Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “asynchronously parallel”

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
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Integrating ytopt and libEnsemble to autotune OpenMC

Ytopt is a Python machine-learning-based autotuning software package developed within the ECP PROTEAS-TUNE project. The ytopt software adopts an asynchronous search framework that consists of sampling a small number of input parameter configurations and progressively fitting a surrogate model over the input-output space until exhausting the user-defined maximum number of evaluations or the wall-clock time. libEnsemble is a Python toolkit for coordinating workflows of asynchronous and dynamic ensembles of calculations across massively parallel resources developed within the ECP PETSc/TAO project. libEnsemble helps users take advantage of massively parallel resources to solve design, decision, and inference problems and expands the class of problems that can benefit from increased parallelism. In this paper we present our methodology and framework to integrate ytopt and libEnsemble to take advantage of massively parallel resources to accelerate the autotuning process. Specifically, we focus on using the proposed framework to autotune the ECP ExaSMR application OpenMC, an open source Monte Carlo particle transport code. OpenMC has seven tunable parameters some of which have large ranges such as the number of particles in-flight, which is in the range of 100,000 to 8 million, with its default setting of 1 million. Setting the proper combination of these parameter values to achieve the best performance is extremely time-consuming. Therefore, we apply the proposed framework to autotune the MPI/OpenMP offload version of OpenMC based on a user-defined metric such as the figure of merit (FoM) (particles/s) or energy efficiency energy-delay product (EDP) on Crusher at Oak Ridge Leadership Computing Facility. In conclusion, the experimental results show that we achieve the improvement up to 29.49% in FoM and up to 30.44% in EDP.

Autotuning↗
NASA NTRS1996

Distributed Large Data-Object Environments: End-to-End Performance Analysis of High Speed Distributed Storage Systems in Wide Area ATM Networks

We have developed and deployed a distributed-parallel storage system (DPSS) in several high speed asynchronous transfer mode (ATM) wide area networks (WAN) testbeds to support several different types of data-intensive applications. Architecturally, the DPSS is a network striped disk array, but is fairly unique in that its implementation allows applications complete freedom to determine optimal data layout, replication and/or coding redundancy strategy, security policy, and dynamic reconfiguration. In conjunction with the DPSS, we have developed a 'top-to-bottom, end-to-end' performance monitoring and analysis methodology that has allowed us to characterize all aspects of the DPSS operating in high speed ATM networks. In particular, we have run a variety of performance monitoring experiments involving the DPSS in the MAGIC testbed, which is a large scale, high speed, ATM network and we describe our experience using the monitoring methodology to identify and correct problems that limit the performance of high speed distributed applications. Finally, the DPSS is part of an overall architecture for using high speed, WAN's for enabling the routine, location independent use of large data-objects. Since this is part of the motivation for a distributed storage system, we describe this architecture.

Johnston, William↗
DOE OSTI2020

Scalable All-pairs Shortest Paths for Huge Graphs on Multi-GPU Clusters

We present an optimized Floyd-Warshall (Floyd-Warshall) algorithm that computes the All-pairs shortest path (APSP) for GPU accelerated clusters. The Floyd-Warshall algorithm due to its structural similarities to matrix-multiplication is well suited for highly parallel GPU architectures. To achieve high parallel efficiency, we address two key algorithmic challenges: reducing high communication overhead and addressing limited GPU memory. To reduce high communication costs, we redesign the parallel (a) to expose more parallelism, (b) aggressively overlap communication and computation with pipelined and asynchronous scheduling of operations, and (c) tailored MPI-collective. To cope with limited GPU memory, we employ an offload model, where the data resides on the host and is transferred to GPU on-demand. The proposed optimizations are supported with detailed performance models for tuning. Our optimized parallel Floyd-Warshall implementation is up to 5x faster than a strong baseline and achieves 8.1 PetaFLOPS/sec on 256~nodes of the Summit supercomputer at Oak Ridge National Laboratory. This performance represents 70% of the theoretical peak and 80% parallel efficiency. The offload algorithm can handle 2.5x larger graphs with a 20% increase in overall running time.

Sao, Piyush↗
DOE OSTI2023

Fast tree-based algorithms for DBSCAN for low-dimensional data on GPUs

DBSCAN is a well-known density-based clustering algorithm to discover arbitrary shape clusters. While conceptually simple in serial, the algorithm is challenging to efficiently parallelize on manycore GPU architectures. Common pitfalls, such as asynchronous range query calls, result in high thread execution divergence in many implementations. In this paper, we propose a new framework for GPU-accelerated DBSCAN, and describe two tree-based algorithms within that framework. Both algorithms fuse the search for neighbors with updating cluster information, but differ in their treatment of dense regions of the data. We show that the time taken to compute clusters is at most twice that of determination of the neighbors. We compare the proposed algorithms with existing CPU and GPU implementations, and demonstrate their competitiveness and performance using a fast traversal structure (bounding volume hierarchy) for low dimensional data. We also show that the memory usage can be reduced by processing object neighbors dynamically without storing them.

Prokopenko, Andrey↗
NASA NTRS2012

High-Performance, Multi-Node File Copies and Checksums for Clustered File Systems

Modern parallel file systems achieve high performance using a variety of techniques, such as striping files across multiple disks to increase aggregate I/O bandwidth and spreading disks across multiple servers to increase aggregate interconnect bandwidth. To achieve peak performance from such systems, it is typically necessary to utilize multiple concurrent readers/writers from multiple systems to overcome various singlesystem limitations, such as number of processors and network bandwidth. The standard cp and md5sum tools of GNU coreutils found on every modern Unix/Linux system, however, utilize a single execution thread on a single CPU core of a single system, and hence cannot take full advantage of the increased performance of clustered file systems. Mcp and msum are drop-in replacements for the standard cp and md5sum programs that utilize multiple types of parallelism and other optimizations to achieve maximum copy and checksum performance on clustered file systems. Multi-threading is used to ensure that nodes are kept as busy as possible. Read/write parallelism allows individual operations of a single copy to be overlapped using asynchronous I/O. Multinode cooperation allows different nodes to take part in the same copy/checksum. Split-file processing allows multiple threads to operate concurrently on the same file. Finally, hash trees allow inherently serial checksums to be performed in parallel. Mcp and msum provide significant performance improvements over standard cp and md5sum using multiple types of parallelism and other optimizations. The total speed-ups from all improvements are significant. Mcp improves cp performance over 27x, msum improves md5sum performance almost 19x, and the combination of mcp and msum improves verified copies via cp and md5sum by almost 22x. These improvements come in the form of drop-in replacements for cp and md5sum, so are easily used and are available for download as open source software at http://mutil.sourceforge.net.

Kolano, Paul Z.↗
NASA NTRS2007

A Parallel Saturation Algorithm on Shared Memory Architectures

Symbolic state-space generators are notoriously hard to parallelize. However, the Saturation algorithm implemented in the SMART verification tool differs from other sequential symbolic state-space generators in that it exploits the locality of ring events in asynchronous system models. This paper explores whether event locality can be utilized to efficiently parallelize Saturation on shared-memory architectures. Conceptually, we propose to parallelize the ring of events within a decision diagram node, which is technically realized via a thread pool. We discuss the challenges involved in our parallel design and conduct experimental studies on its prototypical implementation. On a dual-processor dual core PC, our studies show speed-ups for several example models, e.g., of up to 50% for a Kanban model, when compared to running our algorithm only on a single core.

Ezekiel, Jonathan↗
DOE OSTI2022

Avoiding excess computation in asynchronous evolutionary algorithms

Abstract Asynchronous evolutionary algorithms are becoming increasingly popular as a means of making full use of many processors while solving computationally expensive search and optimization problems. These algorithms excel at keeping large clusters fully utilized, but may sometimes inefficiently sample an excess of fast‐evaluating solutions at the expense of higher‐quality, slow‐evaluating ones. We have previously introduced a steady‐state parent selection strategy, SWEET (“Selection whilE EvaluaTing”), that sometimes selects individuals that are still being evaluated and allows them to reproduce early. We perform a takeover‐time analysis that confirms that this strategy gives slow‐evaluating individuals that have higher fitnesses an increased ability to multiply in the population. We also find that SWEET appears effective at improving optimization performance on problems in which solution quality is positively correlated with evaluation time. We evaluate our approach on six simulated real‐valued optimization problems and three real‐world applications: an autonomous vehicle controller problem that involves tuning a spiking neural network and two adversarial EA problems. We further evaluate SWEET versus a basic asynchronous process in a simulated setting. We present evidence that SWEET outperforms basic asynchronous processes in a use‐case in which performance is positively correlated with evaluation time, and performs comparably (and often better) than basic asynchronous processes in several use‐cases where performance is negatively correlated with evaluation time. That said, in the cases where performance and evaluation time are negatively correlated the variance of outcomes for SWEET is notably high.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1984

Parallel, iterative solution of sparse linear systems: Models and architectures

A model of a general class of asynchronous, iterative solution methods for linear systems is developed. In the model, the system is solved by creating several cooperating tasks that each compute a portion of the solution vector. A data transfer model predicting both the probability that data must be transferred between two tasks and the amount of data to be transferred is presented. This model is used to derive an execution time model for predicting parallel execution time and an optimal number of tasks given the dimension and sparsity of the coefficient matrix and the costs of computation, synchronization, and communication. The suitability of different parallel architectures for solving randomly sparse linear systems is discussed. Based on the complexity of task scheduling, one parallel architecture, based on a broadcast bus, is presented and analyzed.

Reed, D. A.↗
DOE OSTI2022

Computer Science Research Needs for Parallel Discrete Event Simulation (PDES)

Historically, scientific computing efforts have demonstrated the clear need for, and effective use of, supercomputing with traditional time-stepped simulations. Nevertheless, there are several areas in the mission spaces of the U.S. Department of Energy and other agencies waiting to tap advanced computing research using a different, discrete event style of modeling, simulation, and analysis. These span a wide spectrum of applications including energy grid resilience, urban planning and policy, transportation science, building technologies, emergency response and planning, environmental impact analysis, computational epidemiology, Internet communications, cyber security, and cyber-physical systems, to name only a few. Even within traditional scientific applications, the role of discrete event modes of execution is increasing in the form of new event-based mathematical solvers such as quantized state integration methods and discrete-continuous hybrid system solvers. Co-design of advanced supercomputing hardware systems is another area that exploits discrete event simulation at its core for effective analyses. Complex systems, entity behaviors and interconnections play a significant role in all these applications, which are mapped to large-scale models with discrete event formulations. To make advancements in all the aforementioned scientific areas, many technical aspects need to be more thoroughly studied and deeply understood in parallel discrete event simulation (PDES). The unique dynamics inherent in a discrete event modeling approach, by their very nature, intersect and influence the entire stack of the computing system, including (a) the unique nature of the instruction sets exercised in PDES workloads without a predominance of high-precision floating point operations, (b) virtual time-constrained multi-threaded execution of many logical processes per processor, (c) extremely variable and difficult to predict network traffic characteristics, (d) interfaces and inter-dependencies with machine learning and artificial intelligence codes at higher software layers, and (e) highly challenging load balancing needs, especially in effectively accounting for accelerated/extremely heterogeneous computing in current and future high-performance computing systems. Efficient and accurate parallel execution of PDES workloads is also dominated by challenges in dealing with their asynchronous concurrency fundamentally present at the model level. Conservative synchronization, optimistic/speculative synchronization, and their hybrid schemes open new questions in fundamental computer science with respect to reversibility of computation and prediction (lookahead) of behaviors inherent within model codes. On the implementation front, there are relatively few scalable, general-purpose parallel discrete event simulators in the world, and even fewer have been studied on emerging hardware platforms. To enable scientific advances using PDES, the research needs in computer science must also be pursued and met in the intersection of the algorithmic and hardware-aware aspects of scalable PDES engines. This report is aimed at capturing a computer science-oriented view of this important area of research in PDES, presenting a sample of important applications with their inherent discrete event technology elements. Needs are outlined in core areas of parallel discrete event research as well as cross-cutting directions in computer science research that positively impact scientific advancements across several important application areas. A selection of priority research opportunities in advanced computing for PDES is identified to serve as reference for key research topics and their order of importance for scientific advancements.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Asynchronous Iterative Solvers for Extreme-Scale Computing

The Asynchronous Iterative Solvers for Extreme-Scale Computing (AsyncIS) project aims to explore more efficient numerical algorithms by decreasing their overhead. AsyncIS does this by replacing the outer Krylov subspace solver with an asynchronous optimized Schwarz method, thereby removing the global synchronization and bulk synchronous operations typically used in numerical codes. AsyncIS—a U.S. Department of Energy (DOE)-funded collaboration between Georgia Tech, the University of Tennessee, Knoxville, Temple University, and Sandia National Laboratories—also focuses on the development and optimization of asynchronous preconditioners (i.e., preconditioners that are generated and/or applied in an asynchronous fashion). The novel preconditioning algorithms that provide fine-grained parallelism enable preconditioned Krylov solvers to run efficiently on large-scale distributed systems and manycore accelerators like GPUs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Scaling neural simulations in STACS

Abstract As modern neuroscience tools acquire more details about the brain, the need to move towards biological-scale neural simulations continues to grow. However, effective simulations at scale remain a challenge. Beyond just the tooling required to enable parallel execution, there is also the unique structure of the synaptic interconnectivity, which is globally sparse but has relatively high connection density and non-local interactions per neuron. There are also various practicalities to consider in high performance computing applications, such as the need for serializing neural networks to support potentially long-running simulations that require checkpoint-restart. Although acceleration on neuromorphic hardware is also a possibility, development in this space can be difficult as hardware support tends to vary between platforms and software support for larger scale models also tends to be limited. In this paper, we focus our attention on Simulation Tool for Asynchronous Cortical Streams (STACS), a spiking neural network simulator that leverages the Charm++ parallel programming framework, with the goal of supporting biological-scale simulations as well as interoperability between platforms. Central to these goals is the implementation of scalable data structures suitable for efficiently distributing a network across parallel partitions. Here, we discuss a straightforward extension of a parallel data format with a history of use in graph partitioners, which also serves as a portable intermediate representation for different neuromorphic backends. We perform scaling studies on the Summit supercomputer, examining the capabilities of STACS in terms of network build and storage, partitioning, and execution. We highlight how a suitably partitioned, spatially dependent synaptic structure introduces a communication workload well-suited to the multicast communication supported by Charm++. We evaluate the strong and weak scaling behavior for networks on the order of millions of neurons and billions of synapses, and show that STACS achieves competitive levels of parallel efficiency.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

A Task Based Approach for Co-Scheduling Ensemble Workloads on Heterogeneous Nodes

Scientific workflows consist of multiple, connected applications, with data and results flowing from one to another in a pipeline. Traditionally, such workflows are executed in sequential order, storing intermediate data in storage disks. Co-scheduling application workflows concurrently on the same compute nodes would greatly reduce the cost of moving data to/from storage and allow real-time analysis of intermediate results. Nevertheless, most parallel programming runtimes do not allow seamless integration of various applications in a scientific workflow, in part due to the complexity of managing data and resources. The situation is even more complicated for heterogeneous systems. In this work we extend the Minos Computing Library (MCL) runtime to accelerate pipe-lined and parallel workloads where multiple applications are running in the same system. MCL’s asynchronous task library and runtime dynamically manages resources to allow co-scheduling of multiple processes sharing heterogeneous resources. In addition, we design a custom ex- tension of the Open Compute Language (OpenCL) to enable multiple processes to share device memory. We enable MCL to coordinate these shared buffers to allow for easy, fast data sharing between applications. Using malleable micro-benchmarks and two application workflows that combine scientific simulation and AI-based analysis, we show that our method outperforms traditional approaches.

Index Terms—Parallel systems, Scheduling and Task ↗
DOE OSTI2021

Devastator Parallel Discrete Event Simulation Runtime (Devastator) v1.0

The Devastator runtime is a modern C++ implementation of optimistic parallel discrete event simulation methods. Devastator allows simulation application code to productively specify their component and event functionality with C++14 constructs. It utilizes GASNet-EX for distributed memory communication and includes parallel performance optimizations such as light-weight thread message queues and asynchronous GVT. Furthermore, it supports efficient event broadcasts and pause-rewind-resume functionality to support periodic load balancing and outer loop optimization algorithms.

Chan, Cy↗
NASA NTRS1981

Real time software tools and methodologies

Real time systems are characterized by high speed processing and throughput as well as asynchronous event processing requirements. These requirements give rise to particular implementations of parallel or pipeline multitasking structures, of intertask or interprocess communications mechanisms, and finally of message (buffer) routing or switching mechanisms. These mechanisms or structures, along with the data structue, describe the essential character of the system. These common structural elements and mechanisms are identified, their implementation in the form of routines, tasks or macros - in other words, tools are formalized. The tools developed support or make available the following: reentrant task creation, generalized message routing techniques, generalized task structures/task families, standardized intertask communications mechanisms, and pipeline and parallel processing architectures in a multitasking environment. Tools development raise some interesting prospects in the areas of software instrumentation and software portability. These issues are discussed following the description of the tools themselves.

Christofferson, M. J.↗
NASA NTRS1989

Asynchronous multilevel adaptive methods for solving partial differential equations on multiprocessors - Performance results

The fast adaptive composite grid method (FAC) is an algorithm that uses various levels of uniform grids (global and local) to provide adaptive resolution and fast solution of PDEs. Like all such methods, it offers parallelism by using possibly many disconnected patches per level, but is hindered by the need to handle these levels sequentially. The finest levels must therefore wait for processing to be essentially completed on all the coarser ones. A recently developed asynchronous version of FAC, called AFAC, completely eliminates this bottleneck to parallelism. This paper describes timing results for AFAC, coupled with a simple load balancing scheme, applied to the solution of elliptic PDEs on an Intel iPSC hypercube. These tests include performance of certain processes necessary in adaptive methods, including moving grids and changing refinement. A companion paper reports on numerical and analytical results for estimating convergence factors of AFAC applied to very large scale examples.

Mccormick, S.↗
NASA NTRS1989

Fast Asynchronous Data Communication Via Fiber Optics

Transmitter and receiver devised for asynchronous digital communication via optical fiber at rates above 100 Mb/s. Transmitter converts parallel data to serial for high-speed transmission; receiver recovers clock signal and converts data back to parallel. No phase-lock loops used. New receiver design avoids over-sampling altogether. Local sampling oscillator operating nominally at clock frequency generates N clock signals of equally spaced phase, used to clock incoming data into N separate shift registers.

Bergman, Larry A.↗
NASA NTRS1992

High performance interconnection between high data rate networks

The bridge/gateway system needed to interconnect a wide range of computer networks to support a wide range of user quality-of-service requirements is discussed. The bridge/gateway must handle a wide range of message types including synchronous and asynchronous traffic, large, bursty messages, short, self-contained messages, time critical messages, etc. It is shown that messages can be classified into three basic classes, synchronous and large and small asynchronous messages. The first two require call setup so that packet identification, buffer handling, etc. can be supported in the bridge/gateway. Identification enables resequences in packet size. The third class is for messages which do not require call setup. Resequencing hardware based to handle two types of resequencing problems is presented. The first is for a virtual parallel circuit which can scramble channel bytes. The second system is effective in handling both synchronous and asynchronous traffic between networks with highly differing packet sizes and data rates. The two other major needs for the bridge/gateway are congestion and error control. A dynamic, lossless congestion control scheme which can easily support effective error correction is presented. Results indicate that the congestion control scheme provides close to optimal capacity under congested conditions. Under conditions where error may develop due to intervening networks which are not lossless, intermediate error recovery and correction takes 1/3 less time than equivalent end-to-end error correction under similar conditions.

Foudriat, E. C.↗
DOE OSTI2020

Evaluating asynchronous Schwarz solvers on GPUs

With the commencement of the exascale computing era, we realize that the majority of the leadership supercomputers are heterogeneous and massively parallel. Even a single node can contain multiple co-processors such as GPUs and multiple CPU cores. For example, ORNL’s Summit accumulates six NVIDIA Tesla V100 GPUs and 42 IBM Power9 cores on each node. Synchronizing across compute resources of multiple nodes can be prohibitively expensive. Hence, it is necessary to develop and study asynchronous algorithms that circumvent this issue of bulk-synchronous computing. In this study, we examine the asynchronous version of the abstract Restricted Additive Schwarz method as a solver. We do not explicitly synchronize, but allow the communication between the sub-domains to be completely asynchronous, thereby removing the bulk synchronous nature of the algorithm. We accomplish this by using the one-sided Remote Memory Access (RMA) functions of the MPI standard. We study the benefits of using such an asynchronous solver over its synchronous counterpart. We also study the communication patterns governed by the partitioning and the overlap between the sub-domains on the global solver. Finally, we show that this concept can render attractive performance benefits over the synchronous counterparts even for a well-balanced problem.

Nayak, Pratik↗