be overcome by careful control of the analysis kernel launches and software-controlled early completion of analysis kernel executions. Results show that Landrush is superior in terms of time-to-answer compared to serially running simulations followed by analysis or by relying on the GPU driver and hardwired thread dispatcher to run analysis concurrently on a single GPU.

This poster describes our work on SuperGlue, a set of generic, reusable components for composing scientific workflows. These are distributed data analysis and manipulation tools that can be chained together to form a variety of real-time workflows providing analytical results during the execution of the primary scientific code. Unlike existing components used in IAWs, SuperGlue components do not have a fixed data type. This one change enables using these components on completely different kinds of simulations that share nothing in their output format. Key to making this work is using a typed transport mechanism between different components. Many options exist for these transports and the particular mechanism selected is not critical.

A key trend facing extreme-scale computational science is the widening gap between computational and I/O rates, and the challenge that follows is how to best gain insight from simulation data when it is increasingly impractical to save it to persistent storage for subsequent visual exploration and analysis. One approach to this challenge is centered around the idea of in situ processing, where visualization and analysis processing is performed while data is still resident in memory. This paper examines several key design and performance issues related to the idea of in situ processing at extreme scale on modern platforms: scalability, overhead, performance measurement and analysis, comparison and contrast with a traditional post hoc approach, and interfacing with simulation codes. We illustrate these principles in practice with studies, conducted on large-scale HPC platforms, that include a miniapplication and multiple science application codes, one of which demonstrates in situ methods in use at greater than 1M-way concurrency.

As scientific simulation applications evolve on the path towards exascale, a new model of scientific inquiry is required where concurrently with the running simulation, online analytics operate on the data it produces. By avoiding offline data storage except when absoluately necessary, it enables speeding up the scientific discovery process by providing rapid insights into the simulated science phenomena and affording more frequent, detailed data analytics than is possible with the traditional purely offline approach of using disk for intermediate data storage. However, a challenge for online analytics is to respond to behavior dynamics caused by changing simulation outputs and by unforeseen events on the underlying hardware/software platforms. This paper presents SODA, a set of run-time abstractions for online orchestration of data analytics, realized by embedding analytics tasks into workstations that monitor component behavior and enable responses to run-time changes in their resource demands and in the platform's resource availability. For high end simulations running on a leadership class machine, experimental evaluations show SODA can invoke efficient orchestration operations responding to a diverse set of run-time dynamics at different granularities to meet end-user and analysis specific requirements.

As high-end systems move toward exascale sizes, a new model of scientific inquiry being developed is one in which online data analytics run concurrently with the high end simulations producing data outputs. Goals are to gain rapid insights into the ongoing scientific processes, assess their scientific validity, and/or initiate corrective or supplementary actions by launching additional computations when needed. The Flex path system presented in this paper addresses the fundamental problem of how to structure and efficiently implement the communications between high end simulations and concurrently running online data analytics, the latter comprised of componentized dynamic services and service pipelines. Using a type-based publish/subscribe approach, Flexpath encourages diversity by permitting analytics services to differ in their computational and scaling characteristics and even in their internal execution models. Flex path uses direct and MxN connections between interacting services to reduce data movements, to allow for runtime connectivity changes to accommodate component arrivals/departures, and to support the multiple underlying communication protocols used for analytics workflows in which simulation outputs are processed by analytics services residing on the same nodes where they are generated, on the same machine, and/or on attached or remote analytics engines. This paper describes the design and implementation of Flex path, and evaluates it with two widely used scientific applications and their associated data analytics methods.

Collaborative science demands global sharing of scientific data. But it cannot leverage universally accessible cloud-based infrastructures like Drop Box, as those offer limited interfaces and inadequate levels of access bandwidth. We present the Scibox cloud facility for online sharing scientific data. It uses standard cloud storage solutions, but offers a usage model in which high end codes can write/read data to/from the cloud via the APIs they already use for their I/O actions. With Scibox, data upload/download volumes are controlled via Data Reduction-functions stated by end users and applied at the data source, before data is moved, with further gains in efficiency obtained by combining DR-functions to move exactly what is needed by current data consumers. We evaluate Scibox with science applications and their representative data analytics - the GTS fusion and the combustion image processing - demonstrating the potential for ubiquitous data access with substantial reductions in network traffic.

The remote visual exploration of live data generated by scientific simulations is useful for scientific discovery, performance monitoring, and online validation for the simulation results. Online visualization methods are challenged, however, by the continued growth in the volume of simulation output data that has to be transferred from its source - the simulation running on the high end machine - to where it is analyzed, visualized, and displayed. A specific challenge in this context is limits in the communication bandwidth between data source(s) and sinks. Previous work places queries `near' data sources, exploiting their data reduction capabilities, but such work does not address the common scenario in which scientists make multiple different queries on the data being produced. This paper considers the general case in which science users are interested in different (sub)sets of the data produced by a high end simulation. We offer the FlexQuery online data query system that can deploy and execute data queries `along' the I/O and analytics pipelines. FlexQuery carefully extends such analytics pipelines, using online performance monitoring and data location tracking, to realize data queries in ways that minimize additional data movement and offer low latency in data query execution. Using a real-world scientific application - the Maya astrophysics code and its analytics workflow - we demonstrate FlexQuery's ability to dynamically deploy queries for low-latency remote data visualization.

Increasingly severe I/O bottlenecks on High-End Computing machines are prompting scientists to process simulation output data online while simulations are running and before storing data on disk. There are several options to place data analytics along the I/O path: on compute nodes, on separate nodes dedicated to analytics, or after data is stored on persistent storage. Since different placements have different impact on performance and cost, there is a consequent need for flexibility in the location of data analytics. The FlexIO middleware described in this paper makes it easy for scientists to obtain such flexibility, by offering simple abstractions and diverse data movement methods to couple simulation with analytics. Various placement policies can be built on top of FlexIO to exploit the trade-offs in performing analytics at different levels of the I/O hierarchy. Experimental results demonstrate that FlexIO can support a variety of simulation and analytics workloads at large scale through flexible placement options, efficient data movement, and dynamic deployment of data manipulation functionalities.

Severe I/O bottlenecks on High End Computing platforms call for running data analytics in situ. Demonstrating that there exist considerable resources in compute nodes un-used by typical high end scientific simulations, we leverage this fact by creating an agile runtime, termed GoldRush, that can harvest those otherwise wasted, idle resources to efficiently run in situ data analytics. GoldRush uses fine-grained scheduling to "steal" idle resources, in ways that minimize interference between the simulation and in situ analytics. This involves recognizing the potential causes of on-node resource contention and then using scheduling methods that prevent them. Experiments with representative science applications at large scales show that resources harvested on compute nodes can be leveraged to perform useful analytics, significantly improving resource efficiency, reducing data movement costs incurred by alternate solutions, and posing negligible impact on scientific simulations.

As parallel execution platforms continue to proliferate, there is a growing need for real-time introspection tools to provide insight into platform behavior for performance debugging, correctness checks, and to drive effective resource management schemes. To address this need, we present the Lynx dynamic instrumentation system. Lynx provides the capability to write instrumentation routines that are (1) selective, instrumenting only what is needed, (2) transparent, without changes to the applications' source code, (3) customizable, and (4) efficient. Lynx is embedded into the broader GPU Ocelot system, which provides run-time code generation of CUDA programs for heterogeneous architectures. This paper describes (1) the Lynx framework and implementation, (2) its language constructs geared to the Single Instruction Multiple Data (SIMD) model of data-parallel programming used in current general-purpose GPU (GPGPU) based systems, and (3) useful performance metrics described via Lynx's instrumentation language that provide insights into the design of effective instrumentation routines for GPGPU systems. The paper concludes with a comparative analysis of Lynx with existing GPU profiling tools and a quantitative assessment of Lynx's instrumentation performance, providing insights into optimization opportunities for running instrumented GPU kernels.

Large scale applications are generating a tsunami of data, with understanding driven by finding information hidden within this data. The ever-increasing sizes of output, however, are making it difficult for science users to inspect the data generated by their applications, understand its important properties, and/or organize it for subsequent analysis and visualization. This paper presents JITStager, a software infrastructure with which end users can dynamically customize and thus, add value to the output pipelines of their HEC applications. JITStager is able to customize data at scale, by leveraging the computational power of both compute nodes and of additional `data staging' nodes allocated by end users. Using existing, componentized I/O interfaces to decouple the compile-time specification of the program and the run-time customization of the data pipeline, JITStager employs efficient runtime methods for binary code generation and data movement to create custom pipelines for applications' output processes that provide end users with improved insights into the data being produced, without burdening the application's computational performance and without impeding output performance. This paper describes the JITStager architecture, evaluates its performance, and demonstrates the advantages derived from its use with representative HPC applications.

Known challenges for petascale machines are that (1) the costs of I/O for high performance applications can be substantial, especially for output tasks like checkpointing, and (2) noise from I/O actions can inject undesirable delays into the runtimes of such codes on individual compute nodes. This paper introduces the flexible 'DataStager' framework for data staging and alternative services within that jointly address (1) and (2). Data staging services moving output data from compute nodes to staging or I/O nodes prior to storage are used to reduce I/O overheads on applications' total processing times, and explicit management of data staging offers reduced perturbation when extracting output data from a petascale machine's compute partition. Experimental evaluations of DataStager on the Cray XT machine at Oak Ridge National Laboratory establish both the necessity of intelligent data staging and the high performance of our approach, using the GTC fusion modeling code and benchmarks running on 1000+ processors.

Abstract IQ‐Services are application‐specific, resource‐aware code modules executed by data transport middleware. They constitute a ‘thin’ layer between application components and the underlying computational and communication resources. This layer implements the data manipulations necessary to permit wide‐area collaborations to proceed smoothly in the presence of dynamic resource variations. IQ‐Services interact with the application and resource layers via dynamic performance attributes, and end‐to‐end implementations of such attributes also permit clients to interact with data providers. The joint middleware/resource and provider/consumer interactions implemented with performance attributes may be used to realize effective methods for managing the data flows in the large‐data, distributed Grid applications targeted by our research. Experimental results in this paper demonstrate substantial performance improvements. These are attained by coordinating network‐level with service‐level adaptations of the data being transported and by permitting end users to dynamically deploy and use application‐specific services for manipulating data in ways suitable for their current needs. Copyright © 2005 John Wiley & Sons, Ltd.

Most systems must evolve as their missions or roles change and/or as they adapt to new execution environments. When evolving large distributed applications, it is particularly difficult to make changes to the data formats that underlie their components' communications, because such 'format evolution' can affect all or many application components. Prior approaches to the problem of implementing changes in the communications of a deployed system have relied upon ad-hoc solutions or on protocol negotiation to avoid message format mismatches. Unfortunately, such solutions tend to increase the complexity of application code. This paper presents a novel approach to the problem of data format evolution that combines meta-data about the data being exchanged with dynamic binary code generation to create a robust data exchange system that naturally supports application evolution. The idea is to specialize the communications of application components by dynamically generating the code that can automatically transform incoming data into forms that receiving components can understand. A realistic example in the context of publish/subscribe middleware is used to illustrate how this technique can be applied to enhance interoperability between different version of distributed applications

We consider distributed applications that continuously stream data across the network, where data needs to be aggregated and processed to produce a 'useful' stream of updates. Centralized approaches to performing data aggregation suffer from high communication overheads, lack of scalability, and unpredictably high processing workloads at central servers. This paper describes a scalable and efficient solution to distributed stream management based on (1) resource-awareness, which is middleware-level knowledge of underlying network and processing resources, (2) overlay-based in-network data aggregation, and (3) high-level programming constructs to describe data-flow graphs for composing useful streams. Technical contributions include a novel algorithm based on resource-aware network partitioning to support dynamic deployment of dataflow graph components across the network, where efficiency of the deployed overlay is maintained by making use of partition-level resource-awareness. Contributions also include efficient middleware-based support for component deployment, utilizing runtime code generation rather than interpretation techniques, thereby addressing both high performance and resource-constrained applications. Finally, simulation experiments and benchmarks attained with actual operational data corroborate this paper's claims.

Modern computational science applications are becoming increasingly multidisciplinary, involving widely distributed research teams and their underlying computational platforms. A common problem for the grid applications used in these environments is the necessity to couple multiple, parallel subsystems, with examples ranging from data exchanges between cooperating, linked parallel programs, to concurrent data streaming to distributed storage engines. This work presents the XChange/sub mxn/ middleware infrastructure for coupling componentized distributed applications. XChange/sub mxn/ implements the basic functionality of well-known services like the CCA Forum's MxN project, by providing efficient data redistribution across parallel application components. Beyond such basic functionality, however, XChange/sub mxn/ also addresses two of the problems faced by wide area scientific collaborations, which are (1) the need to deal with dynamic application/component behaviors, such as dynamic arrivals and departures due to the availability of additional resources, and (2) the need to 'match' data formats across disparate application components and research teams. In response to these needs, XChange/sub mxn/ uses an anonymous publish/subscribe model for linking interacting components, and the data being exchanged is dynamically specialized and transformed to match end point requirements. The pub/sub paradigm makes it easy to deal with dynamic component arrivals and departures. Dynamic data transformation enables the 'inflight' correction of data or needs mismatches for cooperating components. This work describes the design and implementation of XChange/sub mxn/, and it evaluates its implementation compared to those of less flexible transports like MPI. It also highlights the utility ofXChange/sub mxn/'s 'inflight' data specialization, by applying it to the SmartPointer parallel data visualization environment developed at our institution. Interestingly, using XChange/sub mxn/ did not significantly affect performance but led to a reduction in the size of the code base.

Summary form only given. Heterogeneous computing platforms constitute a challenging execution environment for distributed applications. This article presents a 'systems' view of effective platform usage, by demonstrating the need for application software to be continuously 'aware' of the resources currently available on their underlying heterogeneous computing platforms. Our approach to the implementation of resource awareness is one that (1) provides a 'thin' middleware layer of resource aware services that permit applications to react to changes in resource availability and resources to be managed in accordance with application needs, and that (2) develops compiler- and application-level techniques for dynamic 'service morphing', the goal being to make it easy for application-level services to adjust to runtime changes in application needs or in platform resources. The specific results presented in this article are focused on large-data applications, for which the IQ-services "morphing" layer implements the data manipulations necessary to permit wide-area interactive or multimedia applications to proceed smoothly despite variations in underlying computing and network resources. Experimental results demonstrate substantial performance improvements attained by coordinating network-level with service-level adaptations of the data being transported and by permitting end users to dynamically deploy and use application-specific services for manipulating data in ways suitable for their current needs.

New trends in high-performance software development such as tool- and component-based approaches have increased the need for flexible and high-performance communication systems. When trying to reap the well-known benefits of these approaches, the question of what communication infrastructure should be used to link the various components arises. In this context, flexibility and high-performance seem to be incompatible goals. Traditional HPC-style communication libraries, such as MPI, offer good performance, but are not intended for loosely-coupled systems. Object- and metadata-based approaches like XML offer the needed plug-and-play flexibility, but with significantly lower performance. We observe that the flexibility and baseline performance of data exchange systems are strongly determined by their wire formats, or by how they represent data for transmission in heterogeneous environments. After examining the performance implications of using a number of different wire formats, we propose an alternative approach for flexible high-performance data exchange, Native Data Representation, and evaluate its current implementation in the portable binary I/O library.

Summary form only given. An increasing number of distributed applications aim to provide services to users by interacting with a correspondingly growing set of data-intensive network services. To support such requirements, we believe that new services need to be customizable, applications need to be dynamically extensible, and both applications and services need to be able to adapt to variations in resource availability and demand. A comprehensive approach to building new distributed applications can facilitate this by considering the contents of the information flowing across the application and its services and by adopting a component-based model to application/service programming. It should provide for dynamic adaptation at multiple levels and points in the underlying platform; and, since the mapping of components to resources in dynamic environment is too complicated, it should relieve programmers of this task. We propose Active Streams, a middleware approach and its associated framework for building distributed applications and services that exhibit these characteristics.

The explosive growth of the Internet, with the emergence of new networking technologies and the increasing number of network-capable end devices, is paving the way for a number of novel distributed applications and services. Cooperative distributed systems have become a common computing model, and pervasive computing has caught the interest of academia and industry. To support future network applications, we believe that new services need to be customizable, applications need to be dynamically extensible, and both applications and services should be able to adapt to variations in resource availability and demand. propose Active Streams (F.E. Bustamante and K. Schwan, 1999), a middleware approach and its associated framework for building distributed applications and services that exhibit these characteristics.

High-performance computing faces considerable change as the Internet and the Grid mature. Applications that once were tightly-coupled and monolithic are now decentralized, with collaborating components spread across diverse computational elements. Such distributed systems most commonly communicate through the exchange of structured data. Definition and translation of metadata is incorporated in all systems that exchange structured data. We observe that the manipulation of this metadata can be decomposed into three separate steps: discovery, binding of program objects to the metadata, and marshaling of data to and from wire formats. We have designed a method of representing message formats in XML, using datatypes available in the XML Schema specification. We have implemented a tool, XMIT that uses such metadata and exploits this decomposition in order to provide flexible run-time metadata definition facilities for an efficient binary communication mechanism. We also demonstrate that the use of XMIT makes possible such flexibility at little performance cost.

The definition and translation of metadata is incorporated in all systems that exchange structured data. We observe that the manipulation of this metadata can be decomposed into three separate steps: discovery, binding of program objects to the metadata, and marshaling of data to and from wire formats. We have designed a method of representing message formats in XML, using data types that are available in the XML schema specification. We have implemented a tool called xml2wire that uses such metadata and exploits this decomposition in order to provide flexible metadata definition facilities for an efficient binary communications mechanism. We also observe that the use of xml2wire makes possible such flexibility without intolerable performance effects.

This paper presents JECho, a Java-based communication infrastructure for collaborative high performance applications. JECho implements a publish/subscribe communication paradigm, permitting distributed concurrent sets of components to provide interactive service to collaborating end users via event channels. JECho's eager handler concept allows individual event subscribers to dynamically tailor event flows to adapt to runtime changes in component behaviors and needs, and to changes in platform resources. Benchmark results suggest that JECho may be used for building large-scale, high-performance event delivery systems which can efficiently adapt to changes in user needs or the environment using eager handlers.

The Configuration Toolkit (CTK) is a library for constructing configurable object based abstractions that are part of multiprocessor programs or operating systems. The library is unique in its exploration of runtime configuration for attaining performance improvements: 1) its programming model facilitates the expression and implementation of program configuration; and 2) its efficient runtime support enables performance improvements by the configuration of program components during their execution. Program configuration is attained without compromising the encapsulation or the reuse of software abstractions. CTK programs are configured using attributes associated with object classes, object instances, state variables, operations, and object invocations. At runtime, such attributes are interpreted by policy classes, which may be varied separately from the abstractions with which they are associated. Using policies and attributes, an object's runtime behavior may be varied by: 1) changing its performance or reliability while preserving the implementation of its functional behavior, or 2) changing the implementation of its internal computational strategy. CTK's multiprocessor implementation is layered on a Cthreads-compatible programming library, which results in its portability to a wide variety of uni- and multiprocessor machines, including a Kendall Square KSR-2 Supercomputer, SGI machines, various SUN workstations, and as a native kernel on the GP1000 BBN Butterfly multiprocessor. The platforms evaluated in the paper are the KSR and SGI machines.

The Internet and the Grid are changing the face of high-performance computing. Rather than tightly-coupled SPMD-style components running in a single cluster, on a parallel machine, or even on the Internet programmed in MPI, applications are evolving into sets of collaborating components scattered across diverse computational elements. These collaborating components may run on different operating systems and hardware platforms and may be written by different organizations in different languages. Complete "applications" are constructed by assembling these components in a plug-and-play fashion. This new vision for high-performance computing demands features and characteristics which are not easily provided by traditional high-performance communications middleware. In response to these needs, we have developed ECho, a high-performance event-delivery middleware that meets the new demands of the Grid environment. ECho provides efficient binary transmission of event data with unique features that support data-type discovery and enterprise-scale application evolution. We present measurements detailing ECho's performance to show that ECho significantly outperforms other systems intended to provide this functionality, and that it provides throughput and latency comparable to the most efficient middleware infrastructures available.

High performance computing is being increasingly utilized in non-traditional circumstances where it must interoperate with other applications. For example, online visualization is being used to monitor the progress of applications, and real-world sensors are used as inputs to simulations. Whenever these situations arise, there is a question of what communications infrastructure should be used to link the different components. Traditional HPC-style communications systems such as MPI offer relatively high performance, but are poorly suited for developing these less tightly-coupled cooperating applications. Object-based systems and meta-data formats like XML offer substantial plug-and-play flexibility, but with substantially lower performance. We observe that the flexibility and baseline performance of all these systems is strongly determined by their `wire format', or how they represent data for transmission in a heterogeneous environment. We examine the performance implications of different wire formats and present an alternative with significant advantages in terms of both performance and flexibility.

This research supports the interactive access to large-scale scientific data by creation of active user interfaces (AUIs). An AUI continuously emits events describing its current information needs, based on which methods may be developed for controlling the potentially immense information streams directed at the interface. More precisely the purposes of stream control are twofold. First, stream control is performed to deal with heterogeneity in underlying systems, where low end displays may receive only small portions of the data shown at high end displays. Second, stream control is used to achieve scalability with respect to the size and complexity of data streams directed at a user interface, by filtering the data stream and by offloading certain computations from the AUI to the information generators or to information routing sites, by dynamically migrating such computations to appropriate locations, and by adapting these computations in order to effect tradeoffs in the amount of data moved across network links vs. the computations required.

Advances in high performance computing, communications and user interfaces enable developers to construct increasingly interactive high performance applications. The Falcon system presented in this paper supports such interactivity by providing runtime libraries, tools and user interfaces that permit the on-line monitoring and steering of large-scale parallel codes. The principal aspects of Falcon described in this paper are its abstractions and tools for capture and analysis of application-specific program information, performed on-line, with controlled latencies and scalable to parallel machines of substantial size. In addition, Falcon provides support for the on-line graphical display of monitoring information, and it allows programs to be steered during their execution, by human users or algorithmically. This paper presents our basic research motivation, outlines the Falcon system's functionality, and includes a detailed evaluation of its performance characteristics in light of its principal contributions. Falcon's functionality and performance evaluation are driven by our experiences with large-scale parallel applications being developed with end users in physics and in atmospheric sciences. The sample application highlighted in this paper is a molecular dynamics simulation program (MD) used by physicists to study the statistical mechanics of liquids. © 1998 John Wiley & Sons, Ltd.

The paper focuses on the opportunities and costs of online steering as applied to a substantial parallel application. We demonstrate potential performance improvements through the use of the Falcon system, an experimental system for the online monitoring and steering of parallel programs. The visual presentation of program output along with animated displays of program performance information via Falcon's monitoring system enables the online capture, analysis, and display of program information required for program steering. Falcon also provides the mechanisms for the manipulations of program state that accomplish this online steering.>