Search NASA⌕ Search

SEARCH · Search NASA

Results for “runtime library”

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 199 records · Page 11

Inference-Engine v0.1.0

Given a pre-trained neural network, Inference-Engine performs maps network inputs to outputs by executing the forward pass through the provided network. Although the predominant programming language for machine-learning is Python, most high-performance computing (HPC) applications are written in Fortran, C, or C++. Inference-Engine aims to support HPC programs and is written in Fortran, a language with a large feature set supporting interoperability with C. This software exposes concurrency in a portable way by using standard language features that some modern Fortran compilers can exploit with various optimizations, including offloading computation to a Graphics Processing Unit (GPU). In particular, this software makes extensive use of Fortran's "do concurrent" parallel loop construct, implicitly parallel array statements, and pure procedures that can be invoked inside "do concurrent" blocks. Inference-Engine also supports dynamic choice of inference methods at runtime. Two current options include one method that uses Fortran's "dot_product" intrinsic function inside "do concurrent" blocks and another method that instead uses Fortran' "matmul" array intrinsic function. We plan to investigate automatic compiler offloading of "do concurrent" calculations to GPUs and compile-time substitution of optimized libraries such as the Basic Linear Algebra Library (BLAS) for "matmul" invocations. We also envision the potential for the choice of which method to use could happen at program launch based on in situ performance measurements on any given platform.

Rouson, Damian↗

Accelerating the Inference of the Exa.TrkX Pipeline

Recently, graph neural networks (GNNs) have been successfully used for a variety of particle reconstruction problems in high energy physics, including particle tracking. The Exa.TrkX pipeline based on GNNs demonstrated promising performance in reconstructing particle tracks in dense environments. It includes five discrete steps: data encoding, graph building, edge filtering, GNN, and track labeling. All steps were written in Python and run on both GPUs and CPUs. In this work, we accelerate the Python implementation of the pipeline through customized and commercial GPU-enabled software libraries, and develop a C++ implementation for inferencing the pipeline. The implementation features an improved, CUDA-enabled fixed-radius nearest neighbor search for graph building and a weakly connected component graph algorithm for track labeling. GNNs and other trained deep learning models are converted to ONNX and inferenced via the ONNX Runtime C++ API. The complete C++ implementation of the pipeline allows integration with existing tracking software. We report the memory usage and average event latency tracking performance of our implementation applied to the TrackML benchmark dataset.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Automatic and Transparent Resource Contention Mitigation for Improving Large-Scale Parallel File System Performance

Proportional to the scale increases in HPC systems, many scientific applications are becoming increasingly data intensive, and parallel I/O has become one of the dominant factors impacting the large-scale HPC application performance. On a typical large-scale HPC system, we have observed that the lack of a global workload coordination coupled with the shared nature of storage systems cause load imbalance and resource contention over the end-to-end I/O paths resulting in severe performance degradation. I/O load imbalance on HPC systems is generally a self-inflicted wound and mostly occurs between the I/O paths and resources consumed by each individual job. In this paper, we introduce TAPP-IO, a dynamic, shared load balancing framework for mitigating resource contention. TAPP-IO extends our previous work and solves two major limitations: First, it transparently intercepts file creation calls during runtime to balance the workload over all available storage targets. The usage of TAPP-IO requires no application source code modifications and is independent from any I/O middleware. The framework can be applied to almost any HPC platform and is suitable for systems that lack a centralized file system resource manager. Second, the framework proposes a new placement strategy to support not only file-per-process I/O, but also single shared file I/O. This opens the door to a new class of scientific applications that can leverage the placement library for improved performance. We demonstrate the effectiveness of our integration on the Titan system at the Oak Ridge National Laboratory. Our experiments with a synthetic benchmark and real-world HPC workload show that, even in a noisy production environment, TAPP-IO can improve large-scale application performance significantly.

Neuwirth, Sarah↗

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↗

Fast synchronization-free algorithms for parallel sparse triangular solves with multiple right-hand sides

The sparse triangular solve kernels, SpTRSV and SpTRSM, are important building blocks for a number of numerical linear algebra routines. Parallelizing SpTRSV and SpTRSM on today's many-core platforms, such as GPUs, is not an easy task since computing a component of the solution may depend on previously computed components, enforcing a degree of sequential processing. As a consequence, most existing work introduces a preprocessing stage to partition the components into a group of level-sets or colour-sets so that components within a set are independent and can be processed simultaneously during the subsequent solution stage. However, this class of methods requires a long preprocessing time as well as significant runtime synchronization over-heads between the sets. To address this, we

HPC↗

Experiences with SYCL on AMD GPUs with Kokkos

With the recent diversification of the hardware landscape in the high-performance computing (HPC) community, performance-portability solutions are becoming more and more important. One of the most popular choices is Kokkos, which recently became a Linux Foundation project. Most of its development is supported by the US Department of Energy and the French Alternative Energies and Atomic Energy Commission. Kokkos is implemented as a C++ library with multiple backends to support CPUs as well as various GPU architectures. These backends include OpenMP, CUDA, HIP, and also SCYL. This approach enables users to leverage the preferred vendor toolchain for the respective platform (e.g. CUDA, ROCm, OneAPI). The SYCL backend is used to target Intel GPUs, in particular to support the Aurora exascale supercomputer. However, SYCL itself also offers a large degree of portability, and in fact Kokkos’ CI for SYCL has been running on NVIDIA hardware due to a lack of access to Intel GPUs. In this report, we describe our experience with using Kokkos SYCL backend on AMD GPUs targeting the Frontier supercomputer at Oak Ridge National Laboratory. The two major SYCL implementations are DPC++ and AdaptiveCpp. While the Kokkos SYCL backend has been implemented using the former, the latter was the first implementation to target AMD GPUs. We will discuss the experience with both of these SYCL implementations in terms of functionality and performance. Using Kokkos to evaluate SYCL toolchains has a number of benefits. Kokkos’ use of SYCL is fairly complex, exercising features such as graphs, relocatable device functions, atomics – including for non-arithmetic types, as well as pinned and page migratable memory allocations. Kokkos also needs to implement capabilities such as Kokkos’ hierarchical parallelism that are not a straight-forward mapping to SYCL capabilities. Furthermore, a large number of libraries and applications that represent diverse use cases are implemented in Kokkos, providing readily available test cases for a toolchain evaluation. Preliminary results show that support for AMD GPUs in DPC++ is much less mature than for NVIDIA GPUs or Intel GPUs. While the situation has improved significantly over the last year, we still encounter many runtime failures, dispatching problems, and code generation issues. With AdaptiveCpp the challenges arise even earlier in the evaluation process. Since Kokkos’ SYCL implementation is largely focused on supporting Intel GPUs, we opted to leverage SYCL extensions which are available in DPC++ but not in AdaptiveCpp. Furthermore, AdaptiveCpp appears to be less conformant with the SYCL2020 standard which Kokkos relies on. In some cases, we are able to work around the lack of feature support, in other cases we have to disable certain Kokkos capabilities to evaluate the toolchain. Our evaluation will leverage Kokkos’ unit tests to establish basic functionality and feature completeness. We then use simple benchmarks for components of a CG implementation as a measure of usability and performance of the SYCL toolchains.

97 MATHEMATICS AND COMPUTING↗

HVAC and Control Templates for the Modelica Buildings Library

This article reports on our experience in creating Modelica models for systems with thousands of configurations and closed-loop controls. The development of such templates required exploration of class parameterization techniques and data structures for handling large sets of equipment parameters. By describing these issues and the approach taken, we show how the Modelica language can support advanced templating logic. The main limitation we encountered relates to parameter assignment and propagation. The interpretation of parameter attributes at user interface runtime, or the handling of non-trivial constructs involving record classes at compile time is not consistently supported by Modelica tools. This leads to choices that are difficult to make when looking for a generic implementation.

Gautier, Antoine↗

Highlights of X-Stack ExM Deliverable Swift/T

Swift/T is a key success from the ExM: System support for extreme-scale, many-task applications1 X-Stack project, which proposed to use concurrent dataflow as an innovative programming model to exploit extreme parallelism in exascale computers. The Swift/T component of the project reimplemented the Swift language from scratch to allow applications that compose scientific modules together to be build and run on available petascale computers (Blue Gene, Cray). Swift/T does this via a new compiler and runtime that generates and executes the application as an MPI program. We assume that mission-critical emerging exascale applications will be composed as scalable applications using existing software components, connected by data dependencies. Developers wrap native code fragments using a higherlevel language, then build composite applications to form a computational experiment. This exemplifies hierarchical concurrency: lower-level messaging libraries are used for fine-grained parallelism; highlevel control is used for inter-task coordination. These patterns are best expressed with dataflow, but static DAGs (i.e., other workflow languages) limit the applications that can be built; they do not provide the expressiveness of Swift, such as conditional execution, iteration, and recursive functions.

97 MATHEMATICS AND COMPUTING↗

Detection and Correction of Silent Data Corruption for Large-Scale High-Performance Computing

Faults have become the norm rather than the exception for high-end computing on clusters with 10s/100s of thousands of cores. Exacerbating this situation, some of these faults remain undetected, manifesting themselves as silent errors that corrupt memory while applications continue to operate and report incorrect results. This paper studies the potential for redundancy to both detect and correct soft errors in MPI message-passing applications. Our study investigates the challenges inherent to detecting soft errors within MPI application while providing transparent MPI redundancy. By assuming a model wherein corruption in application data manifests itself by producing differing MPI message data between replicas, we study the best suited protocols for detecting and correcting MPI data that is the result of corruption. To experimentally validate our proposed detection and correction protocols, we introduce RedMPI, an MPI library which resides in the MPI profiling layer. RedMPI is capable of both online detection and correction of soft errors that occur in MPI applications without requiring any modifications to the application source by utilizing either double or triple redundancy. Our results indicate that our most efficient consistency protocol can successfully protect applications experiencing even high rates of silent data corruption with runtime overheads between 0% and 30% as compared to unprotected applications without redundancy. Using our fault injector within RedMPI, we observe that even a single soft error can have profound effects on running applications, causing a cascading pattern of corruption in most cases causes that spreads to all other processes. RedMPI's protection has been shown to successfully mitigate the effects of soft errors while allowing applications to complete with correct results even in the face of errors.

Fiala, David J↗

MONK10: A Monte Carlo Code for Criticality Analysis - 14574

The MONK{sup R} code, if we include its predecessor GEM, has now been in use for 50 years. It is a Monte Carlo code for nuclear criticality and reactor physics analyses which is used extensively in the UK nuclear industry and worldwide. In 2014 a major new version of the code, MONK10A, was released introducing many new features; these are described with example applications presented where appropriate. Experience with MONK9A models indicates that MONK10A has increased run-time performance for all cases and on average runs 2.4 times faster. New geometry options include the direct import of CAD generated models using the new IGES body, POLY body, TETMESH Hole and TETMESH Zone features. Example calculations for a selection of CAD import options are presented and compared with the intrinsic MONK geometry representation, with relative merits discussed. New Features are included to assist with the modeling of distributed parameters; such features include Unified Tally (UT), Action Tallies (AT) in UT and Shannon entropy. The latter is useful in assessing the convergence of distributed parameters, such as scalar neutron flux. As such it is an important tool in determining the appropriate point to stop settling and begin scoring stages in a Monte Carlo simulation. The utility of UT, AT-in-UT and Shannon entropy is demonstrated using calculations employing the new CAD import geometry options. Runtime Doppler broadening is included to allow accurate representation of temperature distributions within models. Example calculations which further demonstrate UT and AT-in-UT are presented for different bodies at different temperatures to evaluate the effects of temperature differences on k-effective and reaction rates. The MONK10A code was issued with a new set of continuous energy and group nuclear data libraries. These include JEFF3.1, JEFF3.1.1, JEFF 3.1.2, ENDF/B-VII.0 and CENDL 3.1 libraries. The inclusion of a range of libraries allows the user to evaluate the impact of different international nuclear data evaluations on their results and an example is provided to illustrate the differences that can arise from the use of different nuclear data evaluations. The code was also issued with a new version of the VisualWorkshop IDE to allow easy construction and editing of input decks, running of calculations and display of geometry and results. Examples are provided of the geometry and results display and showing how results can be superimposed upon the geometry. (authors)

42 ENGINEERING↗

Towards Generic Parallel Programming in Computer Science Education with Kokkos

Parallel patterns, views, and spaces are promising abstractions to capture the programmer's intent as well as the contextual information that can be used by an underlying runtime to efficiently map software to parallel hardware. These abstractions can be valuable in cases where an algorithm must accommodate requirements of code and performance portability across hardware architectures and vendor programming models. Kokkos is a parallel programming model for host- and accelerator architectures that relies on these abstractions and targets these requirements. It consists of a pure C++ interface, a specification, and a programming library. The programming library exposes patterns and types and maps them to an underlying abstract machine model. The abstract machine model offers a generic view of parallel hardware. While Kokkos is gaining popularity in large-scale HPC applications at some DOE laboratories, we believe that the implemented concepts are of interest to a broader audience including academia as they may contribute to a generic, vendor, and architecture-independent education of parallel programming. In this work, we give an insight into the design considerations of this programming model and list important abstractions. Further, we document best practices obtained from giving virtual classes on Kokkos and give pointers to resources that the reader may consider valuable for a lecture on generic parallel programming for students with preexisting knowledge on this matter.

Ciesko, Jan↗

Integrating Asynchronous Task Parallelism with OpenSHMEM, In: OpenSHMEM 2016: OpenSHMEM and Related Technologies. Enhancing OpenSHMEM for Hybrid Environments

Partitioned Global Address Space (PGAS) programming models combine shared and distributed memory features, and provide a foundation for high-productivity parallel programming using lightweight one-sided communications. The OpenSHMEM programming interface has recently begun gaining popularity as a lightweight library-based approach for developing PGAS applications, in part through its use of a symmetric heap to realize more efficient implementations of global pointers than in other PGAS systems. However, current approaches to hybrid inter-node and intra-node parallel programming in OpenSHMEM rely on the use of multithreaded programming models (e.g., pthreads, OpenMP) that harness intra-node parallelism but are opaque to the OpenSHMEM runtime. This OpenSHMEM+X approach can encounter performance challenges such as bottlenecks on shared resources, long pause times due to load imbalances, and poor data locality. Furthermore, OpenSHMEM+X requires the expertise of hero-level programmers, compared to the use of just OpenSHMEM. All of these are hard challenges to mitigate with incremental changes. This situation will worsen as computing nodes increase their use of accelerators and heterogeneous memories.

Computer Science↗

AGILE GETRS

AGILE GETRS provides an optimized implementation of DETRS that is faster than vendor optimized libraries for small (< 4000) problem sizes. These small problems sizes are of interest to researchers in the Grid Research Integration and Deployment Center (GRID-C) researching real-time power electronics simulations. In addition to our implementation of DETRS, this code provides a test using Google Benchmark which generates matrices of various sizes, fills them with random numbers, runs GETRS, verifies the solution is correct and reports average runtime and other performance metrics.

Hahn, Steven [Oak Ridge National Laboratory (ORNL)↗

Mneme

A simple tool allowing recording the execution of a GPU (CUDA) kernel and replaying that kernel as an independent executable. The tool operates in 3 phases. During compile time the user needs to apply a provided LLVM pass to instrument the code. The pass detects all device global variables and device functions and stores this information with the respective LLVM-IR in the global device memory. The compilation generates a record-able executable. The second phase involves running the application executable with a desired input and using LD_PRELOAD to enable recording. When recording before invoking a device kernel the pre-loaded library stores device memory in persistent storage and associates the memory with the device kernel and an LLVM IR file. At the end of the recorded execution the pre-load library generates a database in the form of a JSON file containing information regarding the LLVM-IR files and the snapshots of device memory. During the third and last phase the user can replay the execution of an kernel as a separate independent executable. Besides executing it the user can modify the LLVM IR file and auto-tune parameters such as kernel launch-bounds or kernel runtime execution parameters (e.g. Kernel Block and Grid Dimensions). Is

Parasyris, Konstantinos↗

Runtime power allocation approach for GAMESS hybrid CPU‐GPU implementation

Summary To improve power consumption of applications at the runtime, modern processors provide frequency scaling capabilities, which along with workload optimization, are also available on GPU accelerators. In this work, a runtime strategy is proposed to distribute a given power allocation among the host components and the GPU according to the current application performance and power usage, such that GPU execution is prioritized over CPU for power allocation to maximize application performance. Next, the strategy is tailored to an application, a quantum‐chemistry package GAMESS for ab initio electronic structure calculations. Specifically, GAMESS hybrid CPU–GPU implementation as provided in the Libcchem library is considered. Experiments, performed on a 28‐core node with a Kepler GPU, resulted in performance gains of up to 50% under the proposed strategy and the largest power allocation considered here as compared with the scenario when this allocation was equally distributed among the computing‐platform components.

Sundriyal, Vaibhav↗

Towards reversible basic linear algebra subprograms: A performance study

Problems such as fault tolerance and scalable synchronization can be efficiently solved using reversibility of applications. Making applications reversible by relying on computation rather than on memory is ideal for large scale parallel computing, especially for the next generation of supercomputers in which memory is expensive in terms of latency, energy, and price. In this direction, a case study is presented here in reversing a computational core, namely, Basic Linear Algebra Subprograms, which is widely used in scientific applications. A new Reversible BLAS (RBLAS) library interface has been designed, and a prototype has been implemented with two modes: (1) a memory-mode in which reversibility is obtained by checkpointing to memory in forward and restoring from memory in reverse, and (2) a computational-mode in which nothing is saved in the forward, but restoration is done entirely via inverse computation in reverse. The article is focused on detailed performance benchmarking to evaluate the runtime dynamics and performance effects, comparing reversible computation with checkpointing on both traditional CPU platforms and recent GPU accelerator platforms. For BLAS Level-1 subprograms, data indicates over an order of magnitude better speed of reversible computation compared to checkpointing. For BLAS Level-2 and Level-3, a more complex tradeoff is observed between reversible computation and checkpointing, depending on computational and memory complexities of the subprograms.

97 MATHEMATICS AND COMPUTING↗

Evaluation of a Reduced-Order Model for IBR Fault Response Representation via OEM Blackbox Models: Preprint

Driven by the need to capture the electromagnetic transients of transmission lines, inverter switching behavior, and detailed control systems, electromagnetic transient (EMT) studies have become increasingly important in industry, such as IBR interconnection study and fault study. However, original equipment manufacturer (OEM) inverter models typically include extensive parameters and proprietary settings that are unavailable to protection engineers. This paper introduces a data-driven, reduced-order model (ROM) developed as a PSCAD library component for use in EMT-based fault studies. The ROM replicates key OEM model behaviors without requiring detailed knowledge of control design or parameterization. The accompanying Python automation scripts streamline data generation, parameter fitting, and validation. The ROM's performance is demonstrated through comparison with both IEEE 2800-compliant and non-compliant OEM models in a real-world power system. Relay responses show nearly identical results, while simulation runtime is reduced by an average of 32.8\%, highlighting the ROM's practicality for protection engineers.

14 SOLAR ENERGY↗

Adapting CLUTCH methodology to multigroup TSUNAMI-3D for eigenvalue sensitivity calculations

The sensitivity of the eigenvalue to uncertainties in nuclear data and its evaluation are important for nuclear criticality safety. TSUNAMI-3D sequences within the SCALE code system offer several options to the user community for calculating eigenvalue sensitivity coefficients with multigroup (MG) and continuous energy (CE) 3D transport capabilities. TSUNAMI-3D sequences implement the adjoint-based perturbation theory with MG KENO code, the Contributon Linked eigenvalue sensitivity/Uncertainty estimation via Track length importance CHaracterization (CLUTCH) method with CE KENO code, and the Iterated Fission Probability (IFP) method with CE KENO and Shift codes. Each method has benefits and limitations depending on the problem that is run. The work presented here aims to adapt the CLUTCH method, which enables the Contributon method's mesh-free, memory-efficient approach for calculating adjoint-weighted tallies for sensitivity calculations, to the MG TSUNAMI-3D sequence. This application would eliminate the explicit adjoint KENO calculation, as well as the memory-consuming mesh flux moment tallies required by the conventional MG TSUNAMI-3D. Smaller memory footprints in the CLUTCH methodology and relatively shorter runtimes in MG KENO transport can make MG TSUNAMI-3D a viable method for some complex problems. Moreover, this adaptation allows MG sensitivity calculations with Shift, ORNL's next-generation high-performance Monte Carlo transport code, which currently does not offer any sensitivity capabilities with MG particle transport simulations. Initial implementation of the new MG TSUNAMI-3D sequence and its preliminary results with a selected critical benchmark experiment in the Verified, Archived Library of Inputs and Data (VALID) are presented in this study.

KENO↗