SEARCH · Engineering Papers

Results for “performance portability across architectures”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

14 records

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Performance and Portability of a Linear Solver Across Emerging Architectures

A linear solver algorithm used by a large-scale unstructured-grid computational fluid dynamics application is examined for a broad range of familiar and emerging architectures. Efficient implementation of a linear solver is challenging on recent CPUs offering vector architectures. Vector loads and stores are essential to effectively utilize available memory bandwidth on CPUs, and maintaining performance across different CPUs can be difficult in the face of varying vector lengths offered by each. A similar challenge occurs on GPU architectures, where it is essential to have coalesced memory accesses to utilize memory bandwidth effectively. In this work, we demonstrate that restructuring a computation, and possibly data layout, with regard to architecture is essential to achieve optimal performance by establishing a performance benchmark for each target architecture in a low level language such as vector intrinsics or CUDA. In doing so, we demonstrate how a linear solver kernel can be mapped to Intel® Xeon™ and Xeon Phi™, Marvell® ThunderX2®, NEC® SX-Aurora™ TSUBASA Vector Engine, and NVIDIA® and AMD® GPUs. We further demonstrate that the required code restructuring can be achieved in higher level programming environments such as OpenACC, OCCA, and Intel® OneAPI™/SYCL, and that each generally results in optimal performance on the target architecture. Relative performance metrics for all implementations are shown, and subjective ratings for ease of implementation and optimization are suggested.

Programming models↗

NASA NTRS1998

Performance of a Bounce-Averaged Global Model of Super-Thermal Electron Transport in the Earth's Magnetic Field

In this paper, we report the results of our recent research on the application of a multiprocessor Cray T916 supercomputer in modeling super-thermal electron transport in the earth's magnetic field. In general, this mathematical model requires numerical solution of a system of partial differential equations. The code we use for this model is moderately vectorized. By using Amdahl's Law for vector processors, it can be verified that the code is about 60% vectorized on a Cray computer. Speedup factors on the order of 2.5 were obtained compared to the unvectorized code. In the following sections, we discuss the methodology of improving the code. In addition to our goal of optimizing the code for solution on the Cray computer, we had the goal of scalability in mind. Scalability combines the concepts of portabilty with near-linear speedup. Specifically, a scalable program is one whose performance is portable across many different architectures with differing numbers of processors for many different problem sizes. Though we have access to a Cray at this time, the goal was to also have code which would run well on a variety of architectures.

McGuire, Tim↗

NASA NTRS1995

A portable MPI-based parallel vector template library

This paper discusses the design and implementation of a polymorphic collection library for distributed address-space parallel computers. The library provides a data-parallel programming model for C++ by providing three main components: a single generic collection class, generic algorithms over collections, and generic algebraic combining functions. Collection elements are the fourth component of a program written using the library and may be either of the built-in types of C or of user-defined types. Many ideas are borrowed from the Standard Template Library (STL) of C++, although a restricted programming model is proposed because of the distributed address-space memory model assumed. Whereas the STL provides standard collections and implementations of algorithms for uniprocessors, this paper advocates standardizing interfaces that may be customized for different parallel computers. Just as the STL attempts to increase programmer productivity through code reuse, a similar standard for parallel computers could provide programmers with a standard set of algorithms portable across many different architectures. The efficacy of this approach is verified by examining performance data collected from an initial implementation of the library running on an IBM SP-2 and an Intel Paragon.

Sheffler, Thomas J.↗

NASA NTRS1995

A Portable MPI-Based Parallel Vector Template Library

This paper discusses the design and implementation of a polymorphic collection library for distributed address-space parallel computers. The library provides a data-parallel programming model for C + + by providing three main components: a single generic collection class, generic algorithms over collections, and generic algebraic combining functions. Collection elements are the fourth component of a program written using the library and may be either of the built-in types of c or of user-defined types. Many ideas are borrowed from the Standard Template Library (STL) of C++, although a restricted programming model is proposed because of the distributed address-space memory model assumed. Whereas the STL provides standard collections and implementations of algorithms for uniprocessors, this paper advocates standardizing interfaces that may be customized for different parallel computers. Just as the STL attempts to increase programmer productivity through code reuse, a similar standard for parallel computers could provide programmers with a standard set of algorithms portable across many different architectures. The efficacy of this approach is verified by examining performance data collected from an initial implementation of the library running on an IBM SP-2 and an Intel Paragon.

Sheffler, Thomas J.↗

NASA NTRSDate not supplied

A Multi-Architecture Approach for Implicit Computational Fluid Dynamics on Unstructured Grids

High-performance computing (HPC) architectures are trending toward manycore paradigms such as graphics processing units (GPUs). Approximately half of the top 100 publicly disclosed supercomputers in the world utilize GPU accelerators for performance. This is in contrast to a decade ago, where there were only a few such machines in the top 100. It is not currently possible to compile and run legacy central processing unit (CPU) software efficiently on GPUs without significant refactoring. Though a number of frameworks offering performance portability exist, none offer a standardized specification that is supported by all major hardware vendors. Additionally, experiences show that obtaining a high percentage of peak performance often requires architecture-specific code. This work details a pragmatic multi-architecture computational fluid dynamics library focused on aerospace problems across the speed range from low subsonic to hypersonic flows involving thermochemical nonequilibrium. A thin abstraction layer above NVIDIA CUDA C++ is utilized, which enables primarily single-source software currently capable of running efficiently on multicore CPUs, NVIDIA GPUs, AMD GPUs, and Intel GPUs. Results on various problems of interest across the speed range are presented and performance is compared between various architectures.

GPU↗

NASA NTRSDate not supplied

A Multi-Architecture Approach for Implicit Computational Fluid Dynamics on Unstructured Grids

GPU↗

NASA NTRS1998

Developing Information Power Grid Based Algorithms and Software

This exploratory study initiated our effort to understand performance modeling on parallel systems. The basic goal of performance modeling is to understand and predict the performance of a computer program or set of programs on a computer system. Performance modeling has numerous applications, including evaluation of algorithms, optimization of code implementations, parallel library development, comparison of system architectures, parallel system design, and procurement of new systems. Our work lays the basis for the construction of parallel libraries that allow for the reconstruction of application codes on several distinct architectures so as to assure performance portability. Following our strategy, once the requirements of applications are well understood, one can then construct a library in a layered fashion. The top level of this library will consist of architecture-independent geometric, numerical, and symbolic algorithms that are needed by the sample of applications. These routines should be written in a language that is portable across the targeted architectures.

Dongarra, Jack↗

NASA NTRS1999

Portable Parallel Programming for the Dynamic Load Balancing of Unstructured Grid Applications

The ability to dynamically adapt an unstructured -rid (or mesh) is a powerful tool for solving computational problems with evolving physical features; however, an efficient parallel implementation is rather difficult, particularly from the view point of portability on various multiprocessor platforms We address this problem by developing PLUM, tin automatic anti architecture-independent framework for adaptive numerical computations in a message-passing environment. Portability is demonstrated by comparing performance on an SP2, an Origin2000, and a T3E, without any code modifications. We also present a general-purpose load balancer that utilizes symmetric broadcast networks (SBN) as the underlying communication pattern, with a goal to providing a global view of system loads across processors. Experiments on, an SP2 and an Origin2000 demonstrate the portability of our approach which achieves superb load balance at the cost of minimal extra overhead.

Biswas, Rupak↗

NASA NTRS2003

CORBASec Used to Secure Distributed Aerospace Propulsion Simulations

The NASA Glenn Research Center and its industry partners are developing a Common Object Request Broker (CORBA) Security (CORBASec) test bed to secure their distributed aerospace propulsion simulations. Glenn has been working with its aerospace propulsion industry partners to deploy the Numerical Propulsion System Simulation (NPSS) object-based technology. NPSS is a program focused on reducing the cost and time in developing aerospace propulsion engines. It was developed by Glenn and is being managed by the NASA Ames Research Center as the lead center reporting directly to NASA Headquarters' Aerospace Technology Enterprise. Glenn is an active domain member of the Object Management Group: an open membership, not-for-profit consortium that produces and manages computer industry specifications (i.e., CORBA) for interoperable enterprise applications. When NPSS is deployed, it will assemble a distributed aerospace propulsion simulation scenario from proprietary analytical CORBA servers and execute them with security afforded by the CORBASec implementation. The NPSS CORBASec test bed was initially developed with the TPBroker Security Service product (Hitachi Computer Products (America), Inc., Waltham, MA) using the Object Request Broker (ORB), which is based on the TPBroker Basic Object Adaptor, and using NPSS software across different firewall products. The test bed has been migrated to the Portable Object Adaptor architecture using the Hitachi Security Service product based on the VisiBroker 4.x ORB (Borland, Scotts Valley, CA) and on the Orbix 2000 ORB (Dublin, Ireland, with U.S. headquarters in Waltham, MA). Glenn, GE Aircraft Engines, and Pratt & Whitney Aircraft are the initial industry partners contributing to the NPSS CORBASec test bed. The test bed uses Security SecurID (RSA Security Inc., Bedford, MA) two-factor token-based authentication together with Hitachi Security Service digital-certificate-based authentication to validate the various NPSS users. The test bed is expected to demonstrate NPSS CORBASec-specific policy functionality, confirm adequate performance, and validate the required Internet configuration in a distributed collaborative aerospace propulsion environment.

Blaser, Tammy M.↗

NASA NTRS2024

Runtime Thread-Block Optimization for Custom Multistream CUDA Kernels for the Glenn Research Center Communication Analysis Suite

In preparation of the return of humans to the Moon with the coming Artemis missions, NASA scientists must evaluate proposed landing site locations for terrain and communications viability. The Glenn Research Center Communication Analysis Suite (GCAS) combines sophisticated communication network models with accurate lunar terrain to access sites across the Moon’s south pole. Given the importance of proper site selection to crew safety and mission success, many locations need to be analyzed resulting in a large computational load needing to be performed. To meet the growing project demands, development has begun to improve the runtime efficiency of GCAS with GPU parallelization by way of multi-stream CUDA kernels. One of the most prominent factors in kernel optimization is the proper selection of thread-block dimensions in order to maximize the concurrent operation on the device. Typically, thread-block dimensions are optimized by hand requiring many stages of benchmarking and iteration. Additionally, given the main conditions to optimization are the physical GPU architecture and problem size, these optimal dimensions are non-portable and fragile in their scope. As such, a novel optimization routine was developed to generate the optimal thread-block dimensions during runtime with considerations to hardware specifications and problem size resolving the issues of portability and enabling the function of more dynamic routines.

Aden Bergstresser↗

NASA NTRS2014

Using SpF to Achieve Petascale for Legacy Pseudospectral Applications

Pseudospectral (PS) methods possess a number of characteristics (e.g., efficiency, accuracy, natural boundary conditions) that are extremely desirable for dynamo models. Unfortunately, dynamo models based upon PS methods face a number of daunting challenges, which include exposing additional parallelism, leveraging hardware accelerators, exploiting hybrid parallelism, and improving the scalability of global memory transposes. Although these issues are a concern for most models, solutions for PS methods tend to require far more pervasive changes to underlying data and control structures. Further, improvements in performance in one model are difficult to transfer to other models, resulting in significant duplication of effort across the research community. We have developed an extensible software framework for pseudospectral methods called SpF that is intended to enable extreme scalability and optimal performance. Highlevel abstractions provided by SpF unburden applications of the responsibility of managing domain decomposition and load balance while reducing the changes in code required to adapt to new computing architectures. The key design concept in SpF is that each phase of the numerical calculation is partitioned into disjoint numerical kernels that can be performed entirely inprocessor. The granularity of domain decomposition provided by SpF is only constrained by the datalocality requirements of these kernels. SpF builds on top of optimized vendor libraries for common numerical operations such as transforms, matrix solvers, etc., but can also be configured to use open source alternatives for portability. SpF includes several alternative schemes for global data redistribution and is expected to serve as an ideal testbed for further research into optimal approaches for different network architectures. In this presentation, we will describe our experience in porting legacy pseudospectral models, MoSST and DYNAMO, to use SpF as well as present preliminary performance results provided by the improved scalability.

DYNAMO↗

NASA NTRS2013

SpF: Enabling Petascale Performance for Pseudospectral Dynamo Models

Pseudospectral (PS) methods possess a number of characteristics (e.g., efficiency, accuracy, natural boundary conditions) that are extremely desirable for dynamo models. Unfortunately, dynamo models based upon PS methods face a number of daunting challenges, which include exposing additional parallelism, leveraging hardware accelerators, exploiting hybrid parallelism, and improving the scalability of global memory transposes. Although these issues are a concern for most models, solutions for PS methods tend to require far more pervasive changes to underlying data and control structures. Further, improvements in performance in one model are difficult to transfer to other models, resulting in significant duplication of effort across the research community.We have developed an extensible software framework for pseudospectral methods called SpF that is intended to enable extreme scalability and optimal performance. High-level abstractions provided by SpF unburden applications of the responsibility of managing domain decomposition and load balance while reducing the changes in code required to adapt to new computing architectures. The key design concept in SpF is that each phase of the numerical calculation is partitioned into disjoint numerical kernels that can be performed entirely in-processor. The granularity of domain-decomposition provided by SpF is only constrained by the data-locality requirements of these kernels. SpF builds on top of optimized vendor libraries for common numerical operations such as transforms, matrix solvers, etc., but can also be configured to use open source alternatives for portability. SpF includes several alternative schemes for global data redistribution and is expected to serve as an ideal testbed for further research into optimal approaches for different network architectures.In this presentation, we will describe the basic architecture of SpF as well as preliminary performance data and experience with adapting legacy dynamo codes. We will conclude with a discussion of planned extensions to SpF that will provide pseudospectral applications with additional flexibility with regard to time integration, linear solvers, and discretization in the radial direction.

Pseudospectral (PS)↗

NASA NTRS2021

Harmonized Emissions Component (HEMCO) 3.0 as a Versatile Emissions Component for Atmospheric Models: Application in the GEOS-Chem, NASA GEOS, WRF-GC, CESM2, NOAA GEFS-Aerosol, and NOAA UFS Models

Emissions are a central component of atmospheric chemistry models. The Harmonized Emissions Component (HEMCO) is a software component for computing emissions from a user-selected ensemble of emission inventories and algorithms. It allows users to re-grid, combine, overwrite, subset, and scale emissions from different inventories through a configuration file and with no change to the model source code. The configuration file also maps emissions to model species with appropriate units. HEMCO can operate in offline stand-alone mode, but more importantly it provides an online facility for models to compute emissions at runtime. HEMCO complies with the Earth System Modeling Framework (ESMF) for portability across models. We present a new version here, HEMCO 3.0, that features an improved three-layer architecture to facilitate implementation into any atmospheric model and improved capability for calculating emissions at any model resolution including multiscale and unstructured grids. The three-layer architecture of HEMCO 3.0 includes (1) the Data Input Layer that reads the configuration file and accesses the HEMCO library of emission inventories and other environmental data, (2) the HEMCO Core that computes emissions on the user-selected HEMCO grid, and (3) the Model Interface Layer that re-grids (if needed) and serves the data to the atmospheric model and also serves model data to the HEMCO Core for computing emissions dependent on model state (such as from dust or vegetation). The HEMCO Core is common to the implementation in all models, while the Data Input Layer and the Model Interface Layer are adaptable to the model environment. Default versions of the Data Input Layer and Model Interface Layer enable straightforward implementation of HEMCO in any simple model architecture, and options are available to disable features such as re-gridding that may be done by independent couplers in more complex architectures. The HEMCO library of emission inventories and algorithms is continuously enriched through user contributions so that new inventories can be immediately shared across models. HEMCO can also serve as a general data broker for models to process input data not only for emissions but for any gridded environmental datasets. We describe existing implementations of HEMCO 3.0 in (1) the GEOS-Chem “Classic” chemical transport model with shared-memory infrastructure, (2) the high-performance GEOS-Chem (GCHP) model with distributed-memory architecture, (3) the NASA GEOS Earth System Model (GEOS ESM), (4) the Weather Research and Forecasting model with GEOS-Chem (WRF-GC), (5) the Community Earth System Model Version 2 (CESM2), and (6) the NOAA Global Ensemble Forecast System – Aerosols (GEFS-Aerosols), as well as the planned implementation in the NOAA Unified Forecast System (UFS). Implementation of HEMCO in CESM2 contributes to the Multi-Scale Infrastructure for Chemistry and Aerosols (MUSICA) by providing a common emissions infrastructure to support different simulations of atmospheric chemistry across scales.

Haipeng Lin↗

NASA NTRSDate not supplied

Uncrewed Lunar Surface Operations and Support Activities

Sustained human presence on the surface of the Moon and future missions to Mars require increased independence from surface crews and Earth-based mission control to operate efficiently, safely, and reliably. The time for surface crews to perform tasks will be limited. Extravehicular activities by surface personnel are burdensome and time-consuming, even when a continuous human presence on the surface occurs. Identifying and balancing human/automation roles and tasks and infusing automation and autonomy practices early in a system’s lifecycle will be essential to achieve mission objectives. Among these objectives are attaining a sustained human presence, improving performance and mission effectiveness, reducing operations and maintenance (O&M) costs, and ensuring operations that are robust to communication delays. To achieve these objectives, an operational shift toward increased automation and autonomy with less reliance on humans is needed. Uncrewed lunar surface operations and support activities occur when surface crews are not present or are independent of surface crew timeline activities requiring no surface crew oversight or intervention. These uncrewed surface opportunities can also be planned to minimize crew workload that avoids routine maintenance and support tasks, thus maximizing crew exploration time. Uncrewed preparations such as staging and prepositioning equipment and materials before the crew arrives could improve crew task efficiency. Additional opportunities exist to conduct uncrewed science, exploration, and utilization. Uncrewed surface architecture functions can include science and exploration; habitation; launch and landing support; surface communication and navigation; surface power generation and distribution; human surface mobility; lifting, handling, manipulating; excavation, construction, and site preparation; logistics management; maintenance and repair; surface resource utilization; integrated site operations and shared support services (e.g., site scheduling/prioritization, dust mitigation/contamination control, and surface safety). Early robotic lunar surface campaigns will provide information on the availability of resources, such as oxygen and water, and demonstrate surface-based technologies. After the Artemis III human lunar return mission, a series of landers will deliver surface systems, cargo, supplies, science packages, spare parts, and commodities. A balance of crewed and uncrewed surface operations will enable a sustained lunar surface presence at the South Pole of the Moon at a site that will be known as the Artemis Base Camp (ABC). It is envisioned that base camp operations on and around the Moon will then help prepare for the mission durations and activities needed to support the first human mission to Mars. Before long-duration crew missions to the base camp can occur, the necessary surface infrastructure will be pre-deployed and verified operational. Surface assets will be teleoperated and remotely managed from Earth. Additionally, robotic and short-duration crewed missions to the ABC will ensure the site’s merit to achieve long-term science objectives, availability of usable resources, and that terrain, seasonal variations, and illumination conditions are acceptable. ABC will consist of different areas where specific functions and services are rendered, including: • Launch and Landing Area • Habitation Area • Power Production Area • Resource Areas Launch and Landing Area—The launch and landing area will support associated functions for the arrival and departure of vehicles, such as crewed landing and ascent and uncrewed cargo deliveries and offloading. It will evolve from an unimproved site at the beginning of the exploration campaign to a more sustainable landing and launch area that can support repeated arrivals and departures. Initial uncrewed Lunar Terrain Vehicle (LTV) surface operations may include emplacement of navigation beacons and communication equipment, real-time video and photography of landing/liftoff events, and element repositioning, such as portable utility power (PUP) (applicable for other landed assets at other areas). Site preparations, such as surface leveling, soil compaction, and berm/path construction, may be needed for a more sustainable launch and landing area capable of accommodating vehicles that are increasingly more reusable and reduce the effects of plume surface interactions and ejecta impacts on nearby surface assets. During the ABC missions, cargo and logistics will be delivered to the lunar surface via robotic cargo landers before the crew arrives. These shipments, which can arrive in pressurized logistics carriers, will deliver the logistics necessary to support a crewed mission and include items such as food, water, equipment spares, etc. Providing the capability to retrieve, offload, and transport the logistics closer to the ABC site before the arrival of the crew will increase the overall efficiency of crew operations once they arrive. In the sustained phase of exploration, other supporting services may be needed, such as lander propellant servicing, surface power services, commodity refreshes, and additional inspection, maintenance, and repair capabilities, to sustain a cadence of extended personnel stays and cargo arrivals and departures. Habitation Area—Uncrewed support to surface habitation could involve supporting activation and pre-entry operations of the habitat while the crew is in orbit at the Gateway outpost preparing for a surface landing. Surface Habitat (SH) uncrewed operations may include bringing the cabin environment to a habitable temperature and air mix and activating other critical crew support systems. Potential crop production uncrewed tasks in the SH could also include autonomous watering and tending. Additionally, when the crew departs, the SH enters dormancy for the long period of uncrewed operation. A logistical staging area could also be collocated near the SH. If so, staging operations for crew supplies, waste re-location, and recycling operations may be opportunities for uncrewed operations. Power Production Area—The Fission Surface Power (FSP) element and its supporting distribution equipment provide power to surface elements as needed across the ABC to supplement day-to-day operations and survive lunar nights. Uncrewed support of this power system includes any initial LTV-assisted deployments of cables and other distributed equipment, associated electrical connections, and system testing and activation operations. Robotically performing some inspections, maintenance, or repair tasks on the power distribution equipment could reduce the surface crew workload. Resource Area— Uncrewed resource prospecting, mapping, and characterizing possible resource sites is likely to be time-consuming and represents an opportunity for uncrewed operations between crewed missions. Uncrewed mobile equipment operations will be needed in the extreme environments of permanently shadowed locations where resource extractions occur. As In-Situ Resource Utilization (ISRU) pilot plant operations begin, uncrewed surface support activities with available mobile and portable assets (LTV, PUP, etc.) will better support these operations. Any produced commodities can be stored at a centralized storage location for future use. Also associated with these operations is the use of mobile robotic excavators for resource acquisition and robotic/autonomous regolith processing. The waste tailings generated during excavation and regolith processing would also need to be transported and deposited at a dedicated location. Surface assets will continue operating between crew visits to maintain surface capabilities, conduct lunar surface science, technology demonstrations, and public outreach opportunities. Additionally, certain sustaining tasks that would consume valuable crew time could be performed before crew arrival, or after their departure. This capability may offer more affordable options to construct, activate, test, and maintain a broad set of surface assets. Telerobotically operated human surface mobility systems, such as the LTV and Pressurized Rover (PR), can be utilized for various tasks. Surface environmental conditions pose a distinct challenge for all these activities. Surface illumination and localized shadows are one such factor. Night-survival operations could consist of thermal management, battery pre-charging, and load shedding. Some surface systems may hibernate through the night and then awake and continue nominal operations. Uncrewed mobile assets may use a more adaptive approach to optimize their power and operations; one method is to follow the sunlight. Night-survival operations may be initiated remotely by teleoperation, automated, or accomplished by supervised autonomous operation. The ability to pre-deploy and control remote assets in orbit or on Mars before the arrival of the mission crew is a key capability that can be simulated on the moon. The base camp provides a venue where these advanced operational concepts, technologies, and autonomous methods and techniques, including the incorporation of time delays to simulate Earth-Mars latency can be replicated to help buy down future Mars mission risks. This paper will examine the evolution of uncrewed lunar surface operations and support activities. It will also discuss the lunar surface environmental conditions (thermal, lighting, terrain, topography, communications) along with the challenges they pose on uncrewed surface operations, and the performance of these activities with limited to minimal human interaction and/or teleoperation. Since lunar missions include Mars mission analogs, such investigation provides the framework for future uncrewed Mars mission support.

Mark E Lewis↗