Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “algorithms scalability”

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 415 records · Page 23

A Fast parallel tridiagonal algorithm for a class of CFD applications

The parallel diagonal dominant (PDD) algorithm is an efficient tridiagonal solver. This paper presents for study a variation of the PDD algorithm, the reduced PDD algorithm. The new algorithm maintains the minimum communication provided by the PDD algorithm, but has a reduced operation count. The PDD algorithm also has a smaller operation count than the conventional sequential algorithm for many applications. Accuracy analysis is provided for the reduced PDD algorithm for symmetric Toeplitz tridiagonal (STT) systems. Implementation results on Langley's Intel Paragon and IBM SP2 show that both the PDD and reduced PDD algorithms are efficient and scalable.

Moitra, Stuti↗

Molecular Simulations in Astrobiology

One of the main goals of astrobiology is to understand the origin of cellular life. The most direct approach to this problem is to construct laboratory models of protocells. Such efforts, currently underway in the NASA Astrobiology Program, are accompanied by computational studies aimed at explaining self-organization of simple molecules into ordered structures that are capable of performing protocellular functions. Many of these functions, such as importing nutrients, capturing energy and responding to changes in the environment, are carried out by proteins bound to membranes. We use computer simulations to address the following questions about these proteins: (1) How do small proteins self-organize into ordered structures at water-membrane interfaces and insert into membranes? (2) How do peptides form membrane-spanning structures (e.g. channels)? (3) By what mechanisms do such structures perform their functions? The simulations are performed using the molecular dynamics method. In this method, Newton's equations of motion for each atom in the system are solved iteratively. At each time step, the forces exerted on each atom by the remaining atoms are evaluated by dividing them into two parts. Short-range forces are calculated in real space while long-range forces are evaluated in reciprocal space, using a particle-mesh algorithm which is of order O(NInN). With a time step of 2 femtoseconds, problems occurring on multi-nanosecond time scales (10(exp 6)-10(exp 8) time steps) are accessible. To address a broader range of problems, simulations need to be extended by three orders of magnitude, which requires algorithmic improvements and codes scalable to a large number of processors. Work in this direction is in progress. Two series of simulations are discussed. In one series, it is shown that nonpolar peptides, disordered in water, translocate to the nonpolar interior of the membrane and fold into helical structures (see Figure). Once in the membrane, the peptides exhibit orientational flexibility with changing conditions, which may have provided a mechanism of transmitting signals between the protocell and its environment. In another series of simulations, the mechanism by which a simple protein channel efficiently mediates proton transport across membranes was investigated. This process is a key step in cellular bioenergetics. In the channel under study, proton transport is gated by four histidines that occlude the channel pore. The simulations identify the mechanisms by which protons move through the gate.

Pohorille, Andrew↗

Molecular Simulations in Astrobiology

One of the main goals of astrobiology is to understand the origin of cellular life. In the absence of any record of the earliest ancestors of contemporary cells, protocells, the most direct way to test our understanding of their characteristics is to construct laboratory models of protocells. Such efforts, currently underway in the NASA Astrobiology Program, are accompanied by computational studies aimed at explaining self-organization of simple molecules into ordered structures and developing designs of molecules that are capable of performing protocellular functions. Many of these functions, such as importing nutrients, capturing and storing energy, and responding to changes in the environment, are carried out by proteins bound to membranes. We use computer simulations to address the following, questions about these proteins: (1) How do small proteins (peptides) organize themselves into ordered structures at water-membrane interfaces and insert into membranes? (2) How do peptides aggregate to form membrane-spannin(y structures (e.g., channels)? (3) By what mechanisms do such aggregates perform their functions? The simulations are performed using the molecular dynamics (MD) method. In this method, Newton's equations of motion for each atom in the system are solved iteratively. At each time step, the forces exerted on each atom by the remaining atoms are evaluated by dividing them into two parts. Short-range forces are calculated directly in real space while long-range forces are evaluated in reciprocal space, usually using a particle-mesh algorithm which is of order O(NlnN). Currently, a time step of 2 femtoseconds is typically used, thereby making studies of problems occurring on multi-nanosecond time scales (10(exp 6) - 10(exp 8) time steps) accessible. To address a broader range of problems, simulations need to be extended by three orders of magnitude. Such an extension requires both algorithmic improvements and codes scalable to a large number of parallel processors. Work in this direction is in progress. Two specific series of simulations that demonstrate how peptides self-organize and function in membranes are discussed. In one series of simulations, it was shown that nonpolar peptides, disordered in water, translocate to the nonpolar interior of the membrane and, simultaneously, fold into two different helical structures, which remain in equilibrium. Once in the membrane, the peptides can readily change their orientation, especially in response to local electric fields. This structural and orientational flexibility of peptides with changing conditions may have provided a mechanism of transmitting signals between the environment and the interior of the protocell. In another series of simulations, the mechanism by which a simple protein channel efficiently mediates proton transport across membranes was investigated. This process is a key step in cellular bioenergetics. In the channel under study, proton transport is gated by four histidines that occlude the channel pore. The simulations demonstrate that protons move through the gate by a "shuttle" mechanism, wherein one histidine is protonated on the extracellular side and, subsequently, the proton bound on the opposite side is released.

Pohorille, Andrew↗

Distributed Parallel Particle Advection using Work Requesting

Particle advection is an important vector field visualization technique that is difficult to apply to very large data sets in a distributed setting due to scalability limitations in existing algorithms. In this paper, we report on several experiments using work requesting dynamic scheduling which achieves balanced work distribution on arbitrary problems with minimal communication overhead. We present a corresponding prototype implementation, provide and analyze benchmark results, and compare our results to an existing algorithm.

97 MATHEMATICS AND COMPUTING↗

Machine Learning Toolkit for Extreme Scale

Support Vector Machines (SVM) is a popular machine learning technique, which has been applied to a wide range of domains such as science, finance, and social networks for supervised learning. MaTEx undertakes the challenge of designing a scalable parallel SVM training algorithm for large scale systems, which includes commodity multi-core machines, tightly connected supercomputers and cloud computing systems. Several techniques are proposed for improved speed and memory space usage including adaptive and aggressive elimination of samples for faster convergence , and sparse format representation of data samples. Several heuristics for earliest possible to lazy elimination of non-contributing samples are considered in MaTEx. In many cases, where an early sample elimination might result in a false positive, low overhead mechanisms for reconstruction of key data structures are proposed. The proposed algorithm and heuristics are implemented and evaluated on various publicly available datasets

Source record↗

167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation

An artificial intelligence system called MENNDL, which used 25,200 NVIDIA Volta GPUs on Oak Ridge National Laboratory's Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity towards nanofabricating materials automatically. MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.

Patton, Robert↗

Productive Programming of Distributed Systems with the SHAD C++ Library

High-performance computing (HPC) is often perceived as a matter of making large-scale systems (e.g., clusters) run as fast as possible, regardless the required programming effort. However, the idea of "bringing HPC to the masses" has recently emerged. Inspired by this vision, we have designed SHAD, the Scalable High-performance Algorithms and Data-structures library. SHAD is open source software, written in C++, for C++ developers. Unlike other HPC libraries for distributed systems, which rely on SPMD models, SHAD adopts a shared-memory programming abstraction, to make C++ programmers feel at home. Underneath, SHAD manages tasking and data-movements, moving the computation where data resides and taking advantage of asynchrony to tolerate network latency. At the bottom of his stack, SHAD can interface with multiple runtime systems: this not only improves developer’s productivity, by hiding the complexity of such software and of the underlying hardware, but also greatly enhance code portability. Thanks to its abstraction layers, SHAD can indeed target different systems, ranging from laptops to HPC clusters, without any need for modifying the user-level code. We have prototyped and open-sourced the implementation of (a subset of) the C++ standard library (STL) targeting multi-node HPC clusters. Our work allows plain STL-based C++ code to scale on HPC systems, with no need for rewriting the code to exploit the complex hardware. SHAD is available under Apache v2 License at https://github.com/pnnl/SHAD. In this paper we overview the design of the SHAD library, depicting its main components: runtime systems abstractions for tasking; parallel and distributed data-structures; STL-compliant interfaces and algorithms.

Castellana, Vito G.↗

MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks

In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the detector resolution for jets and the missing transverse momentum. In view of the planned high-luminosity upgrade of the CERN Large Hadron Collider (LHC), it is necessary to revisit existing reconstruction algorithms and ensure that both the physics and computational performance are sufficient in an environment with many simultaneous proton–proton interactions (pileup). Machine learning may offer a prospect for computationally efficient event reconstruction that is well-suited to heterogeneous computing platforms, while significantly improving the reconstruction quality over rule-based algorithms for granular detectors. We introduce MLPF, a novel, end-to-end trainable, machine-learned particle-flow algorithm based on parallelizable, computationally efficient, and scalable graph neural network optimized using a multi-task objective on simulated events. We report the physics and computational performance of the MLPF algorithm on a Monte Carlo dataset of top quark–antiquark pairs produced in proton–proton collisions in conditions similar to those expected for the high-luminosity LHC. The MLPF algorithm improves the physics response with respect to a rule-based benchmark algorithm and demonstrates computationally scalable particle-flow reconstruction in a high-pileup environment.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Scalable method for demonstrating the Deutsch-Jozsa and Bernstein-Vazirani algorithms using cluster states

We show that fundamental versions of the Deutsch-Jozsa and Bernstein-Vazirani quantum algorithms can be performed using a small entangled cluster state resource of only six qubits. We then investigate the minimal resource states needed to demonstrate general n-qubit versions and a scalable method to produce them. For this purpose, we propose a versatile photonic on-chip setup.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Fast katz and commuters : efficient estimation of social relatedness in large networks.

Motivated by social network data mining problems such as link prediction and collaborative filtering, significant research effort has been devoted to computing topological measures including the Katz score and the commute time. Existing approaches typically approximate all pairwise relationships simultaneously. In this paper, we are interested in computing: the score for a single pair of nodes, and the top-k nodes with the best scores from a given source node. For the pairwise problem, we apply an iterative algorithm that computes upper and lower bounds for the measures we seek. This algorithm exploits a relationship between the Lanczos process and a quadrature rule. For the top-k problem, we propose an algorithm that only accesses a small portion of the graph and is related to techniques used in personalized PageRank computing. To test the scalability and accuracy of our algorithms we experiment with three real-world networks and find that these algorithms run in milliseconds to seconds without any preprocessing.

99 GENERAL AND MISCELLANEOUS↗

Fast Katz and commuters : efficient estimation of social relatedness.

Motivated by social network data mining problems such as link prediction and collaborative filtering, significant research effort has been devoted to computing topological measures including the Katz score and the commute time. Existing approaches typically approximate all pairwise relationships simultaneously. In this paper, we are interested in computing: the score for a single pair of nodes, and the top-k nodes with the best scores from a given source node. For the pairwise problem, we apply an iterative algorithm that computes upper and lower bounds for the measures we seek. This algorithm exploits a relationship between the Lanczos process and a quadrature rule. For the top-k problem, we propose an algorithm that only accesses a small portion of the graph and is related to techniques used in personalized PageRank computing. To test the scalability and accuracy of our algorithms we experiment with three real-world networks and find that these algorithms run in milliseconds to seconds without any preprocessing.

99 GENERAL AND MISCELLANEOUS↗

Scalable and Fault Tolerant Failure Detection and Consensus

Future extreme-scale high-performance computing systems will be required to work under frequent component failures. The MPI Forum's User Level Failure Mitigation proposal has introduced an operation, MPI_Comm_shrink, to synchronize the alive processes on the list of failed processes, so that applications can continue to execute even in the presence of failures by adopting algorithm-based fault tolerance techniques. This MPI_Comm_shrink operation requires a fault tolerant failure detection and consensus algorithm. This paper presents and compares two novel failure detection and consensus algorithms. The proposed algorithms are based on Gossip protocols and are inherently fault-tolerant and scalable. The proposed algorithms were implemented and tested using the Extreme-scale Simulator. The results show that in both algorithms the number of Gossip cycles to achieve global consensus scales logarithmically with system size. The second algorithm also shows better scalability in terms of memory and network bandwidth usage and a perfect synchronization in achieving global consensus.

Katti, Amogh↗

Discontinuous Galerkin Dynamical Core in HOMME

Atmospheric numerical modeling has been going through radical changes over the past decade. One major reason for this trend is due to the recent paradigm change in scientific computing , triggered by the arrival of petascale computing resources with core counts in the tens of thousands to hundreds of thousands range. Modern atmospheric modelers must adapt grid systems and numerical algorithms to facilitate an unprecedented levels of scalability on these modern highly parallel computer architectures. The numerical algorithms which can address these challenges should have the local properties such as high on-processor floating-point operation count to bytes moved and minimum parallel communication overhead.

17 WIND ENERGY↗

DUNE: Michel Electron Selection with SPINE

This poster details the evaluation of a Michel electron selection algorithm centered on the neural network-based software SPINE (Scalable Particle Imageing with Neural Embeddings). The algorithm was developed and calibrated using simulated data from the SBND (Short-Baseline Neutrino Detector) experiment before being applied to simulated data from DUNE (Deep Underground Neutrino Experiment).

Wilson, Dante [U. Colorado, Boulder]↗

Variational Quantum Eigensolver of Interacting Bosons with NISQ Devices [Slides]

Interacting bosons attract broad interest from different fields of physics and is often challenging to simulate on a classical computer. The recent advances in variational-quantum-eigensolver (VQE) algorithms offer a new and scalable way to investigate these interacting boson systems with noisy intermediate scale quantum (NISQ) devices. In this work, we present a proof-of-principle experiment of a boson VQE algorithm implemented on Rigetti's 8Q-device. Our experiment determines the low-energy eigenspectrum of the Rabi model -- a simple boson model with interactions mediated by an atom. Our result illustrates the promising future of scalable quantum simulation of interacting bosons using NISQ devices.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A De-Centralized Scheduling and Load Balancing Algorithm for Heterogeneous Grid Environments

In the past two decades, numerous scheduling and load balancing techniques have been proposed for locally distributed multiprocessor systems. However, they all suffer from significant deficiencies when extended to a Grid environment: some use a centralized approach that renders the algorithm unscalable, while others assume the overhead involved in searching for appropriate resources to be negligible. Furthermore, classical scheduling algorithms do not consider a Grid node to be N-resource rich and merely work towards maximizing the utilization of one of the resources. In this paper we propose a new scheduling and load balancing algorithm for a generalized Grid model of N-resource nodes that not only takes into account the node and network heterogeneity, but also considers the overhead involved in coordinating among the nodes. Our algorithm is de-centralized, scalable, and overlaps the node coordination time of the actual processing of ready jobs, thus saving valuable clock cycles needed for making decisions. The proposed algorithm is studied by conducting simulations using the Message Passing Interface (MPI) paradigm.

Arora, Manish↗

ISAVS: Interactive Scalable Analysis and Visualization System

Modern science is inundated with ever increasing data sizes as computational capabilities and image acquisition techniques continue to improve. For example, simulations are tackling ever larger domains with higher fidelity, and high-throughput microscopy techniques generate larger data that are fundamental to gather biologically and medically relevant insights. As the image sizes exceed memory, and even sometimes local disk space, each step in a scientific workflow is impacted. Current software solutions enable data exploration with limited interactivity for visualization and analytic tasks. Furthermore analysis on HPC systems often require complex hand-written parallel implementations of algorithms that suffer from poor portability and maintainability. We present a software infrastructure that simplifies end-to-end visualization and analysis of massive data. First, a hierarchical streaming data access layer enables interactive exploration of remote data, with fast data fetching to test analytics on subsets of the data. Second, a library simplifies the process of developing new analytics algorithms, allowing users to rapidly prototype new approaches and deploy them in an HPC setting. Third, a scalable runtime system automates mapping analysis algorithms to whatever computational hardware is available, reducing the complexity of developing scaling algorithms. Here, we demonstrate the usability and performance of our system using a use case from neuroscience: filtering, registration, and visualization of tera-scale microscopy data. We evaluate the performance of our system using a leadership-class supercomputer, Shaheen II.

97 MATHEMATICS AND COMPUTING↗

Machine and Application Aware Partitioning for Adaptive Mesh Refinement Applications. In: HPDC '17 Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing

Load balancing and partitioning are critical when it comes to parallel computations. Popular partitioning strategies based on space filling curves focus on equally dividing work. The partitions produced are independent of the architecture or the application. Given the ever-increasing relative cost of data movement and increasing heterogeneity of our architectures, it is no longer sufficient to only consider an equal partitioning of work. Minimizing communication costs are equally if not more important. Our hypothesis is that an unequal partitioning that minimizes communication costs significantly can scale and perform better than conventional equal-work partitioning schemes. This tradeoff is dependent on the architecture as well as the application. We validate our hypothesis in the context of a finite-element computation utilizing adaptive mesh-refinement. Our central contribution is a new partitioning scheme that minimizes the overall runtime of subsequent computations by performing architecture and application-aware non-uniform work assignment in order to decrease time to solution, primarily by minimizing data-movement. We evaluate our algorithm by comparing it against standard space-filling curve based partitioning algorithms and observing time-to-solution as well as energy-to-solution for solving Finite Element computations on adaptively refined meshes. We demonstrate excellent scalability of our new partition algorithm up to $262,144$ cores on ORNL's Titan and demonstrate that the proposed partitioning scheme reduces overall energy as well as time-to-solution for application codes by up to 22.0%.

Fernando, Milinda↗