Automaton & Cognition
AutoCog is a framework to design programming models (PM) for language models (LM). It permits researchers to devise Cognitive Architectures where traditional Artificial Intelligence algorithms are executed by Language Models.
SEARCH · Engineering Papers
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.
AutoCog is a framework to design programming models (PM) for language models (LM). It permits researchers to devise Cognitive Architectures where traditional Artificial Intelligence algorithms are executed by Language Models.
Grit is a software library designed specifically for conducting particle-based Lagrangian simulations with CPU/GPUperformance portability. This library allows researchers and engineers to perform a wide range of simulations, including multiphase flow, and more. Grit employs Message Passing Interface (MPI) for distributed memory parallelism and Kokkos programming model for on-node shared memory parallelism with performance portability across different architectures of GPUs and multi-core/manycore CPUs.
Caffeine is the CoArray Fortran Framework of Efficient Interfaces to Network Environments. Caffeine aims to produce a parallel runtime library that will support Fortran compilers with a programming-model-agnostic application binary interface (ABI) to various lower-level communication libraries. The current version of Caffeine uses the GASNet-EX networking middleware, also developed at Berkeley Lab. On many combinations of applications and platforms, GASNet-EX outperforms the widely used Message Passing Interface (MPI). Through GASNet-EX's support for communicating between graphics processing units (GPU), GASNet-EX has features that specifically target the emerging, leading-edge exascale computing platforms.
An interactive, container-based workflow tool for creating and spawning directed acyclic graphs (DAGs) of operators in a distributed environment. It has a microservices architecture, and flow-based programming model. Current tools like this do not enable streaming of data directly between operators.
This analysis estimates the cost of selected oil and biomass supply shocks for producers and consumers in the light-duty vehicle fuel market under various supply chain configurations using a mathematical programing model, BioTrans. The supply chain configurations differ by whether they include selected flexibility levers: multi-feedstock biorefineries; advanced biomass logistics; and the ability to adjust ethanol content of low-ethanol fuel blends, from E10 to E15 or E05. The simulated scenarios explore market responses to supply shocks including substitution between gasoline and ethanol, substitution between different sources of ethanol supply, biorefinery capacity additions or idling, and price adjustments. Welfare effects for the various market participants represented in BioTrans are summarized into a net shock cost measure. As oil accounts for a larger fraction of fuel by volume, its supply shocks are costlier than biomass supply shocks. Corn availability and the high cost of adding biorefinery capacity limit increases in ethanol use during gasoline price spikes. During shocks that imply sudden decreases in the price of gasoline, the renewable fuel standard (RFS) biofuel blending mandate limits the extent to which flexibility can be exercised to reduce ethanol use. The selected flexibility levers are most useful in response to cellulosic biomass supply shocks.
School buses are an essential component of the transportation infrastructure, serving as a lifeline for students across the globe. However, the widespread use of diesel school buses has raised concerns about the health impact on millions of students exposed to harmful emissions daily. Recognizing this issue, school districts worldwide are urgently seeking cleaner energy alternatives. Electric school buses emerge as an environmentally friendly and sustainable option, fostering a healthier environment for both students and communities. However, school bus electrification faces the challenges of high upfront cost, cumbersome charging management, and constraints from power grids. To help school bus operators address those challenges, this study presents a data-driven analysis for school bus electrification. This study considered a real-world school bus system in Richmond, VA, and developed a mathematical programming model to analyze the system design, charging strategies, and charging load profiles for the electrification scenario. The study evaluated different charging strategies based on model outcomes, aiming to optimize efficiency and effectiveness. Ultimately, this research generated electric school bus charging demand profiles under various scenarios, shedding light on the feasibility and implications of transitioning to electric-powered school buses.
C++ template metaprogramming has emerged as a prominent approach for achieving performance portability in heterogeneous computing. Kokkos represents a notable paradigm in this domain, offering programmers a suite of high-level abstractions for generic programming while deferring much of the device-specific code generation and optimization to the compiler through template specializations. Kokkos furnishes a range of device-specific code specializations across multiple back ends, including CUDA and HIP. Diverging from conventional back ends, the OpenACC implementation presents a high-level, multicompiler, multidevice, and directive-based programming model. This paper presents recent advancements in the OpenACC back end for Kokkos (i.e., KokkACC) and focuses on its integration into the Kokkos ecosystem, exploration of automatic device selection capabilities to enhance productivity, and performance evaluation on modern hardware such as NVIDIA H100 GPUs. The study includes implementation details and a thorough performance assessment across various computational benchmarks, including minibenchmarks (AXPY and DOT product), miniapps (LULESH, MiniFE, and SNAP-LAMMPS), and a scientific kernel based on the lattice Boltzmann method.
The Open MPI for Exascale (OMPI-X) project was one of two in the Exascale Computing Project (ECP) focused on advancing the MPI ecosystem. The OMPI-X team worked with other MPI Forum members to champion several important features for inclusion in the MPI 4.0, 4.1, and upcoming 5.0 MPI standard versions, in support of the needs of exascale applications and systems. The team also worked with the larger Open MPI community to bring implementations of these new features and other enhancements into Open MPI, one of the leading open-source implementations of the MPI interface. Here, this paper describes the motivation for the work of the OMPI-X project in the context of exascale computing needs, the nature of the resulting new capabilities in the MPI standard, and how they were implemented in the Open MPI library. Features include improved support for “MPI + X” programming models through partitioned communications and support for user-level threading, sessions, fault tolerance through the user-level fault mitigation (ULFM) and Reinit models, and other features. We also discuss enhancements to Open MPI providing improved performance and scalability for existing features, such as collective operations, one-sided operations, support for the Slingshot-11 interconnect of the initial exascale systems, and how the OMPI-X team worked to improve quality assurance for the Open MPI library, particularly on platforms of interest to the Department of Energy community.
The Exascale Computing Project (ECP) Software Technology and Co-Design teams addressed the growing complexities in high-performance computing (HPC) by developing scalable software libraries and tools that leverage exascale system capabilities. As we enter the exascale era, the need for reusable, optimized software solutions that can handle the unique challenges posed by these systems becomes increasingly important. The primary challenges the ECP teams faced were to create software libraries and tools that are performant on exascale architectures and portable and usable across diverse hardware platforms. Efforts addressed issues related to concurrent execution, memory management, and the integration of heterogeneous computing resources, such as GPUs from multiple vendors. The ECP’s strategy involved a structured development process encompassing the creation, optimization, and deployment of software in collaboration with industry, academia, and national laboratories. The project was organized into several technical areas: co-design of domain-specific suites with target applications, programming models and runtimes, development tools, mathematical libraries, data and visualization tools, and software ecosystem and delivery mechanisms. ECP has successfully developed a large portfolio of software libraries and tools that demonstrate significant improvements in performance and scalability on exascale systems. These products have been integrated into the Department of Energy’s computing facilities, supporting various scientific applications and ensuring robust performance across different hardware setups. ECP advancements in software development for exascale computing highlight the importance of a collaborative and adaptive approach to handling next-generation HPC systems complexities. The lessons learned emphasize the need for continuous engagement with end-users and vendors, and the importance of maintaining a balance between innovation and practical implementation. Future efforts will focus on ensuring scalability, keeping pace with rapid hardware advancements, and further enhancing the interoperability and usability of the software ecosystem. In conclusion, subsequent articles in this special issue provide in-depth discussions and case studies into specific library and tool efforts.
The advent of exascale supercomputers heralds a new era of scientific discovery, yet it introduces significant architectural challenges that must be overcome for MPI applications to fully exploit its potential. Among these challenges is the adoption of heterogeneous architectures, particularly the integration of GPUs to accelerate computation. Additionally, the complexity of multithreaded programming models has also become a critical factor in achieving performance at scale. The efficient utilization of hardware acceleration for communication, provided by modern NICs, is also essential for achieving low latency and high throughput communication in such complex systems. In response to these challenges, the MPICH library, a high-performance and widely used Message Passing Interface (MPI) implementation, has undergone significant enhancements. Here, this paper presents four major contributions that prepare MPICH for the exascale transition. First, we describe a lightweight communication stack that leverages the advanced features of modern NICs to maximize hardware acceleration. Second, our work showcases a highly scalable multithreaded communication model that addresses the complexities of concurrent environments. Third, we introduce GPU-aware communication capabilities that optimize data movement in GPU-integrated systems. Finally, we present a new datatype engine aimed at accelerating the use of MPI derived datatypes on GPUs. These improvements in the MPICH library not only address the immediate needs of exascale computing architectures but also set a foundation for exploiting future innovations in high-performance computing. By embracing these new designs and approaches, MPICH-derived libraries from HPE Cray and Intel were able to achieve real exascale performance on OLCF Frontier and ALCF Aurora respectively.
This paper proposes a machine-learning (ML)-aided cognitive approach for effective bandwidth reconfiguration in optically interconnected datacenter/high-performance computing (HPC) systems. The proposed approach relies on a Hyper-X-like architecture augmented with flexible-bandwidth photonic interconnections at large scales using a hierarchical intra/inter-POD photonic switching layout. We first formulate the problem of the connectivity graph and routing scheme optimization as a mixed-integer linear programming model. A two-phase heuristic algorithm and a joint optimization approach are devised to solve the problem with low time complexity. Then, we propose an ML-based end-to-end performance estimator design to assist the network control plane with intelligent decision making for bandwidth reconfiguration. Numerical simulations using traffic distribution profiles extracted from HPC applications traces as well as random traffic matrices verify the accuracy performance of the ML design estimator ( < <#comment/> 9 % <#comment/> error) and demonstrate up to 5 × <#comment/> throughput gain from the proposed approach compared with the baseline Hyper-X network using fixed all-to-all intra/inter-portable data center interconnects.
Cellulosic butanol is a very promising renewable fuel to consider for the future transportation market. However, the seasonal availability of the raw materials, high maintenance cost, and high logistical cost of the biomass energy supply chain are the main factors impeding the commercialization and large-scale-production of this energy source. Furthermore, research focusing on an environmental or green supply chain network design of cellulosic butanol has been insufficient. Here, this study focused on designing a green supply chain network for cellulosic butanol. A life cycle analysis was integrated into a multi-objective linear programming model to optimize the cellulosic butanol supply chain network. With the objectives of maximizing the economic profits and minimizing the greenhouse gas emissions, the proposed model can optimize the location and size of a bio-butanol production plant. The mathematical model was applied to a case study in the state of Missouri, and solved the tradeoff between the feedstock and market availabilities of sorghum stem bio-butanol.
Deep C Wind, a consortium headed by the University of Maine will test the first U.S. offshore wind platforms in 2012. In advance of final siting and permitting of the test turbines off Monhegan Island, residents of the island off Maine require reassurance that the noise levels from the test turbines will not disturb them. Pacific Northwest National Laboratory, at the request of the University of Maine, and with the support of the U.S. Department of Energy Wind Program, modeled the acoustic output of the planned test turbines.
The increasing on-chip parallelism has some substantial implications for HPC applications. Currently, hybrid programming models (typically MPI+OpenMP) are employed for mapping software to the hardware in order to leverage the hardware?s architectural features. In this paper, we present an approach that automatically introduces thread level parallelism into Chombo, a parallel adaptive mesh refinement framework for finite difference type PDE solvers. In Chombo, core algorithms are specified in the ChomboFortran, a macro language extension to F77 that is part of the Chombo framework. This domain-specific language forms an already used target language for an automatic migration of the large number of existing algorithms into a hybrid MPI+OpenMP implementation. It also provides access to the auto-tuning methodology that enables tuning certain aspects of an algorithm to hardware characteristics. Performance measurements are presented for a few of the most relevant kernels with respect to a specific application benchmark using this technique as well as benchmark results for the entire application. The kernel benchmarks show that, using auto-tuning, up to a factor of 11 in performance was gained with 4 threads with respect to the serial reference implementation.
The primary goal of the Minimizing System Noise Effects For Extreme-Scale Scientific Simulation through Function Delegation project is to eliminate or at best strongly minimize the impact of the noise introduced by the operating system, during large scale parallel applications runs. Collective communication operations are a basic building block for parallel programing models and scientific applications. These operations often dominate execution time of applications and tend to limit their scalability. In order to address this challenge, we evaluated different strategies to adapt the collective communications underlying topologies to the hardware architecture in order to provide increased levels of performance to the parallel applications.
Load imbalance can lead to wasted CPU hours especially when running on a large number of processors. Achieving the best parallel efficiency for a program requires optimal load balancing which is a NP-hard problem. Charm++, a migratable objects based programming model, provides a measurement-based dynamic load balancing frame work. This paper explores the use of graph partitioning algorithms, traditionally used for partitioning physical domains/meshes, for measurement based dynamic load balancing of parallel applications. In particular, we present repartitioning methods developed in a graph partitioning toolbox called Scotch that consider the previous mapping to minimize migration costs. We also discuss a new imbalance reduction algorithm for graphs with irregular load distributions. We compare several load balancing algorithms using a micro-benchmark and the NAS BT multi-zone bench mark. New algorithms developed in Scotch lead to better performance compared to other existing partitioners, both in terms of the application execution time and fewer number of objects migrated.
All activities of the Exascale Co-design Center for Materials in Extreme Environments (ExMatEx) are focused on the two ultimate goals of the project: (1) demonstrating and delivering a prototype scale-bridging materials science application based upon adaptive physics refinement, and (2) identifying the requirements for the exascale ecosystem that are necessary to perform computational materials science simulations (both single- and multi-scale). During the first year of ExMatEx, our focus was on establishing how we do computational materials science, by developing an initial suite of flexible proxy applications. These “proxy apps” are the primary vehicle for the co-design process, involving assessments and tradeoff evaluations both within the ExMatEx team, and with the entire exascale ecosystem. These interactions have formed the basis of our second year activities. The set of artifacts from these co-design interactions are the lessons learned, that are used to re-express the applications and algorithms within the context of emerging architectures, programming models, and runtime systems.
The following report explains the moisture-related concerns for High R-value wall assemblies and discusses past Building America research work that informs this study. Hygrothermal simulations were prepared for several common approaches to High R-value wall construction in six cities (Houston, Atlanta, Seattle, St. Louis, Chicago, and International Falls) representing a range of climate zones (2, 3, 4C, 4, 5A, and 7, respectively). The simulations are informed by experience gained from past research in this area and validated by field measurement and forensic experience. The modeling program was developed to assess the moisture durability of the wall assemblies based on three primary sources of moisture: construction moisture, air leakage condensation, and bulk water leakage. The peak annual moisture content of the wood based exterior sheathing was used to comparatively analyze the response to the moisture loads for each of the walls in each given city. Walls which experienced sheathing moisture contents between 20% and 28% were identified as risky, whereas those exceeding 28% were identified as very high risk. All of the wall assemblies perform well under idealized conditions. However, only the walls with exterior insulation, or cavity insulation which provides a hygrothermal function similar to exterior insulation, perform adequately when exposed to moisture loads. Walls with only cavity insulation are particularly susceptible to air leakage condensation. None of the walls performed well when a precipitation based bulk water leak was introduced to the backside of the sheathing, emphasizing the importance of proper flashing details.