Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Parallel Supercomputers”

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 451 records · Page 25

Hvac: Removing I/O Bottleneck for Large-Scale Deep Learning Applications

Scientific communities are increasingly adopting deep learning (DL) models in their applications to accelerate scientific discovery processes. However, with rapid growth in the computing capabilities of HPC supercomputers, large-scale DL applications have to spend a significant portion of training time performing I/O to a parallel storage system. Previous research works have investigated optimization techniques such as prefetching and caching. Unfortunately, there exist non-trivial challenges to adopting the existing solutions on HPC supercomputers for large-scale DL training applications, which include non-performance and/or failures at extreme scale, lack of portability and generality in design, complex deployment methodology, and being limited to a specific application or dataset. To address these challenges, we propose High-Velocity AI Cache (HVAC), a distributed read-cache layer that targets and fully exploits the node-local storage or near node-local storage technology. HVAC seamlessly accelerates read I/O by aggregating node-local or near node-local storage, avoiding metadata lookups and file locking while preserving portability in the application code. We deploy and evaluate HVAC on 1,024 nodes (with over 6000 NVIDIA V100 GPUS) of the Summit supercomputer. In particular, we evaluate the scalability, efficiency, accuracy, and load distribution of HVAC compared to GPFS and XFS-on-NVMe. With four different DL applications, we observe an average 25 % performance improvement atop GPFS and 9% drop against XFS-on-NVMe, which scale linearly and are considered the performance upper bound. We envision HVAC as an important caching library for upcoming HPC supercomputers such as Frontier.

Khan, Awais↗

Performance and Accuracy Implications of Parallel Split Physics-Dynamics Coupling in the Energy Exascale Earth System Atmosphere Model

Simultaneous calculation of atmospheric processes is faster than calculating processes one at a time. This type of parallelism is beneficial or perhaps even necessary to provide good performance on modern supercomputers, which achieve faster performance through increased processor count rather than improved clock speed. The scalability of the Energy Exascale Earth System Model (E3SM) Atmosphere Model (EAM) is limited by the fluid dynamics which scales up to the number of mesh cells in the global mesh. In contrast, the suite of physics parameterizations in EAM is scalable up to the total number of physics columns, which is an order of magnitude greater than the number of mesh cells. A proposed solution to unlocking the greater potential performance from the physics suite is to solve the physics and dynamics in parallel. This work represents a first attempt at parallel splitting of the grid-scale fluid dynamics model and the subgrid-scale physics parameterizations in a global atmosphere model. We will demonstrate that switching to parallel physics-dynamics coupling extends the scalability of the EAM to up to 3 times the previous peak scalability limit and is up to 20% faster than the sequentially split coupling at the highest core counts and the same time step. Decadal simulations of both coupling approaches show very little impact to the model climate. This improved performance does not come without drawbacks, however. Parallel splitting requires a shorter time step and other modifications which largely offset performance gains. A mass fixer is required for conservation. Techniques for mitigating these issues are also discussed.

97 MATHEMATICS AND COMPUTING↗

A Scalable Parallel Hypergraph Generator (HyGen)

Graphs are extensively used to model real-world complex systems. An edge in a graph can model pairwise relationships. However, multiway relationships (connections between three or more vertices) are common in many complex systems such as cellular process, image segmentation, and circuit design. A graph edge cannot model multiway relationships. A hypergraph, which can connect more than two vertices, is thus a better option to model multiway relationships. A large-scale hypergraph analysis has the potential to find useful insights from a complex system and assist in knowledge discovery. Currently a limited number of hypergraphs exists that are representative of real-world datasets. Moreover, real-world hypergraph datasets are small in size and inadequate to incorporate future needs. A graph generator that can produce large-scale synthetic hypergraphs can solve the above mentioned problems. In this paper, we present a scalable parallel hypergraph generator (HyGen) based on the Message Passing Interface (MPI) standard. To generate hypergraphs, HyGen takes the following parameter values as inputs: i) number of vertices, ii) number of hyperedges, iii) number of clusters, iv) vertex distribution, v) hyperedge distribution, vi) local cluster cardinality, and vii) global cluster cardinality. We have demonstrated that HyGen can generate hypergraphs of various sizes in a scalable fashion. HyGen takes approximately four minutes to generate a hypergraph with 4.8 million vertices, 1.6 million hyperedges, and 800 clusters using 1,024 processes on a leadership class computing platform. Our strong and weak scaling experiments on supercomputers demonstrate that HyGen can quickly create large-scale hypergraphs in a parallel manner, thus providing a useful capability for hypergraph analysis.

Hasan, S M Shamimul↗

Progress in Computational Aeroelasticity Using High Fidelity Flow and Structural Equations on Parallel Computers

Aeroelasticity which involves strong coupling of fluids, structures and controls is an important element in designing an aircraft. Computational aeroelasticity using low fidelity methods such as the linear aerodynamic flow equations coupled with the modal structural equations are well advanced. Though these low fidelity approaches are computationally less intensive, they are not adequate for the analysis of modern aircraft such as High Speed Civil Transport (HSCT) and Advanced Subsonic Transport (AST) which can experience complex flow/structure interactions. HSCT can experience vortex induced aeroelastic oscillations whereas AST can experience transonic buffet associated structural oscillations. Both aircraft may experience a dip in the flutter speed at the transonic regime. For accurate aeroelastic computations at these complex fluid/structure interaction situations, high fidelity equations such as the Navier-Stokes for fluids and the finite-elements for structures are needed. Computations using these high fidelity equations require large computational resources both in memory and speed. Current conventional supercomputers have reached their limitations both in memory and speed. As a result, parallel computers have evolved to overcome the limitations of conventional computers. This paper will address the transition that is taking place in computational aeroelasticity from conventional computers to parallel computers. The paper will address special techniques needed to take advantage of the architecture of new parallel computers. Results will be illustrated from computations made on iPSC/860 and IBM SP2 computer by using ENASERO code that directly couples the Euler/Navier-Stokes flow equations with high resolution finite-element structural equations.

Guruswamy, Guru P.↗

Parallel implementation of an algorithm for Delaunay triangulation

The theory and practice of implementing Tanemura's algorithm for 3D Delaunay triangulation on Intel's Gamma prototype, a 128 processor MIMD computer, is described. Efficient implementation of Tanemura's algorithm on a conventional, vector processing supercomputer is problematic. It does not vectorize to any significant degree and requires indirect addressing. Efficient implementation on a parallel architecture is possible, however. Speeds in excess of 20 times a single processor Cray Y-MP are realized on 128 processors of the Intel Gamma prototype.

Merriam, Marshal L.↗

Reducing Application Runtime Variability on Jaguar XT5

Operating system (OS) noise is defined as interference generated by the OS that prevents a compute core from performing ``useful'' work. Compute node kernel daemons, network interfaces, and other OS related services are major sources of such interference. This interference on individual compute cores can vary in duration and frequency, and can cause de-synchronization (jitter) in collective communication tasks and thus results in variable (degraded) overall parallel application performance. This behavior is more observable in large-scale applications using certain types of collective communication primitives, such as MPI\_Allreduce. This paper presents our effort towards reducing the overall effect of OS noise on our large-scale parallel applications. Our tests were performed on the quad-core Jaguar, the Cray XT5 at the Oak Ridge National Laboratory Leadership Computing Facility (OLCF). At the time of these tests, Jaguar was a 1.4 PFLOPS supercomputer with 149,504 compute cores and 8 cores per node. We aggregated OS noise sources onto a single core for each node. The scientific application was then run on six of the remaining cores in each node. Our results show that we were able to improve the MPI_Allreduce performance by two orders of magnitude. We demonstrated up to a 30% boost in the performance of the Parallel Ocean Program (POP) using this technique.

97 MATHEMATICS AND COMPUTING↗

A step towards the final frontier: Lessons learned from acceptance testing of the first HPE/Cray EX 3000 system at ORNL

Summary In this article, we summarize the deployment of the Air Force Weather (AFW) HPC11 system at Oak Ridge National Laboratory (ORNL) including the process followed to successfully complete acceptance testing of the system. HPC11 is the first HPE/Cray EX 3000 system that has been successfully released to its user community in a federal facility. HPC11 consists of two identical 800‐node supercomputers, Fawbush and Miller, with access to two independent and identical lustre parallel file systems. HPC11 is equipped with Slingshot 10 interconnect technology and relies on the HPE Performance Cluster Manager software for system configuration. ORNL has a clearly defined acceptance testing process used to ensure that every new system deployed can provide the necessary capabilities to support user workloads. We worked closely with HPE and AFW to develop a set of tests that used the United Kingdom's Meteorological Office's Unified Model and 4‐dimensional variational data assimilation. We also included benchmarks and applications from the Oak Ridge Leadership Computing Facility portfolio to fully exercise the HPE/Cray programming environment and evaluate the functionality and performance of the system. Acceptance testing of HPC11 required parallel execution of each element on Fawbush and Miller. In addition, careful coordination was needed to ensure successful acceptance of the newly deployed lustre file systems alongside the compute resources. In this work, we present test results from specific system components and provide an overview of the issues identified, challenges encountered, and the lessons learned along the way.

Melesse Vergara, Verónica G.↗

Quantum Electrodynamics Coupled-Cluster at Scale: High-Performance Implementation for Complex Systems

Coupled-cluster theory (CC) is a highly accurate and versatile method for simulating complex interactions within quantum systems. The extension of CC theory to model mixed electron-photon processes with quantum electrodynamics (QED) has improved our capability to predict cavity-modified chemistry, a field where photons are used as cost-effective and eco-friendly alternatives to catalyze/inhibit chemical reactions. However, calculations with CC methods, even without incorporating QED effects, are often prohibitively expensive. Simulations of larger systems require scalable infrastructures that exist for traditional CC methods but not for QED-CC methods. As such, we present a GPU-enabled, high-performance, open-source implementation of the quantum electrodynamics coupled-cluster method with single and double excitations (QED-CCSD) within the ExaChem quantum chemistry software package. ExaChem relies on the Tensor Algebra for Many-body Methods (TAMM) infrastructure: a parallel heterogeneous tensor library designed to achieve scalable performance on modern heterogeneous supercomputing platforms. Furthermore, we discuss theoretical foundations, algorithmic details, and numerical benchmarks to showcase the larger systems that ExaChem can simulate and how the integration of photonic degrees-of-freedom alters their ground-state properties.

Basis sets↗

Accelerating DCA++ (Dynamical Cluster Approximation) Scientific Application on the Summit supercomputer

Optimizing scientific applications on today’s accelerator-based high performance computing systems can be challenging, especially when multiple GPUs and CPUs with heterogeneous memories and persistent non-volatile memories are present. An example is Summit, an accelerator-based system at the Oak Ridge Leadership Computing Facility (OLCF) that is rated as the world’s fastest supercomputer to-date. New strategies are thus needed to expose the parallelism in legacy applications, while being amenable to efficient mapping to the underlying architecture.In this paper we discuss our experiences and strategies to port a scientific application, DCA++, to Summit. DCA++ is a highperformance research application that solves quantum manybody problems with a cutting edge quantum cluster algorithm, the dynamical cluster approximation.Our strategies aim to synergize the strengths of the different programming models in the code. These include: (a) streamlining the interactions between the CPU threads and the GPUs, (b) implementing computing kernels on the GPUs and decreasing CPU-GPU memory transfers, (c) allowing asynchronous GPU communications, and (d) increasing compute intensity by combining linear algebraic operations.Full-scale production runs using all 4600 Summit nodes attained a peak performance of 73.5 PFLOPS with a mixed precision implementation.We observed a perfect strong and weak scaling for the quantum Monte Carlo solver in DCA++, while encountering about 2× input/output (I/O) and MPI communication overhead on the time-to-solution for the full machine run. Our hardware agnostic optimizations are designed to alleviate the communication and I/O challenges observed, while improving the compute intensity and obtaining optimal performance on a complex, hybrid architecture like Summit.

Balduzzi, Giovanni↗

Finite element analysis in fluids; Proceedings of the Seventh International Conference on Finite Element Methods in Flow Problems, University of Alabama, Huntsville, Apr. 3-7, 1989

Recent advances in computational fluid dynamics are examined in reviews and reports, with an emphasis on finite-element methods. Sections are devoted to adaptive meshes, atmospheric dynamics, combustion, compressible flows, control-volume finite elements, crystal growth, domain decomposition, EM-field problems, FDM/FEM, and fluid-structure interactions. Consideration is given to free-boundary problems with heat transfer, free surface flow, geophysical flow problems, heat and mass transfer, high-speed flow, incompressible flow, inverse design methods, MHD problems, the mathematics of finite elements, and mesh generation. Also discussed are mixed finite elements, multigrid methods, non-Newtonian fluids, numerical dissipation, parallel vector processing, reservoir simulation, seepage, shallow-water problems, spectral methods, supercomputer architectures, three-dimensional problems, and turbulent flows.

Chung, T. J.↗

Multitasking domain decomposition fast Poisson solvers on the Cray Y-MP

The results of multitasking implementation of a domain decomposition fast Poisson solver on eight processors of the Cray Y-MP are presented. The object of this research is to study the performance of domain decomposition methods on a Cray supercomputer and to analyze the performance of different multitasking techniques using highly parallel algorithms. Two implementations of multitasking are considered: macrotasking (parallelism at the subroutine level) and microtasking (parallelism at the do-loop level). A conventional FFT-based fast Poisson solver is also multitasked. The results of different implementations are compared and analyzed. A speedup of over 7.4 on the Cray Y-MP running in a dedicated environment is achieved for all cases.

Chan, Tony F.↗

Predicting Cost/Performance Trade-Offs for Whitney: A Commodity Computing Cluster

Recent advances in low-end processor and network technology have made it possible to build a "supercomputer" out of commodity components. We develop simple models of the NAS Parallel Benchmarks version 2 (NPB 2) to explore the cost/performance trade-offs involved in building a balanced parallel computer supporting a scientific workload. We develop closed form expressions detailing the number and size of messages sent by each benchmark. Coupling these with measured single processor performance, network latency, and network bandwidth, our models predict benchmark performance to within 30%. A comparison based on total system cost reveals that current commodity technology (200 MHz Pentium Pros with 100baseT Ethernet) is well balanced for the NPBs up to a total system cost of around $1,000,000.

Becker, Jeffrey C.↗

Parallelization of the Flow Field Dependent Variation Scheme for Solving the Triple Shock/Boundary Layer Interaction Problem

A parallelized version of the Flowfield Dependent Variation (FDV) Method is developed to analyze a problem of current research interest, the flowfield resulting from a triple shock/boundary layer interaction. Such flowfields are often encountered in the inlets of high speed air-breathing vehicles including the NASA Hyper-X research vehicle. In order to resolve the complex shock structure and to provide adequate resolution for boundary layer computations of the convective heat transfer from surfaces inside the inlet, models containing over 500,000 nodes are needed. Efficient parallelization of the computation is essential to achieving results in a timely manner. Results from a parallelization scheme, based upon multi-threading, as implemented on multiple processor supercomputers and workstations is presented.

Schunk, Richard Gregory↗

Predicting Cost/Performance Trade-offs For Whitney: A Commodity Computing Cluster

Recent advances in low-end processor and network technology have made it possible to build a "supercomputer" out of commodity components. We develop simple models of the NAS Parallel Benchmarks version 2 (NPB 2) to explore the cost/performance trade-offs involved in building a balanced parallel computer supporting a scientific workload. By measuring single processor benchmark performance, network latency, and network bandwidth, and using closed form expressions detailing the number and size of messages sent by each benchmark, our models predict benchmark performance to within 30%. A comparison based on total system cost reveals that current commodity technology (200 MHz Pentium Pros with 100baseT Ethernet) is well balanced for the NPBs up to a total system cost of around $ 1,000,000.

Becker, Jeffrey C.↗

Implementation of an Open-Scenario, Long-Term Space Debris Simulation Approach

This paper provides a status update on the implementation of a flexible, long-term space debris simulation approach. The motivation is to build a tool that can assess the long-term impact of various options for debris-remediation, including the LightForce space debris collision avoidance concept that diverts objects using photon pressure [9]. State-of-the-art simulation approaches that assess the long-term development of the debris environment use either completely statistical approaches, or they rely on large time steps on the order of several days if they simulate the positions of single objects over time. They cannot be easily adapted to investigate the impact of specific collision avoidance schemes or de-orbit schemes, because the efficiency of a collision avoidance maneuver can depend on various input parameters, including ground station positions and orbital and physical parameters of the objects involved in close encounters (conjunctions). Furthermore, maneuvers take place on timescales much smaller than days. For example, LightForce only changes the orbit of a certain object (aiming to reduce the probability of collision), but it does not remove entire objects or groups of objects. In the same sense, it is also not straightforward to compare specific de-orbit methods in regard to potential collision risks during a de-orbit maneuver. To gain flexibility in assessing interactions with objects, we implement a simulation that includes every tracked space object in Low Earth Orbit (LEO) and propagates all objects with high precision and variable time-steps as small as one second. It allows the assessment of the (potential) impact of physical or orbital changes to any object. The final goal is to employ a Monte Carlo approach to assess the debris evolution during the simulation time-frame of 100 years and to compare a baseline scenario to debris remediation scenarios or other scenarios of interest. To populate the initial simulation, we use the entire space-track object catalog in LEO. We then use a high precision propagator to propagate all objects over the entire simulation duration. If collisions are detected, the appropriate number of debris objects are created and inserted into the simulation framework. Depending on the scenario, further objects, e.g. due to new launches, can be added. At the end of the simulation, the total number of objects above a cut-off size and the number of detected collisions provide benchmark parameters for the comparison between scenarios. The simulation approach is computationally intensive as it involves tens of thousands of objects; hence we use a highly parallel approach employing up to a thousand cores on the NASA Pleiades supercomputer for a single run. This paper describes our simulation approach, the status of its implementation, the approach to developing scenarios and examples of first test runs.

laser↗

A Step Towards the Final Frontier: Lessons Learned from Acceptance Testing of the First HPE/Cray EX 3000 System at ORNL

In this paper, we summarize the deployment of the Air Force Weather (AFW) HPC11 system at Oak Ridge National Laboratory (ORNL) including the process followed to successfully complete acceptance testing of the system. HPC11 is the first HPE/Cray EX 3000 system that has been successfully released to its user community in a federal facility. HPC11 consists of two identical 800-node supercomputers, Fawbush and Miller, with access to two independent and identical Lustre parallel file systems. HPC11 is equipped with Slingshot 10 interconnect technology and relies on the HPE Performance Cluster Manager (HPCM) software for system configuration. ORNL has a clearly defined acceptance testing process used to ensure that every new system deployed can provide the necessary capabilities to support user workloads. We worked closely with HPE and AFW to develop a set of tests that used the United Kingdom’s Meteorological Office’s Unified Model (UM) and 4DVAR. We also included benchmarks and applications from the Oak Ridge Leadership Computing Facility (OLCF) portfolio to fully exercise the HPE/Cray programming environment and evaluate the functionality and performance of the system. Acceptance testing of HPC11 required parallel execution of each element on Fawbush and Miller. In addition, careful coordination was needed to ensure successful acceptance of the newly deployed Lustre file systems alongside the compute resources. In this work, we present test results from specific system components and provide an overview of the issues identified, challenges encountered, and the lessons learned along the way.

Melesse Vergara, Veronica↗

New Parallel computing framework for radiation transport codes

A new parallel computing framework has been developed to use with general-purpose radiation transport codes. The framework was implemented as a C++ module that uses MPI for message passing. The module is significantly independent of radiation transport codes it can be used with, and is connected to the codes by means of a number of interface functions. The framework was integrated with the MARS15 code, and an effort is under way to deploy it in PHITS. Besides the parallel computing functionality, the framework offers a checkpoint facility that allows restarting calculations with a saved checkpoint file. The checkpoint facility can be used in single process calculations as well as in the parallel regime. Several checkpoint files can be merged into one thus combining results of several calculations. The framework also corrects some of the known problems with the scheduling and load balancing found in the original implementations of the parallel computing functionality in MARS15 and PHITS. The framework can be used efficiently on homogeneous systems and networks of workstations, where the interference from the other users is possible.

43 PARTICLE ACCELERATORS↗

Comparison of 250 MHz R10K Origin 2000 and 400 MHz Origin 2000 Using NAS Parallel Benchmarks

This report describes results of benchmark tests on Steger, a 250 MHz Origin 2000 system with R10K processors, currently installed at the NASA Ames National Advanced Supercomputing (NAS) facility. For comparison purposes, the tests were also run on Lomax, a 400 MHz Origin 2000 with R12K processors. The BT, LU, and SP application benchmarks in the NAS Parallel Benchmark Suite and the kernel benchmark FT were chosen to measure system performance. Having been written to measure performance on Computational Fluid Dynamics applications, these benchmarks are assumed appropriate to represent the NAS workload. Since the NAS runs both message passing (MPI) and shared-memory, compiler directive type codes, both MPI and OpenMP versions of the benchmarks were used. The MPI versions used were the latest official release of the NAS Parallel Benchmarks, version 2.3. The OpenMP versions used were PBN3b2, a beta version that is in the process of being released. NPB 2.3 and PBN3b2 are technically different benchmarks, and NPB results are not directly comparable to PBN results.

Turney, Raymond D.↗