Search NASA⌕ Search

SEARCH · Search NASA

Results for “Runtime Scheduling”

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.

At least 91 records · Page 5

Framework for Extensible, Asynchronous Task Scheduling (FEATS) in Fortran

Most parallel scientific programs contain compiler directives (pragmas) such as those from OpenMP, explicit calls to runtime library procedures such as those implementing the Message Passing Interface (MPI), or compiler-specific language extensions such as those provided by CUDA. By contrast, the recent Fortran standards empower developers to express parallel algorithms without directly referencing lower-level parallel programming models. Fortran’s parallel features place the language within the Partitioned Global Address Space (PGAS) class of programming models. When writing programs that exploit data-parallelism, application developers often find it straightforward to develop custom parallel algorithms. Problems involving complex, heterogeneous, staged calculations, however, pose much greater challenges. Such applications require careful coordination of tasks in a manner that respects dependencies prescribed by a directed acyclic graph. When rolling one’s own solution proves difficult, extending a customizable framework becomes attractive. The paper presents the design, implementation, and use of the Framework for Extensible Asynchronous Task Scheduling (FEATS), which we believe to be the first task-scheduling tool written in modern Fortran. We describe the benefits and compromises associated with choosing Fortran as the implementation language, and we propose ways in which future Fortran standards can best support the use case in this paper.

Modern Fortran↗

Coding the Computing Continuum: Fluid Function Execution in Heterogeneous Computing Environments

Advances in network technologies have greatly decreased barriers to accessing physically distributed computers. This newfound accessibility coincides with increasing hardware specialization, creating exciting new opportunities to dispatch workloads to the best resource for a specific purpose, rather than those that are closest or most easily accessible. We present Delta, a service designed to intelligently schedule function-based workloads across a distributed set of heterogeneous computing resources. Delta implements an extensible architecture in which different predictors and scheduling algorithms can be integrated to provide dynamically evolving estimates of function execution times on different resources-estimates that can be used to determine the most appropriate location for execution. We describe predictors for function runtime, data transfer time, and cold-start resource provisioning and configuration delay; dynamic learning methods that update predictor models over time; and scheduling strategies that take into account both function and endpoint information. We show that these methods can halve workload makespan when compared with a strategy that selects the fastest resource, and decrease makespan by a factor of five when compared to a round robin strategy, when deployed on a heterogeneous testbed with resources ranging from a Raspberry Pi to a GPU node in an academic cloud.

Computing continuum↗

Kokkos' Task DAG Capabilities.

This report documents the ASC/ATDM Kokkos deliverable "Production Portable Dy- namic Task DAG Capability." This capability enables applications to create and execute a dynamic task DAG ; a collection of heterogeneous computational tasks with a directed acyclic graph (DAG) of "execute after" dependencies where tasks and their dependencies are dynamically created and destroyed as tasks execute. The Kokkos task scheduler executes the dynamic task DAG on the target execution resource; e.g. a multicore CPU, a manycore CPU such as Intel's Knights Landing (KNL), or an NVIDIA GPU. Several major technical challenges had to be addressed during development of Kokkos' Task DAG capability: (1) portability to a GPU with it's simplified hardware and micro- runtime, (2) thread-scalable memory allocation and deallocation from a bounded pool of memory, (3) thread-scalable scheduler for dynamic task DAG, (4) usability by applications.

97 MATHEMATICS AND COMPUTING↗

Mastering HPC Runtime Prediction: From Observing Patterns to a Methodological Approach

The continual expansion of high-performance computing (HPC) brings with it an increasing need for efficiency. Heavy investment in energy, hardware, and software infrastructure to support peta- and exascale computing requires the optimization of existing systems and, wherever possible, the discernment and adoption of best-practices towards these goals. Such is the case for runtime prediction. When a job is submitted to an HPC system, an estimate of its runtime is provided by the user in the form of "requested wallclock". Error in this user-provided estimate can lead to jobs being prematurely killed by the scheduler, increased wait time on the queue, and decreased system utilization. More than fifteen years of research has been directed at mitigating these effects by using data-driven runtime predictions. Codified here is a set of commonalities and insights emerging from this body of work, which we present as recommendations and best practices. These practices are combined into a methodological approach described and evaluated on an 11-million-job dataset from the National Renewable Energy Laboratory's petascale HPC system, Eagle. This dataset and the accompanying codebase have been released to the public domain for the benefit of the wider HPC research community.

high performance computing↗

Mastering HPC Runtime Prediction: From Observing Patterns to a Methodological Approach: Preprint

The continual expansion of high-performance computing (HPC) brings with it an increasing need for efficiency. Heavy investment in energy, hardware, and software infrastructure to support peta- and exascale computing requires the optimization of existing systems and, wherever possible, the discernment and adoption of best-practices towards these goals. Such is the case for runtime prediction. When a job is submitted to an HPC system, an estimate of its runtime is provided by the user in the form of "requested wallclock''. Error in this user-provided estimate can lead to jobs being prematurely killed by the scheduler, increased wait time on the queue, and decreased system utilization. More than fifteen years of research has been directed at mitigating these effects by using data-driven runtime predictions. Codified here is a set of commonalities and insights emerging from this body of work, which we present as recommendations and best practices. These practices are combined into a methodological approach described and evaluated on an 11-million-job dataset from the National Renewable Energy Laboratory's petascale HPC system, Eagle. This dataset and the accompanying codebase have been released to the public domain for the benefit of the wider HPC research community.

high performance computing↗

A method to generate heating and cooling schedules based on data from connected thermostats

Internet-connected thermostats are a promising new source of temperature and operational data in homes because they record inside temperatures, setpoints, and HVAC runtimes every five minutes. Over 20 million Internet-connected thermostats have already been installed in American homes. Data from about 20,000 connected thermostats were collected and organized by climate zone, number of occupants, floor area, and day type. A method was developed to create up to 40 representative temperature schedules which, together, can more accurately capture the diversity of heating and cooling behaviors. These results are suitable for input into schedules for building energy simulation models. This information enables more realistic simulations of American heating and cooling behavior, leading to more accurate estimates of energy consumption and savings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Applying Machine Learning to Understand Write Performance of Large-scale Parallel Filesystems

In high-performance computing (HPC), I/O performance prediction offers the potential to improve the efficiency of scientific computing. In particular, accurate prediction can make runtime estimates more precise, guide users toward optimal checkpoint strategies, and better inform facility provisioning and scheduling policies. HPC I/O performance is notoriously difficult to predict and model, however, in large part because of inherent variability and a lack of transparency in the behaviors of constituent storage system components. In this work we seek to advance the state of the art in HPC I/O performance prediction by (1) modeling the mean performance to address high variability, (2) deriving model features from write patterns, system architecture and system configurations, and (3) employing Lasso regression model to improve model accuracy. We demonstrate the efficacy of our approach by applying it to a crucial subset of common HPC I/O motifs, namely, file-per-process checkpoint write workloads. We conduct experiments on two distinct production HPC platforms—Titan at the Oak Ridge Leadership Computing Facility and Cetus at the Argonne Leadership Computing Facility—to train and evaluate our models. We find that we can attain ≤ 30% relative error for 92.79% and 99.64% of the samples in our test set on these platforms, respectively.

Xie, Bing↗

Measured and Modeled Vineyard Canopy Development and Water Use

Two publicly available applications relevant to vineyard irrigation management are described. OpenET is a satellite-based system that applies an ensemble of remote sensing methods to enable wide-area monitoring of evapotranspiration (ET) and related measures such as vegetation canopy development (via the NDVI spectral index). Data are freely available at one-quarter acre spatial resolution, and may be automatically aggregated to the individual block level. The satellite-based daily ET data were compared with in-situ eddy covariance measurements collected by micro-meteorological instrumentation in a Central Coast vineyard over a three-year period (2020-2022). Estimation uncertainties were reasonably consistent with prior reports for GRAPEX sites in the Central Valley and North Coast. The CropManage (CM) web application is a free software tool developed and operated U.C. Cooperative Extension for ET-based irrigation scheduling of major specialty crops. CM provides specific guidance for irrigation events in terms of irrigation system runtime. Applied water recommendations are based largely on estimated ET, derived from assumed canopy cover and associated crop coefficients, since the last irrigation or rainfall event. The application was recently adapted to vineyards by accounting for presence of winter/spring cover crop, and vine water stress imposed by regulated deficit irrigation. A 2022 field campaign involved 12 Central Coast and San Joaquin Valley commercial vineyards, and OpenET data were used to help evaluate CM output. Maximum percent vine cover was compared to estimates derived from average July satellite NDVI. The difference for 10 sites lacking midseason groundcover ranged from 0-7% between datasets with average agreement near 4%. Cumulative ET estimates agreed with OpenET to within 12% at the majority of sites, while larger discrepancies at the remaining sites may require additional data collection and analysis during the 2023 season. Satellite based systems such as OpenET have the potential to help parameterize CropManage and similar agricultural decision-support systems.

Measured↗

IRIS Reimagined: Advancements in Intelligent Runtime System for Task-Based Programming

Task-based programming models are gaining traction in scientific computing. IRIS is a portable runtime system that exploits multiple heterogeneous programming systems and can discover available resources and manage multiple diverse programming systems (e.g., CUDA, Hexagon, HIP, Level Zero, OpenCL, and OpenMP) simultaneously. It accounts for the constraints of task dependencies and provides customizable scheduling policies to map those tasks to heterogeneous devices. In this paper, we present new capabilities added to IRIS to improve its portability for heterogeneous programming, build-friendliness, and performance efficiency. The new additions include vendor-specific kernel support, a runtime system with a foreign function interface to eliminate writing wrapper or boilerplate code for heterogeneous kernels, an easy-to-use and configurable CMake-based build environment, automatic and efficient data transfers and orchestration, and the Hunter and DAGGER toolchains to evaluate IRIS’s task scheduling algorithms.

Miniskar, Narasinga Rao↗

On the adequacy of lightweight thread approaches for high-level parallel programming models

High-level parallel programming models (PMs) are becoming crucial in order to extract the computational power of current on-node multi-threaded parallelism. The most popular PMs, such as OpenMP or OmpSs, are directive-based: the complexity of the hardware is hidden by the underlying runtime system, improving coding productivity. The implementations of OpenMP usually rely on POSIX threads (pthreads), offering excellent performance for coarse-grained parallelism and a perfect match with the current hardware. OmpSs is a task oriented PM based on an ad hoc runtime solution called Nanos++; it is the precursor of the tasking parallelism in the OpenMP tasking specification. A recent trend in runtimes and applications points to leveraging massive on-node parallelism in conjunction with fine-grained and dynamic scheduling paradigms. In this paper we analyze the behavior of the OpenMP and OmpSs PMs on top of the recently emerged Generic Lightweight Threads (GLT) API. GLT exposses a common API for lightweight thread (LWT) libraries that offers the possibility of running the same application over different native LWT solutions. We describe the design details of those high-level PMs implemented on top of GLT and analyze different scenarios in order to assess where the use of LWTs may benefit application performance. Our work reveals those scenarios where LWTs overperform pthread-based solutions and compares the performance between an ad hoc solution and a generic implementation.

97 MATHEMATICS AND COMPUTING↗

Mission Data System Java Edition Version 7

The Mission Data System framework defines closed-loop control system abstractions from State Analysis including interfaces for state variables, goals, estimators, and controllers that can be adapted to implement a goal-oriented control system. The framework further provides an execution environment that includes a goal scheduler, execution engine, and fault monitor that support the expression of goal network activity plans. Using these frameworks, adapters can build a goal-oriented control system where activity coordination is verified before execution begins (plan time), and continually during execution. Plan failures including violations of safety constraints expressed in the plan can be handled through automatic re-planning. This version optimizes a number of key interfaces and features to minimize dependencies, performance overhead, and improve reliability. Fault diagnosis and real-time projection capabilities are incorporated. This version enhances earlier versions primarily through optimizations and quality improvements that raise the technology readiness level. Goals explicitly constrain system states over explicit time intervals to eliminate ambiguity about intent, as compared to command-oriented control that only implies persistent intent until another command is sent. A goal network scheduling and verification process ensures that all goals in the plan are achievable before starting execution. Goal failures at runtime can be detected (including predicted failures) and handled by adapted response logic. Responses can include plan repairs (try an alternate tactic to achieve the same goal), goal shedding, ignoring the fault, cancelling the plan, or safing the system.

Reinholtz, William K.↗

Addressing Global Data Dependencies in Heterogeneous Asynchronous Runtime Systems on GPUs

Large-scale parallel applications with complex global data dependencies beyond those of reductions pose significant scalability challenges in an asynchronous runtime system. Internodal challenges include identifying the all-to-all communication of data dependencies among the nodes. Intranodal challenges include gathering together these data dependencies into usable data objects while avoiding data duplication. This paper addresses these challenges within the context of a large-scale, industrial coal boiler simulation using the Uintah asynchronous many-task runtime system on GPU architectures. We show significant reduction in time spent analyzing data dependencies through refinements in our dependency search algorithm. Multiple task graphs are used to eliminate subsequent analysis when task graphs change in predictable and repeatable ways. Using a combined data store and task scheduler redesign reduces data dependency duplication ensuring that problems fit within host and GPU memory. Furthermore, these modifications did not require any changes to application code or sweeping changes to the Uintah runtime system. We report results running on the DOE Titan system on 119K CPU cores and 7.5K GPUs simultaneously. Our solutions can be generalized to other task dependency problems with global dependencies among thousands of nodes which must be processed efficiently at large scale.

97 MATHEMATICS AND COMPUTING↗

Providing Runtime Clock Synchronization With Minimal Node-to-Node Time Deviation on XT4s and XT5s

We present a new high precision clock synchronization algorithm designed for large XT4 and XT5 leadership-class machines. The algorithm, which is designed to support OS noise reduction through co-scheduling, is suitable for usage cases requiring low overhead and minimal time deviation between nodes. Unlike most high-precision algorithms which reach their precision in a post-mortem analysis after the application has completed, the new ORNL developed algorithm rapidly provides precise results during runtime. Previous to our work, the leading high-precision clock synchronization algorithms that made results available during runtime relied on probabilistic schemes that are not guaranteed to result in an answer.

99 GENERAL AND MISCELLANEOUS↗

The SGI/Cray T3E: Experiences and Insights

The NASA Goddard Space Flight Center is home to the fifth most powerful supercomputer in the world, a 1024 processor SGI/Cray T3E-600. The original 512 processor system was placed at Goddard in March, 1997 as part of a cooperative agreement between the High Performance Computing and Communications Program's Earth and Space Sciences Project (ESS) and SGI/Cray Research. The goal of this system is to facilitate achievement of the Project milestones of 10, 50 and 100 GFLOPS sustained performance on selected Earth and space science application codes. The additional 512 processors were purchased in March, 1998 by the NASA Earth Science Enterprise for the NASA Seasonal to Interannual Prediction Project (NSIPP). These two "halves" still operate as a single system, and must satisfy the unique requirements of both aforementioned groups, as well as guest researchers from the Earth, space, microgravity, manned space flight and aeronautics communities. Few large scalable parallel systems are configured for capability computing, so models are hard to find. This unique environment has created a challenging system administration task, and has yielded some insights into the supercomputing needs of the various NASA Enterprises, as well as insights into the strengths and weaknesses of the T3E architecture and software. The T3E is a distributed memory system in which the processing elements (PE's) are connected by a low latency, high bandwidth bidirectional 3-D torus. Due to the focus on high speed communication between PE's, the T3E requires PE's to be allocated contiguously per job. Further, jobs will only execute on the user specified number of PE's and PE timesharing is possible but impractical. With a highly varied job mix in both size and runtime of jobs, the resulting scenario is PE fragmentation and an inability to achieve near 100% utilization. SGI/Cray has provided several scheduling and configuration tools to minimize the impact of fragmentation. These tools include PScheD (the political scheduler), GRM (the global resource manager) and NQE (the Network Queuing Environment). Features and impact of these tools will be discussed, as will resulting performance and utilization data. As a distributed memory system, the T3E is designed to be programmed through explicit message passing. Consequently, certain assumptions related to code design are made by the operating system (UNICOS/mk) and its scheduling tools. With the exception of HPF, which does run on the T3E, however poorly, alternative programming styles have the potential to impact the T3E in unexpected and undesirable ways. Several examples will be presented (preceeded with the disclaimer, "Don't try this at home! Violators will be prosecuted!")

Bernard, Lisa Hamet↗

Comfort in High-Performance Homes in a Hot-Humid Climate

TO5 2.3.2: Large-Scale Temperature Study Although space-conditioning systems are required to meet standards such as those in the Air Conditioning Contractors of America (ACCA) Manual RS (Rutkowski 1997) and the ASHRAE Standard 55 (ASHRAE 2013) comfort criteria, little is known about how space-conditioning systems are actually operating in the field and if these systems are meeting those standards. Unconventional space-conditioning systems may be necessary for low-load homes in the future. It is important to know how current systems are functioning in existing homes and to what temperatures occupants typically set the thermostats in their homes. The U.S. Department of Energy's Building America research team IBACOS set out to find some answers. By using low-cost data loggers and occupant surveys to monitor 37 single-family homes that have standard heating, ventilating, and air-conditioning (HVAC) equipment, the team gained insight into how sensitive occupants are to comfort in their homes relative to the ACCA and ASHRAE standards. This study focused on one climate zone (hot-humid); however, future studies may find differences among occupants- ideas of thermal comfort in other climate zones. Data were collected from installed sensors during a 2-month period from late August 2014 through late October 2014. The final aspect of this project was to review the business metrics associated with builders involved in a comfort and performance guarantee program. The results of this study-taken as an aggregate-show that the homes provided room-to-room temperature differences less than 6 degrees F 95% of the time. Temperature differences were less than 4 degrees F 80% of the time. Some homes showed better or worse performance. On average, two-story homes had a 3.3 degrees F temperature difference between rooms; single-story homes had an average of a 2.2 degrees F temperature difference between rooms. Occupants who did not use programmable thermostats had an average set point of 75 degrees F. Homes in which the thermostats were programmed with a setback schedule showed a median baseline temperature value of 74 degrees F and had a median afternoon setback of 75 degrees F. System runtime was analyzed and showed that the room-to-room temperature uniformity in some homes worsened during an on cycle, whereas the uniformity improved in other homes. That is, when the system was running, some rooms were receiving too much or too little air relative to the rest of the house, and the temperatures in those rooms were moving away from the temperatures of the other rooms in the house. Finally, analysis of the thermostat data shows a wide degree of variability among homes in the study. Interpretation of the measured data suggests that 21 occupants made no regular adjustments to the thermostats in their homes, seven had regular setbacks, seven showed varying setbacks, and 10 appeared to follow no pattern (with random adjustments). Ultimately, the data show that current systems are maintaining expected levels of comfort. As expected, it is more challenging to maintain a uniform temperature in all rooms of two-story homes, and future systems should address this issue. Furthermore, the data show that the majority of homes maintained relative humidity levels below 60% without any supplemental dehumidification

ACCA Manual RS↗

Vehicle routing for the last mile of power system restoration

This paper studied a novel problem in power system restoration: the Power Restoration Vehicle Routing Problem (PRVRP). The goal of PRVRPs is to decide how coordinate repair crews effectively in order to recover from blackouts as fast as possible after a disaster has occurred. PRVRPs are complex problems that combine vehicle routing and power restoration scheduling problems. The paper proposed a multi-stage optimization algorithm based on the idea of constraint injection that meets the aggressive runtime constraints necessary for disaster recovery. The algorithms were validated on benchmarks produced by the Los Alamos National Laboratory, using the infrastructure of the United States. The disaster scenarios were generated by state-of-the-art hurricane simulation tools similar to those used by the National Hurricane Center. Experimental results show that the constraint-injection algorithms can reduce the blackouts by 50% or more over field practices. Moreover, the results show that the constraint-injection algorithm using large neighborhood search over a blackbox simulator provide competitive quality and scales better than using a MIP solver on the subproblems.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Elastic distributed training with fast convergence and efficient resource utilization

Distributed learning is now routinely conducted on cloud as well as dedicated clusters. Training with elastic resources brings new challenges and design choices. Prior studies focus on runtime performance and assume a static algorithmic behavior. In this work, by analyzing the impact of of resource scaling on convergence, we introduce schedules for synchronous stochastic gradient descent that proactively adapt the number of learners to reduce training time and improve convergence. Our approach no longer assumes a constant number of processors throughout training. In our experiment, distributed stochastic gradient descent with dynamic schedules and reduction momentum achieves better convergence and significant speedups over prior static ones. Numerous distributed training jobs running on cloud may benefit from our approach.

Cong, Guojing↗

CIFO 3.0

The Ada Runtime Environment Working Group has, since 1985, developed and published the Catalog of Interface Features and Options (CFIO) for Ada runtime environments. These interfaces, expressed in legal Ada, provide 'hooks' into the runtime system to export both functionality and enhanced performance beyond that of 'vanilla' Ada implementations. Such enhancements include high- and low-level scheduling control, asynchronous communications facilities, predictable storage management facilities, and fast interrupt response. CIFO 3.0 represents the latest release, which incorporates the efforts of the European real time community as well as new interfaces and expansions of previous catalog entries. This presentation will give both an overview of the Catalog's contents and an 'insider's' view of the Catalog as a whole.

Rogers, Pat↗