Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “distributed parallel programming”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Influence of Antarctic and Greenland Continental Shelf Circulation on High‐Latitude Oceans in E3SM

The science objectives of this project are to simulate and understand the impacts of both deep-basin warm-water intrusions and land-ice melt on the continental shelf circulations and sea-ice distributions around the margins of Greenland and Antarctica. As well, the role of subsurface ocean heat from the Atlantic on declining sea-ice cover in the Arctic is explored. Mesoscale processes and fine bathymetry are implicated in cross-shelf property transports around both Greenland and Antarctica. Therefore, we configured and ran an atmospheric reanalysis-forced global ocean/sea-ice simulation on a grid that reduces from 8 km at the Equator to 2 km at the poles (UH8to2) with 60 vertical levels. It was produced using the Energy Exascale Earth System Model ‘‘HiLAT’’ code (E3SMv0-HiLAT) that uses the Parallel Ocean Program (POP) and CICE5 as its ocean and sea-ice components, respectively. Two main UH8to2 simulations were carried out: one for 1975-2009 and the other for July 2016-2020 after it was initialized from a 1/25° data-assimilative ocean/sea-ice prediction system ocean/sea-ice state. The UH8to2 is not coupled to an active land-ice model. Rather, land-ice melt is represented by observationally informed freshwater fluxes (FWFs). Short (multi-year) UH8to2 simulations were conducted to understand sensitivities when Greenland ice sheet (GrIS) melt is released only at the ocean surface or when it is distributed over the upper water column in accordance with fjord melt plume behavior; these cases were compared with a no GrIS melt case. West Greenland continental shelf currents were fastest in the vertical distribution case and an increase in baroclinic conversion at the shelf break associated with increased eddy kinetic energy was found relative to the surface release case. Further, salinity is lower and meltwater volume greater in the eastern Labrador Sea in the vertical distribution case. For the Arctic, the veracity of the UH8to2 was evaluated for 2017-2020 using available observations. Simulated seasonal sea-ice thickness and concentration are realistic, but the ice is unrealistically thin in the central and eastern Arctic in the fall. Comparisons of vertical sections of ocean temperature, salinity, and buoyancy collected from Ice-Tethered Profilers (ITPs) in the eastern Arctic in the fall and winter of 2019/2020 and co-located/concurrent UH8to2 fields show the stratification over the top 100 m of the water column is too low in the model, the simulated mixed layer too deep, and the simulated subsurface Atlantic Water (AW) too warm; these biases may contribute to the sea-ice biases. A model intercomparison study using the UH8to2 and a forced 1/25° regional Arctic ocean/sea-ice (uses the HYbrid Coordinate Ocean Model and CICE5) simulation further investigates the relationship between AW and sea-ice in the eastern Arctic. The models show a mesoscale-rich pulse of Atlantic Water extending into the eastern basin that reaches maximum intensity in late winter of 2018, after which it decreases in strength. Concurrent and co-located sea-ice melt or the inhibition of sea-ice growth is seen and is attributed to halocline mesoscale eddies doming into the mixed layer with convection bringing this heat into the vicinity of the sea-ice.

58 GEOSCIENCES↗
DOE OSTI2019

Exploring MPI Communication Models for Graph Applications Using Graph Matching as a Case Study

Traditional implementations of parallel graph operations on distributed memory platforms are written using Message Passing Interface (MPI) point to point communication primitives such as Send-Recv (blocking and nonblocking). Apart from this classical model, the MPI community has over the years added other communication models; however, their suitability for handling the irregular traffic workloads typical of graph operations remain comparatively less explored. Our aim in this paper is to study these relatively underutilized communication models of MPI for graph applications. More specifically, we evaluate MPI’s one-sided programming, or Remote Memory Access (RMA), and nearest neighborhood collectives using a process graph topology. There are features in these newer models that are intended to better map to irregular communication patterns, as exemplified in graph algorithms. As a concrete application for our case study, we use distributed memory implementations of a weighted graph matching algorithm to investigate performances of MPI-3 RMA and neighborhood collective operations compared to nonblocking Send- Recv. A matching in a graph is a subset of edges such that no two matched edges are incident on the same vertex. A maximum weight matching is a matching of maximum weight computed as the sum of the weights of matched edges. Algorithms for optimal matching have quadratic complexity and are difficult to parallelize. More importantly, execution of graph matching is dominated by high volume of irregular memory accesses, making it an ideal candidate for studying the effects of various MPI communication models on graph applications at scale. Our neighborhood collectives and RMA implementations yields up to 6× speedup over traditional optimized nonblocking Send-Recv implementations, on thousands of cores of the NERSC Cori supercomputer. We believe the lessons learned from this case study can be adopted to benefit a wider range of graph application codes.

Ghosh, Sayan↗
DOE OSTI2020

Establishing a Technical Assistance Network to Build Capacity in Southwest Alaska (Southwest Alaska Energy Network - Final Report)

The Southwest Alaska Municipal Conference (SWAMC) is a non-profit regional membership economic development organization that represents the Aleutian/Pribilof Islands, Bristol Bay, and Kodiak regions of southwest Alaska. SWAMC applied for the DOE-OIE Establishment of an Inter-Tribal Technical Assistance Energy Providers Network grant FOA to work with our partners to provide energy planning and project development technical assistance. The project team was made up of SWAMC, three regional organizations, a management consulting firm, and a panel of technical consultants. SWAMC sub-contracted with the three Alaska Native regional non-profit organizations – Aleutian Pribilof Islands Association (APIA), Bristol Bay Native Association (BBNA), and Kodiak Area Native Association (KANA) – to fund full or partial Regional Energy Coordinator (REC) positions. The project period ran from September 2016 to March 2020. The project goal was to help southwest Alaska regional tribal partners and communities to develop efficient and financially sustainable structures for identifying and developing energy projects that enhance community resiliency and energy sustainability. This project established energy coordinators and management structures in the Aleutian, Bristol Bay, and Kodiak regions to expand technical assistance capacity of regional residents; demonstrate this capacity by advancing energy efficiency, heat, and power supply projects; and secure long-term funding commitments to establish a sustained technical assistance structure. The project team expanded technical assistance capacity of energy coordinators and regional stakeholders in several ways: by providing funding for the SWAMC project manager to attend three Office of Indian Energy trainings; for energy coordinators to attend numerous energy conferences; for utility clerks from several villages to receive one-on-one reporting training on Alaska’s Power Cost Equalization electric subsidy program; and for the Kodiak REC to complete the Arctic Remote Energy Networks Academy and NREL’s Executive Energy Leadership Academy. The energy coordinators demonstrated and shared their increased capacity by hosting several public events: SWAMC hosted two full-day energy workshops in February 2017 and 2018; the Kodiak REC hosted seven Energy Committee meetings for Kodiak stakeholders and gave several presentations at other events; and SWAMC and BBNA organized a Bristol Bay Regional Energy Visioning Session in May 2019. The project team created platforms to both share and request information to involve energy stakeholders in this project, including an energy website, a Facebook group, a periodic newsletter, surveys, mass emails, and paper mailers. An increase in regional capacity was demonstrated through several grant awards, including a $1.2 million USDA grant for Akhiok for an electric distribution infrastructure replacement; an AHFC Kickstarter grant for Aleknagik to audit 2 Tribal and 3 City buildings; and installation of an Air Source Heat Pump demonstration project in Atka. Two communities and one region – Ouzinkie (May 2017), Ugashik (July 2017), and the Bristol Bay region (May 2019) – utilized DOE’s technical assistance services to hold Strategic Energy Planning sessions with NREL and DOE facilitation assistance. And in early 2018, SWAMC established a parallel program, funded through a USDA Energy Audit and Renewable Energy Development grant to provide subsidized energy audits for small businesses in the region. SWAMC and partners have now completed energy audits of over 60 businesses (buildings and fishing vessels) and are currently operating a third round of the USDA program. Fifteen of those business owners have now received additional grant funding to cover 25% of the cost of the energy efficiency upgrades identified in the audit. This technical assistance structure will be sustained beyond DOE grant funding in several forms. As a sign of increased grant writing and project management capacity, the Kodiak Regional Energy Coordinator applied for and received a USDA Community Facilities Technical Assistance and Training grant to continue work begun under this program. Energy coordination tasks have been folded into existing economic development positions at SWAMC and at BBNA, ensuring long-term outreach and support in the region.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing

The next generation HPC and data centers are likely to be reconfigurable and data-centric due to the trend of hardware specialization and the emergence of data-driven applications. In this work, we propose ARENA – an asynchronous reconfigurable accelerator ring architecture as a potential scenario on how the future HPC and data centers will be like. Despite using the coarse-grained reconfigurable arrays (CGRAs) as the substrate platform, our key contribution is not only the CGRA-cluster design itself, but also the ensemble of a new architecture and programming model that enables asynchronous tasking across a cluster of reconfigurable nodes, so as to bring specialized computation to the data rather than the reverse. We presume distributed data storage without asserting any prior knowledge on the data distribution. Hardware specialization occurs at runtime when a task finds the majority of data it requires are available at the present node. In other words, we dynamically generate specialized CGRA accelerators where the data reside. The asynchronous tasking for bringing computation to data is achieved by circulating the task token, which describes the dataflow graphs to be executed for a task, among the CGRA cluster connected by a fast ring network. Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement (53.9 percent). Compared with contemporary compute-centric parallel models, ARENA can bring on average 4.37× speedup. The synthesized CGRAs and their task-dispatchers only occupy 2.93mm 2 chip area under 45nm process technology and can run at 800MHz with on average 759.8mW power consumption. ARENA also supports the concurrent execution of multi-applications, offering ideal architectural support for future high-performance parallel computing and data analytics systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Center for Computing Research Highlights

Sandia has a legacy of leadership in the advancement of high performance computing (HPC) at extreme scales. First-of-a-kind scalable distributed-memory parallel platforms such as the Intel Paragon, ASCI Red (the world’s first teraflops computer), and Red Storm (co-developed with Cray) helped form the basis for one of the most successful supercomputer product lines ever: the Cray XT series. Sandia also has pioneered system software elements—including lightweight operating systems, the Portals network programming interface, advanced interconnection network designs, and scalable I/O— that are critical to achieving scalability on large computing systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

A UPC++ Actor Library and Its Evaluation On a Shallow Water Proxy Application

Programmability is one of the key challenges of Exascale Computing. Using the actor model for distributed computations may be one solution. The actor model separates computation from communication while still enabling their overlap. Each actor possesses specified communication endpoints to publish and receive information. Computations are undertaken based on the data available on these channels. We present a library that implements this programming model using UPC++, a PGAS library, and evaluate three different parallelization strategies, one based on rank-sequential execution, one based on multiple threads in a rank, and one based on OpenMP tasks. In an evaluation of our library using shallow water proxy applications, our solution compares favorably against an earlier implementation based on X10, and a BSP-based approach.

Pöppl, Alexander↗
DOE OSTI2025

Multi-GPU porting of a phase-change cascaded lattice Boltzmann method for three-dimensional pool boiling simulations

The Lattice Boltzmann method (LBM) has proven effective in simulating phase-change phenomena, such as melting, solidification, evaporation, and boiling. In this work, we develop a highly parallelized multi-GPU implementation of LBM for three-dimensional pool boiling simulations. The code is based on the OpenACC programming model, which enables the code to be deployed efficiently on multi-core CPUs, GPUs, and potentially other accelerators, without the need for architecture-specific rewrites. To support large-scale simulations, the domain is decomposed and distributed across multiple compute nodes using MPI. We demonstrate that the code exhibits excellent scaling properties, with ideal strong-scaling running with up to 256 GPUs on the MareNostrum5 cluster.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

DARMA-Kokkos Data and Execution Interoperability WBS 2.3.1.04 Milestone 16 (ECP Milestone Report)

DARMA (Distributed Asynchronous Resilient Models for Applications) is a runtime library supporting the Sandia ATDM (Advanced Technology Development and Mitigation) program. The main application drivers fall within the ECP milestone 2.2.5.03 ADNN03-ASC ATDM SNL Application, which includes applications that require load balancing and asynchronous communication for high performance. The DARMA runtime infrastructure has been modified to be compatible with Kokkos/OpenMP parallelization within tasks, which is a critical requirement for high performance for the Sandia ATDM apps. DARMA development has occurred in parallel with a verification milestone for ATDM in FY18. For FY19, DARMA should impact ATDM by enabling dynamic load balancing and communication through only incremental changes to the existing verified MPI codes. DARMA can now support the intra-kernel thread parallelization in the parent MPI apps, allowing DARMA to be easily added without rewriting individual math kernels. The results presented here demonstrate the DARMA results for an MPI mini-app.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Coupling Big Data Analytics and Reactive Transport Modeling for Cost-effective Groundwater Monitoring - 17163

This study presents an innovative approach for sustainable and cost-effective groundwater monitoring. This approach takes advantage of recent advances in various technologies: (1) in situ autonomous sensors, (2) big data analytics, and (3) parallel high-performance computing for flow and reactive transport modeling. In situ sensors are used to periodically measure the key variables (such as pH, redox potential, electrical conductivity, and groundwater level), which control contaminant mobility and the plume spatial and temporal distribution. Based on a limited number of groundwater sampling, the data analytics methods-data mining and machine learning-allow us to identify and quantify the correlations between the in situ-measured variables and contaminant concentrations, and also to detect significant changes associated with the plume mobility. In addition, a state-of-the-art parallel numerical flow and reactive transport simulator Amanzi, and uncertainty quantification software Agni are used to provide an improved physical and mechanistic understanding of the contaminated groundwater system behavior, and to predict the long-term plume distribution for optimizing and adapting the monitoring strategy. Amanzi and Agni were developed as part of the Advanced Simulation Capability for Environmental Management (ASCEM) program of the DOE Office of Environmental Management. Such modeling is critical, particularly, for assessing the impact of climate change and associated hydrological shifts. The developed approach is expected to significantly reduce the groundwater sampling frequency and associated cost. In addition, the real-time information on plume mobility serves as an early warning system, improving the resiliency of contaminated or potentially contaminated sites. We demonstrate this approach using as an example the Savannah River Site (SRS) F-Area, where groundwater is contaminated by various radionuclides, including uranium, tritium and technetium. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2026

SAIGE-GPU: accelerating genome- and phenome-wide association studies using GPUs

Genome-wide association studies (GWAS) at biobank scale are computationally intensive, especially for admixed populations requiring robust statistical models. SAIGE is a widely used method for generalized linear mixed-model GWAS but is limited by its CPU-based implementation, making phenome-wide association studies impractical for many research groups. We developed SAIGE-GPU, a GPU-accelerated version of SAIGE that replaces CPU-intensive matrix operations with GPU-optimized kernels. The core innovation is distributing genetic relationship matrix calculations across GPUs and communication layers. Applied to 2068 phenotypes from 635 969 participants in the Million Veteran Program, including diverse and admixed populations, SAIGE-GPU achieved a 5-fold speedup in mixed model fitting on supercomputing infrastructure and cloud platforms. We further optimized the variant association testing step through multi-core and multi-trait parallelization. Deployed on Google Cloud Platform and Azure, the method provided substantial cost and time savings. Source code and binaries are available for download at https://github.com/saigegit/SAIGE/tree/SAIGE-GPU-1.3.3. A code snapshot is archived at Zenodo for reproducibility (DOI: [10.5281/zenodo.17642591]). SAIGE-GPU is available in a containerized format for use across HPC and cloud environments and is implemented in R/C++ and runs on Linux systems.

Rodriguez, Alex [Argonne National Laboratory (ANL)↗
DOE OSTI2013

Heterogeneous scalable framework for multiphase flows

Two categories of challenges confront the developer of computational spray models: those related to the computation and those related to the physics. Regarding the computation, the trend towards heterogeneous, multi- and many-core platforms will require considerable re-engineering of codes written for the current supercomputing platforms. Regarding the physics, accurate methods for transferring mass, momentum and energy from the dispersed phase onto the carrier fluid grid have so far eluded modelers. Significant challenges also lie at the intersection between these two categories. To be competitive, any physics model must be expressible in a parallel algorithm that performs well on evolving computer platforms. This work created an application based on a software architecture where the physics and software concerns are separated in a way that adds flexibility to both. The develop spray-tracking package includes an application programming interface (API) that abstracts away the platform-dependent parallelization concerns, enabling the scientific programmer to write serial code that the API resolves into parallel processes and threads of execution. The project also developed the infrastructure required to provide similar API s to other application. The API allow object-oriented Fortran applications direct interaction with Trilinos to support memory management of distributed objects in central processing units (CPU) and graphic processing units (GPU) nodes for applications using C++.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

PETSc/TAO Users Manual V.3.21

This manual describes the use of the Portable, Extensible Toolkit for Scientific Computation (PETSc) and the Toolkit for Advanced Optimization (TAO) for the numerical solution of partial differential equations (PDEs) and related problems on high-performance computers. PETSc/TAO is a suite of data structures and routines that provide the building blocks for implementing large-scale application codes on parallel (and serial) computers. PETSc uses the MPI standard for all distributed memory communication. PETSc/TAO includes a large suite of parallel linear solvers, nonlinear solvers, time integrators, and optimizers that may be used in application codes written in Fortran, C, C++, and Python (via petsc4py; see Getting Started ). The library is organized hierarchically, enabling users to employ the abstraction level most appropriate for a particular problem. By using techniques of object-oriented programming, PETSc provides enormous flexibility for users.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

SU-G-TeP1-06: Fast GPU Framework for Four-Dimensional Monte Carlo in Adaptive Intensity Modulated Proton Therapy (IMPT) for Mobile Tumors

Purpose: To demonstrate the feasibility of fast Monte Carlo (MC) treatment planning and verification using four-dimensional CT (4DCT) for adaptive IMPT for lung cancer patients. Methods: A validated GPU MC code, gPMC, has been linked to the patient database at our institution and employed to compute the dose-influence matrices (Dij) on the planning CT (pCT). The pCT is an average of the respiratory motion of the patient. The Dijs and patient structures were fed to the optimizer to calculate a treatment plan. To validate the plan against motion, a 4D dose distribution averaged over the possible starting phases is calculated using the 4DCT and a model of the time structure of the delivered spot map. The dose is accumulated using vector maps created by a GPU-accelerated deformable image registration program (DIR) from each phase of the 4DCT to the reference phase using the B-spline method. Calculation of the Dij matrices and the DIR are performed on a cluster, with each field and vector map calculated in parallel. Results: The Dij production takes ∼3.5s per beamlet for 10e6 protons, depending on the energy and the CT size. Generating a plan with 4D simulation of 1000 spots in 4 fields takes approximately 1h. To test the framework, IMPT plans for 10 lung cancer patients were generated for validation. Differences between the planned and the delivered dose of 19% in dose to some organs at risk and 1.4/21.1% in target mean dose/homogeneity with respect to the plan were observed, suggesting potential for improvement if adaptation is considered. Conclusion: A fast MC treatment planning framework has been developed that allows reliable plan design and verification for mobile targets and adaptation of treatment plans. This will significantly impact treatments for lung tumors, as 4D-MC dose calculations can now become part of planning strategies.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

ATLAS Data Analysis using a Parallel Workflow on Distributed Cloud-based Services with GPUs

A new type of parallel workflow is developed for the ATLAS experiment at the Large Hadron Collider, that makes use of distributed computing combined with a cloud-based infrastructure. This has been developed for a specific type of analysis using ATLAS data, one popularly referred to as Simulation-Based Inference (SBI). The JAX library is used for the parts of the workflow to compute gradients as well as accelerate program execution using just-in-time compilation, which becomes essential in a full SBI analysis and can also offer significant speed-ups in more traditional types of analysis.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2019

Red Storm Case Study

Sandia and Cray Inc. co-developed Red Storm, a distributed memory, massively paralleled highperformance supercomputer modeled on ASCI Redl, to run computer codes used for conducting materials science simulations for national security. Supercomputers have some of the fastest highperformance systems available and are used primarily for scientific and engineering work requiring exceedingly high-speed computations. Unlike conventional computers, supercomputers have large storage capacity; more than one central processing unit to rapidly retrieve stored data and program instructions; and input/output capability.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2013

A REST-FRAME OPTICAL VIEW ON z {approx} 4 GALAXIES. I. COLOR AND AGE DISTRIBUTIONS FROM DEEP IRAC PHOTOMETRY OF THE IUDF10 AND GOODS SURVEYS

We present a study of rest-frame UV-to-optical color distributions for z {approx} 4 galaxies based on the combination of deep HST/ACS+WFC3/IR data with Spitzer/IRAC imaging. In particular, we use new, ultra-deep data from the IRAC Ultradeep Field program (IUDF10), together with previous, public IRAC data over the GOODS fields. Our sample contains a total of {approx}2600 galaxies selected as B-dropout Lyman-break Galaxies in the HUDF and its deep parallel field HUDF09-2, as well as GOODS-North/South. This sample is used to investigate the UV continuum slopes {beta} and Balmer break colors (J{sub 125} - [4.5]) as a function of rest-frame optical luminosity (using [4.5] to avoid optical emission lines). We find that galaxies at M{sub z} < -21.5 (roughly corresponding to L{sup *}{sub z{approx}4}) are significantly redder than their lower luminosity counterparts. The UV continuum slopes and the J{sub 125} - [4.5] colors are well correlated, indicating that the dust reddening at these redshifts is better described by an SMC-like extinction curve, rather than the typically assumed Calzetti reddening. After dust correction, we find that the galaxy population shows mean stellar population ages in the range 10{sup 8.5} to 10{sup 9} yr, with a dispersion of {approx}0.5 dex, and only weak trends as a function of luminosity. Only a small fraction of galaxies shows Balmer break colors consistent with extremely young ages, younger than 100 Myr. Under the assumption of smooth star-formation histories, this fraction is 12%-19% for galaxies at M{sub z} < -19.75. Our results are consistent with a gradual build-up of stars and dust in galaxies at z > 4 with only a small fraction of stars being formed in short, intense bursts of star-formation.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Usability and Optimization Improvements in MOOSE

The Multiphysics Object-Oriented Simulation Environment (MOOSE) framework is a foundational capability used by the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program to create over 15 different simulation tools for advanced nuclear reactors. Due to MOOSE’s broad use, improvements to the framework in support of modeling and simulation goals are critical to the program. Such improvements can take many forms, including optimization, improved user experience, streamlined application programming interfaces (APIs), parallelism, and new capabilities. The work described in this report was conducted in direct support of the simulation tools and has already been deployed. The capabilities were implemented in the same order as they are covered in this report: multiple nonlinear systems in the same input file, implementation of generic field transfers and other transfer system enhancements, support for stateful material property redistribution for adaptivity and distributed meshes, and dynamic linking and loading of individually compiled applications. These four additions are fundamental capabilities that will be leveraged by many NEAMS applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Massively scalable workflows for quantum chemistry: BigChem and ChemCloud

Electronic structure theory, i.e., quantum chemistry, is the fundamental building block for many problems in computational chemistry. Here we present a new distributed computing framework (BigChem), which allows for an efficient solution of many quantum chemistry problems in parallel. BigChem is designed to be easily composable and leverages industry-standard middleware (e.g., Celery, RabbitMQ, and Redis) for distributed approaches to large scale problems. BigChem can harness any collection of worker nodes, including ones on cloud providers (such as AWS or Azure), local clusters, or supercomputer centers (and any mixture of these). BigChem builds upon MolSSI packages, such as QCEngine to standardize the operation of numerous computational chemistry programs, demonstrated here with Psi4, xtb, geomeTRIC, and TeraChem. BigChem delivers full utilization of compute resources at scale, offers a programable canvas for designing sophisticated quantum chemistry workflows, and is fault tolerant to node failures and network disruptions. We demonstrate linear scalability of BigChem running computational chemistry workloads on up to 125 GPUs. Finally, we present ChemCloud, a web API to BigChem and successor to TeraChem Cloud. ChemCloud delivers scalable and secure access to BigChem over the Internet.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗