Search NASA⌕ Search

SEARCH · Search NASA

Results for “asynchronous processing”

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 37 records · Page 2

Scaling NWChem with Efficient and Portable Asychronous Communication in MPI RMA

NWChem is one of the most widely used computational chemistry application suites for chemical and biological systems. Despite its vast success, the computational efficiency of NWChem is still low. This is especially true in higher accuracy methods such as the CCSD(T) coupled cluster method, where it currently achieves a mere 50% computational efficiency when run at large scales. In this paper, we demonstrate the most computationally efficient scaling of NWChem CCSD(T) to date, and use it to solve large water clusters. We use our recently proposed process-based asynchronous progress framework for MPI RMA, called Casper, to scale the computation on water clusters at near-100% computational efficiency on up to 12288 cores.

Si, Min↗

Techniques for Enabling Highly Efficient Message Passing on Many-Core Architectures

Many-core architecture provides a massively parallel environment with dozens of cores and hundreds of hardware threads. Scientific application programmers are increasingly looking at ways to utilize such large numbers of lightweight cores for various programming models. Efficiently executing these models on massively parallel many-core environments is not easy, however and performance may be degraded in various ways. The first author's doctoral research focuses on exploiting the capabilities of many-core architectures on widely used MPI implementations. While application programmers have studied several approaches to achieve better parallelism and resource sharing, many of those approaches still face communication problems that degrade performance. In the thesis, we investigate the characteristics of MPI on such massively threaded architectures and propose two efficient strategies -- a multi-threaded MPI approach and a process-based asynchronous model -- to optimize MPI communication for modern scientific applications.

Si, Min↗

STEMDL

The code "STEMDL" provides highly-optimized multi-gpu implementations of DL models of applicability in electron microscopy via the use of mixed-precision arithmetic, native graph construction and evaluation in Tensorflow, and adaptive scaling of learning parameters to avoid numerical instabilities due to reduced precision. STEMDL also uses low-level methods from the Horovod library for gradient communication and reduction and adds an additional optimization by allowing the user to scheduling the gradient reduction operations based on their position within the layers of a neural net. STEMDL provides optimized I/O routines for data staging and data reading/writing in both Tensorflow and Pytorch using multi-processing and asynchronous transfer between host and device. .

Laanait, Nouamane↗

Dissociation Dynamics and Electronic Structures of Highly Excited Ferrocenium Ions Studied by Femtosecond XUV Absorption Spectroscopy

In this work, the dissociation dynamics of ferrocene are explored following strong field ionization using femtosecond time-resolved extreme ultraviolet (XUV) transient absorption spectroscopy. Employing transitions in the vicinity of the iron 3p (M 2,3 ) edge, the dissociation is monitored from the point of view of the iron atom. With low strong field pump intensities (≈2 × 10 13 W cm -2 ), only ferrocenium cations are produced, and their iron 3p absorption spectrum is reported. It very closely resembles the 3p spectrum of atomic Fe + ions but is red-shifted by 0.8 eV. With the aid of time-dependent density functional theory calculations, the spectrum is assigned to a combination of doublet and quartet spin states of ferrocenium ions. Ionization with more intense strong field pump pulses (≥6 × 10 13 W cm –2 ) leads predominantly to the prompt production of ferrocenium ions that dissociate to give the spectral signature of bare Fe + ions within 240 ± 80 fs. Within the temporal resolution of the experiment (≈40 fs), no spectral intermediates are observed, suggesting that the dissociation process occurs directly from the excited ferrocenium ion and that the bonds between the iron center and both cyclopentadienyl rings are broken almost simultaneously in an asynchronous concerted decay process. Finally, no evidence of slower dissociation channels is observed at a pump–probe delay of 250 ps, suggesting that all energy is very rapidly routed into dissociative states.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Photodissociation dynamics of the tert -butyl perthiyl radical

Here, the photodissociation dynamics of the tert-butyl perthiyl (t-BuSS) radical are investigated by fast-beam coincidence translational spectroscopy. A fast (6 keV-8 keV) beam of neutral t-BuSS radicals is produced via photodetachment of the corresponding anion, followed by photodissociation at 248 nm (5.00 eV) or 193 nm (6.42 eV) and coincident detection of the neutral products. Photofragment mass and translational energy distributions are obtained at both wavelengths. At 248 nm, the dominant product channel (90%) is found to be S loss, with a product translational energy distribution that peaks close to the maximum available energy and an anisotropic photofragment angular distribution, indicating dissociation along a repulsive excited state. A minor channel (10%) leading to the formation of S 2 + t-Bu is also observed. At 193 nm, both two- and three-body dissociation are observed. The formation of S 2 + t-Bu is the dominant two-body product channel, with multiple electronic states of the S 2 molecule produced via excited-state dissociation processes. The formation of S + t-BuS is a minor two-body channel at this dissociation energy. The three-body channels are S 2 + H + isobutene, S 2 + CH 3 + propene, and S + SH + isobutene. The first two of these channels result from a sequential dissociation process in which the loss of S 2 from t-BuSS results in ground-state t-Bu with sufficient internal energy to undergo secondary fragmentation. The third three-body channel, S + SH + isobutene, is attributed to the loss of internally excited HS 2 from t-BuSS, which then rapidly dissociates to form S + SH in an asynchronous concerted dissociation process.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Highly scalable distributed-memory sparse triangular solution algorithms.

This paper presents a highly efficient distributed-memory parallel sparse triangular solver. The triangular solution phase is often performed following factorization phase in the sparse linear solvers and has become increasingly computa­tionally expensive for direct solvers with many right hand sides (RHSs) or preconditioned iterative solvers. However, the low arithmetic intensity and sequential nature of the triangular solve algorithm pose performance challenges for its large-scale distributed-memory parallelization. In this work, we propose several strategies to enhance scalability of an algorithm with 2D block cyclic process layout. First, an asynchronous binary-tree-based communication scheme implemented via non-blocking MPI functions is leveraged to broadcast partial solutions and reduce partial updates among a subset of processes for each block column and row of the triangular matrix, respectively. This scheme reduces message latency, improves communication load balance and significantly accelerates asynchronous execution of the triangular solve. In addition, efficient BLAS operations and threading implementations are exploited to accelerate local computations and further reduce process idle time. The proposed strategies are implemented in SuperLU_DIST and numerical experiments show up to 4.4x improvement with one right-hand side and up to 6.1x improvement with 50 right- hand sides on 4096 processes, compared to the current release. This is the first time that sparse triangular solution is demonstrated strong scaling on more than 4000 cores.

Liu, Yang↗

Towards an Intelligent Data Delivery Service

The ATLAS Event Streaming Service (ESS) at the LHC is an approach to preprocess and deliver data for Event Service (ES) that has implemented a fine-grained approach for ATLAS event processing. The ESS allows one to asynchronously deliver only the input events required by ES processing, with the aim to decrease data traffic over WAN and improve overall data processing throughput. A prototype of ESS was developed to deliver streaming events to fine-grained ES jobs. Based on it, an intelligent Data Delivery Service (iDDS) is under development to decouple the "cold format" and the processing format of the data, which also opens the opportunity to include the production systems of other HEP experiments. Here we will at first present the ESS model view and its motivations for iDDS system. Then we will also present the iDDS schema, architecture and the applications of iDDS.

97 MATHEMATICS AND COMPUTING↗

Modeling the asynchronous Jacobi method without communication delays

Asynchronous iterative methods for solving linear systems are gaining renewed interest due to the high cost of synchronization points in massively parallel codes. Historically, theory on asynchronous iterative methods has focused on asymptotic behavior, while the transient behavior remains poorly understood. In this paper, we study a model of the asynchronous Jacobi method without communication delays, which we call simplified asynchronous Jacobi. Simplified asynchronous Jacobi can be used to model asynchronous Jacobi implemented in shared memory or distributed memory with fast communication networks. Our analysis uses the idea of a propagation matrix, which is similar in concept to an iteration matrix. We show that simplified asynchronous Jacobi can continue to reduce the residual when some processes are slower than other processes. We also show that simplified asynchronous Jacobi can converge when synchronous Jacobi does not. We verify our analysis of simplified asynchronous Jacobi using results from asynchronous Jacobi implemented in shared and distributed memory.

97 MATHEMATICS AND COMPUTING↗

Building Scalable PGAS Communication Subsystem on Blue Gene/Q

This paper presents a design of scalable Partitioned Global Address Space (PGAS) communication subsystems on recently proposed Blue Gene/Q architecture. The proposed design provides an in-depth modeling of communication infrastructure using Parallel Active Messaging Interface (PAMI). The communication infrastructure is used to design time-space efficient communication protocols for frequently used data-types (contiguous, uniformly non-contiguous) using Remote Direct Memory Access (RDMA) get/put primitives. The proposed design accelerates load balance counters by using asynchronous threads, which are required due to the missing network hardware support for Atomic Memory Operations (AMOs). Under the proposed design, the synchronization traffic is reduced by tracking conflicting memory accesses in distributed space with slightly increment in space complexity. An evaluation with simple communication benchmarks show a adjacent node get latency of 2.89$\mu$s and peak bandwidth of 1775 MB/s resulting in $\approx$ 99\% communication efficiency.The evaluation shows a reduction in the execution time by up to 30\% for NWChem self consistent field calculation on 4096 processes using the proposed asynchronous thread based design.

Vishnu, Abhinav↗

Benchmark Tracking System for Performance Monitoring

Benchmarking is essential for high-performance software development, particularly for monitoring performance across code iterations. This project focused on enhancing the benchmarking process for Lamellar, an asynchronous runtime for High-Performance Computing (HPC) systems developed at Pacific Northwest National Laboratory. Prior to this work, benchmark results were difficult to track and compare across code versions, presenting significant challenges in identifying performance regressions and long-term trends. The primary objective was to establish a systematic, reproducible approach for measuring performance and detecting regressions following code commits. Our methodology involved three key components: standardizing benchmark outputs, implementing data versioning, and developing analysis tools. We standardized the benchmark output format to JSON Line records containing specific fields (execution time, hardware specifications, and environmental variables). To address data management challenges, we evaluated several options and eventually chose a git repository dedicated to benchmark data. We developed a suite of Python tools that processed benchmark results, enriched them with metadata, and facilitated search in the repository. The resulting system enables more efficient filtering and comparison of performance metrics across commit histories, hardware configurations, and benchmark variants through a unified query interface. Our implementation reduces computational overhead by first checking for existing results through configuration matching before initiating new benchmark runs, thereby conserving resources. The system has been validated by Lamellar developers. It organizes results by benchmark type and build configurations for efficient retrieval. Future developments include a planned Large Language Model interface for predicting benchmark performance, incorporating the criterion package for statistical analysis, which will enable automated detection of statistically significant performance changes, and integration with continuous integration pipelines. Despite these enhancements being reserved for future work, this project has successfully provided the Lamellar development team with a framework for maintaining consistent performance standards and identifying optimization opportunities across workloads and hardware environments.

97 MATHEMATICS AND COMPUTING↗

Designing a graphics processing unit accelerated petaflop capable lattice Boltzmann solver: Read aligned data layouts and asynchronous communication

The lattice Boltzmann method is a well-established numerical approach for complex fluid flow simulations. Recently, general-purpose graphics processing units (GPUs) have become available as high-performance computing resources at large scale. We report on designing and implementing a lattice Boltzmann solver for multi-GPU systems that achieves 1.79 PFLOPS performance on 16,384 GPUs. To achieve this performance, we introduce a GPU compatible version of the so-called bundle data layout and eliminate the halo sites in order to improve data access alignment. Furthermore, we make use of the possibility to overlap data transfer between the host central processing unit and the device GPU with computing on the GPU. As a benchmark case, we simulate flow in porous media and measure both strong and weak scaling performance with the emphasis being on large-scale simulations using realistic input data.

Computer Science↗

mdtmFTP and its evaluation on ESNET SDN testbed

In this paper, to address the high-performance challenges of data transfer in the big data era, we are developing and implementing mdtmFTP: a high-performance data transfer tool for big data. mdtmFTP has four salient features. First, it adopts an I/O centric architecture to execute data transfer tasks. Second, it more efficiently utilizes the underlying multicore platform through optimized thread scheduling. Third, it implements a large virtual file mechanism to address the lots-of-small-files (LOSF) problem. In conclusion, mdtmFTP integrates multiple optimization mechanisms, including–zero copy, asynchronous I/O, pipelining, batch processing, and pre-allocated buffer pools–to enhance performance. mdtmFTP has been extensively tested and evaluated within the ESNET 100G testbed. Evaluations show that mdtmFTP can achieve higher performance than existing data transfer tools, such as GridFTP, FDT, and BBCP.

97 MATHEMATICS AND COMPUTING↗

Continuing Efforts on Efficiency and Performance Improvement of mdtmFTP

mdtmFTP is a high-performance data transfer tool: • Pipelined I/O-centric design to streamline data transfer • Multicore-aware data transfer middleware (MDTM) optimizes use of underlying multicore system • Extremely efficient in transferring of Lots Of Small Files • Various optimization mechanisms including Asynchronous I/O and Batch processing. • Sponsored by DOE/SC/ASCR. http://mdtm.fnal.gov $\bullet$Continuing efforts on efficiency and Performance Improvement: • Refactoring event queue mechanism • I/O optimization • Scalability evaluation

Zhang, L.↗

An asynchronous traversal engine for graph-based rich metadata management

Rich metadata in high-performance computing (HPC) systems contains extended information about users, jobs, data files, and their relationships. Property graphs are a promising data model to represent heterogeneous rich metadata flexibly. Specifically, a property graph can use vertices to represent different entities and edges to record the relationships between vertices with unique annotations. The high-volume HPC use case, with millions of entities and relationships, naturally requires an out-of-core distributed property graph database, which must support live updates (to ingest production information in real time), low-latency point queries (for frequent metadata operations such as permission checking), and large-scale traversals (for provenance data mining). Among these needs, large-scale property graph traversals are particularly challenging for distributed graph storage systems. Most existing graph systems implement a "level synchronous" breadth-first search algorithm that relies on global synchronization in each traversal step. This performs well in many problem domains; but a rich metadata management system is characterized by imbalanced graphs, long traversal lengths, and concurrent workloads, each of which has the potential to introduce or exacerbate stragglers (i.e., abnormally slow steps or servers in a graph traversal) that lead to low overall throughput for synchronous traversal algorithms. Previous research indicated that the straggler problem can be mitigated by using asynchronous traversal algorithms, and many graph-processing frameworks have successfully demonstrated this approach. Such systems require the graph to be loaded into a separate batch-processing framework instead of being iteratively accessed, however. In this work, we investigate a general asynchronous graph traversal engine that can operate atop a rich metadata graph in its native format. We outline a traversal-aware query language and key optimizations (traversal-affiliate caching and execution merging) necessary for efficient performance. We further explore the effect of different graph partitioning strategies on the traversal performance for both synchronous and asynchronous traversal engines. Our experiments show that the asynchronous graph traversal engine is more efficient than its synchronous counterpart in the case of HPC rich metadata processing, where more servers are involved and larger traversals are needed. Furthermore, the asynchronous traversal engine is more adaptive to different graph partitioning strategies.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Implementing asyncronous collective operations in a multi-node processing system

A method, system, and computer program product are disclosed for implementing an asynchronous collective operation in a multi-node data processing system. In one embodiment, the method comprises sending data to a plurality of nodes in the data processing system, broadcasting a remote get to the plurality of nodes, and using this remote get to implement asynchronous collective operations on the data by the plurality of nodes. In one embodiment, each of the nodes performs only one task in the asynchronous operations, and each nodes sets up a base address table with an entry for a base address of a memory buffer associated with said each node. In another embodiment, each of the nodes performs a plurality of tasks in said collective operations, and each task of each node sets up a base address table with an entry for a base address of a memory buffer associated with the task.

97 MATHEMATICS AND COMPUTING↗

Scalable Data Management of the Uintah Simulation Framework for Next-Generation Engineering Problems with Radiation

The need to scale next-generation industrial engineering problems to the largest computational platforms presents unique challenges. This paper focuses on data management related problems faced by the Uintah simulation framework at a production scale of 260K processes. Uintah provides a highly scalable asynchronous many-task runtime system, which in this work is used for the modeling of a 1000 megawatt electric (MWe) ultra-supercritical (USC) coal boiler. At 260K processes, we faced both parallel I/O and visualization related challenges, e.g., the default file-per-process I/O approach of Uintah did not scale on Mira. In this paper we present a simple to implement, restructuring based parallel I/O technique. We impose a restructuring step that alters the distribution of data among processes. The goal is to distribute the dataset such that each process holds a larger chunk of data, which is then written to a file independently. This approach finds a middle ground between two of the most common parallel I/O schemes–file per process I/O and shared file I/O–in terms of both the total number of generated files, and the extent of communication involved during the data aggregation phase. To address scalability issues when visualizing the simulation data, we developed a lightweight renderer using OSPRay, which allows scientists to visualize the data interactively at high quality and make production movies. Finally, this work presents a highly efficient and scalable radiation model based on the sweeping method, which significantly outperforms previous approaches in Uintah, like discrete ordinates. The integrated approach allowed the USC boiler problem to run on 260K CPU cores on Mira.

97 MATHEMATICS AND COMPUTING↗

Automated high-throughput flow-through real-time diagnostic system

An automated real-time flow-through system capable of processing multiple samples in an asynchronous, simultaneous, and parallel fashion for nucleic acid extraction and purification, followed by assay assembly, genetic amplification, multiplex detection, analysis, and decontamination. The system is able to hold and access an unlimited number of fluorescent reagents that may be used to screen samples for the presence of specific sequences. The apparatus works by associating extracted and purified sample with a series of reagent plugs that have been formed in a flow channel and delivered to a flow-through real-time amplification detector that has a multiplicity of optical windows, to which the sample-reagent plugs are placed in an operative position. The diagnostic apparatus includes sample multi-position valves, a master sample multi-position valve, a master reagent multi-position valve, reagent multi-position valves, and an optical amplification/detection system.

47 OTHER INSTRUMENTATION↗

Asynchronous communication in spectral-element and discontinuous Galerkin methods for atmospheric dynamics – a case study using the High-Order Methods Modeling Environment (HOMME-homme_dg_branch)

The scalability of computational applications on current and next-generation supercomputers is increasingly limited by the cost of inter-process communication. We implement non-blocking asynchronous communication in the High-Order Methods Modeling Environment for the time integration of the hydrostatic fluid equations using both the spectral-element and discontinuous Galerkin methods. This allows the overlap of computation with communication, effectively hiding some of the costs of communication. A novel detail about our approach is that it provides some data movement to be performed during the asynchronous communication even in the absence of other computations. This method produces significant performance and scalability gains in large-scale simulations.

58 GEOSCIENCES↗