Search NASA⌕ Search

SEARCH · Search NASA

Results for “graph optimization”

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

Scalable Graph Analytics and HPC Operational Enhancement: Parallel Computing and ML/DL Innovations

Parallel computing plays a pivotal role in the efficient processing of large-scale graphs. Complex network analysis stands as a capti- vating research frontier, holding promise across diverse scientific domains such as sociology, biology, online media, and recommenda- tion systems. In this era, Machine Learning (ML) and Deep Learning (DL) have emerged as indispensable tools, underpinning remarkable technological achievements. Within this dynamic landscape, my research revolves around advancing parallel algorithms tailored for large-scale graph operations. To achieve this, I harness the power of cutting-edge technologies including OpenMP, MPI, HIP, and CUDA, on the High-Performance Computing (HPC) platforms to unlock optimal performance. I also apply ML/DL techniques to HPC operational data, to streamline the monitoring and maintenance of supercomputers, alleviating the complexities associated with their upkeep and enhancing user support. My research echoes the syn- ergy between parallel computing, large-scale graph analysis, and ML/DL, improving computational efficiency and user experience.

Sattar, Naw Safrin↗

Efficient mapping algorithms for scheduling robot inverse dynamics computation on a multiprocessor system

Two efficient mapping algorithms for scheduling the robot inverse dynamics computation consisting of m computational modules with precedence relationship to be executed on a multiprocessor system consisting of p identical homogeneous processors with processor and communication costs to achieve minimum computation time are presented. An objective function is defined in terms of the sum of the processor finishing time and the interprocessor communication time. The minimax optimization is performed on the objective function to obtain the best mapping. This mapping problem can be formulated as a combination of the graph partitioning and the scheduling problems; both have been known to be NP-complete. Thus, to speed up the searching for a solution, two heuristic algorithms were proposed to obtain fast but suboptimal mapping solutions. The first algorithm utilizes the level and the communication intensity of the task modules to construct an ordered priority list of ready modules and the module assignment is performed by a weighted bipartite matching algorithm. For a near-optimal mapping solution, the problem can be solved by the heuristic algorithm with simulated annealing. These proposed optimization algorithms can solve various large-scale problems within a reasonable time. Computer simulations were performed to evaluate and verify the performance and the validity of the proposed mapping algorithms. Finally, experiments for computing the inverse dynamics of a six-jointed PUMA-like manipulator based on the Newton-Euler dynamic equations were implemented on an NCUBE/ten hypercube computer to verify the proposed mapping algorithms. Computer simulation and experimental results are compared and discussed.

Lee, C. S. G.↗

A Multithreaded Algorithm for Network Alignment Via Approximate Matching

Network alignment is an optimization problem to find the best one-to-one map between the vertices of a pair of graphs that overlaps in as many edges as possible. It is a relaxation of the graph isomorphism problem and is closely related to the subgraph isomorphism problem. The best current approaches are entirely heuristic, and are iterative in nature. They generate real-valued heuristic approximations that must be rounded to find integer solutions. This rounding requires solving a bipartite maximum weight matching problem at each step in order to avoid missing high quality solutions. We investigate substituting a parallel, half-approximation for maximum weight matching instead of an exact computation. Our experiments show that the resulting difference in solution quality is negligible. We demonstrate almost a 20-fold speedup using 40 threads on an 8 processor Intel Xeon E7-8870 system (from 10 minutes to 36 seconds).

network alignment, matching, multicore↗

Enabling Scalable and Extensible Memory-mapped Datastores in Userspace

Exascale workloads are expected to incorporate data-intensive processing in close coordination with traditional physics simulations. These emerging scientific, data-analytics and machine learning applications need to access a wide variety of datastores in flat files and structured databases. Programmer productivity is greatly enhanced by mapping datastores into the application process's virtual memory space to provide a unified “in-memory” interface. Currently, memory mapping is provided by system software primarily designed for generality and reliability. However, scalability at high concurrency is a formidable challenge on exascale systems. Also, there is a need for extensibility to support new datastores potentially requiring HPC data transfer services. In this article, we present UMap , a scalable and extensible userspace service for memory-mapping datastores. Furthermore, through decoupled queue management, concurrency aware adaptation, and dynamic load balancing, UMap enables application performance to scale even at high concurrency. We evaluate UMap in data-intensive applications, including sorting, graph traversal, database operations, and metagenomic analytics. Our results show that UMap as a userspace service outperforms an optimized kernel-based service across a wide range of intra-node concurrency by 1.22-1.9 × . We performed two case studies to demonstrate UMap 's extensibility. First, a new datastore residing in remote memory is incorporated into UMap as an application-specific plugin. Second, we present a persistent memory allocator Metall built atop UMap for unified storage/memory.

97 MATHEMATICS AND COMPUTING↗

Runtime Systems for Energy Efficiency in Advanced Computing Systems

As heterogeneous systems become increasingly popular for both mobile and high-performance computing, conventional efficiency techniques such as dynamic voltage and frequency scaling (DVFS) fail to account for the tightly coupled and varied nature of systems on a chip (SoCs). In this work, we explore the impact of system unaware DVFS techniques on a mobile SoC under three benchmark suites: Chai, Rodinia, and Antutu. We then analyze performance trends across the suites to identify a set of consistent operating points that optimally balance power and performance across the system. The consistent operating points are then constructed into a dependency graph which can be leveraged to produce a more effective, SoC-wide governor.

97 MATHEMATICS AND COMPUTING↗

Cyber Network Design for Secondary Frequency Regulation: A Spectral Approach

We present a preliminary theoretical framework based on spectral graph theory that captures how the cyber topology of a distributed secondary frequency control scheme impacts the stability, optimality, and transient performance of our power system as a cyber-physical network. We show that a collection of polynomials defined in terms of the cyber and physical Laplacian eigenvalues encode information on the interplay between cyber and physical networks. It is demonstrated that to understand the impact of adding cyber connectivity, one should separate the low-damping and high-damping regimes. Although adding cyber connectivity always improves the performance for high-damping systems, it is not the case for low-damping scenarios. Based on the theoretical study, we discuss how a good cyber network should be designed. Our empirical study shows that for practical systems, the number of communication channels that is needed to achieve near-optimal performance is usually less than twice the number of buses.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Study of magnetic perturbations on SEC vidicon tubes

A laboratory measurements program was conducted to determine the tolerances that must be imposed to achieve optimum performance from SEC-vidicon data sensors in the LST mission. These measurements along with other data were used to formulate recommendations regarding the necessary telemetry and remote control for the television data sensors when in orbit. The study encompassed the following tasks: (1) Conducted laboratory measurements of the perturbations which an external magnetic field produces on a magnetically focused, SEC-vidicon. Evaluated shielding approaches. (2) Experimentally evaluated the effects produced on overall performance by variations of the tube electrode potentials, and the focus, deflection and alignment fields. (3) Recommended the extent of ground control of camera parameters and camera parameter telemetry required for optimizing the performance of the television system in orbit. The experimental data are summarized in a set of graphs.

Long, D. C.↗

Obtaining schedules for digital systems

A systematic technique is presented to derive correct schedules for a synchronous digital system, given a signal flow graph for an algorithm. It is also shown how to use this technique to derive designs that are optimal in having the lowest latency, the highest throughput, or the smallest number of registers. The same technique can also be used to verify digital systems that have already been designed.

Jagadish, H. V.↗

System and method for reasoning about the optimality of a configuration parameter of a distributed system

Embodiments provide a system and method for reasoning about the optimality of a configuration parameter of a distributed system. During operation, the system obtains a multi-layer graph for a system with a plurality of components, wherein the multi-layer graph comprises a configuration subgraph, a vulnerability subgraph, and a dependency subgraph. The system determines, based on the multi-layer graph, constraint relationships associated with configuration parameters for the components, wherein the constraint relationships include security constraints and functionality constraints. The system computes an unsatisfiable core which comprises a set of mutually incompatible constraints. The system resolves, based on a strategy and over multiple iterations, the unsatisfiable core by analyzing one pair of mutually incompatible constraints per a respective iteration, to obtain a new unsatisfiable core which comprises a smaller number of mutually incompatible constraints than the computed unsatisfiable core or a previously computed unsatisfiable core from a most recent iteration.

Soroush, Hamed↗

Applying graph partitioning methods in measurement-based dynamic load balancing

Load imbalance leads to an increasing waste of resources as an application is scaled to more and more processors. Achieving the best parallel efficiency for a program requires optimal load balancing which is a NP-hard problem. However, finding near-optimal solutions to this problem for complex computational science and engineering applications is becoming increasingly important. Charm++, a migratable objects based programming model, provides a measurement-based dynamic load balancing framework. This framework instruments and then migrates over-decomposed objects to balance computational load and communication at runtime. 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 microbenchmarks on Intrepid and Ranger and evaluate the effect of communication, number of cores and number of objects on the benefit achieved from load balancing. New algorithms developed in SCOTCH lead to better performance compared to the METIS partitioners for several cases, both in terms of the application execution time and fewer number of objects migrated.

97 MATHEMATICS AND COMPUTING↗

A spatial superstructure approach to the optimal design of modular processes and supply chains

Modularity is a design principle that aims to provide flexibility for spatio-temporal assembly/disassembly and reconfiguration of systems. This design principle can be applied to multiscale (hierarchical) manufacturing systems that connect units, processes, facilities, and entire supply chains. Designing modular systems is challenging because of the need to capture spatial interdependencies that arise between system components due to product exchange/transport between components and due to product transformation in such components. In this work, we propose an optimization framework to facilitate the design of modular manufacturing systems. Central to our approach is the concept of a spatial superstructure, which is a graph that captures all possible system configurations and interdependencies between components. The spatial superstructure is a generalization of the notion of a superstructure and of a p-graph used in process design, in that it encodes spatial (geographical) context of the system components. Here, we show that this generalization facilitates the simultaneous design and analysis of processes, facilities, and of supply chains. Our framework aims to select the system topology from the spatial superstructure that minimizes design cost and that maximizes design modularity. We show that this design problem can be cast as a mixed-integer, multi-objective optimization formulation. We demonstrate these capabilities using a case study arising in the design of a plastic waste upcycling supply chain.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

MDLoader: A Hybrid Model-Driven Data Loader for Distributed Graph Neural Network Training

Scalable data management is essential for processing large scientific dataset on HPC platforms for distributed deep learning. In-memory distributed storage is preferred for its speed, enabling rapid, random, and frequent data access required by stochastic optimizers. Processes use one-sided or collective communication to fetch remote data, with optimal performance depending on (i) dataset characteristics, (ii) training scale, and (iii) interconnection network. Empirical analysis shows collective communication excels with larger mini-batch sizes and/or fewer processes, whereas one-sided communication outperforms at larger scales. We propose MDLoader, a hybrid in-memory data loader for distributed graph neural network training. MDLoader features a model-driven performance estimator that dynamically selects between one-sided and collective communication at the beginning of training using Tree of Parzen Estimators (TPE). Evaluations on NERSC Perlmutter and OLCF Summit show MDLoader outperforms single-backend loaders by up to 2.83 × and predicts the suitable communication method with 96.3% (Perlmutter) and 94.3% (Summit) success rate.

Bae, Jonghyun↗

Noisy evolution of graph-state entanglement

A general method for the study of the entanglement evolution of graph states under the action of Pauli maps was recently proposed in Cavalcanti et al. [Phys. Rev. Lett. 103, 030502 (2009)]. This method is based on lower and upper bounds to the entanglement of the entire state as a function only of the state of a (typically) considerably smaller subsystem undergoing an effective noise process related to the original map. This provides a huge decrease in the size of the matrices involved in the calculation of entanglement in these systems. In the present paper we elaborate on this method in detail and generalize it to other natural situations not described by Pauli maps. Specifically, for Pauli maps we introduce an explicit formula for the characterization of the resulting effective noise. Beyond Pauli maps, we show that the same ideas can be applied to the case of thermal reservoirs at arbitrary temperature. In the latter case, we discuss how to optimize the bounds as a function of the noise strength. We illustrate our ideas with explicit exemplary results for several different graphs and particular decoherence processes. The limitations of the method are also discussed.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A Synchronization-Avoiding Distance-1 Grundy Coloring Algorithm for Power-Law Graphs

In this paper, we propose a distributed, unordered, label-correcting distance-1 Grundy (vertex) coloring algorithm, namely, Distributed Control (DC) coloring algorithm. Our algorithm eliminates the need for vertex-centric barriers and global synchronization for color refinement, relying only on atomic operations and local termination detection to update vertex color. DC proceeds optimistically, correcting the colors asynchronously as the algorithm progresses and depends on local ordering of tasks to minimize the execution of sub-optimal work. We implement our DC coloring algorithm and the well-known Jones-Plassmann algorithm and compare their performance with 4 different types of standard RMAT graphs and real-world graphs. We show that the elimination of waiting time of global and vertex-centric barriers and investing this time for local ordering leads to improved scaling for graphs with prominent power-law characteristics and densely interconnected local subgraphs.

Firoz, Jesun S.↗

Short-depth QAOA circuits and quantum annealing on higher-order ising models

Abstract We present a direct comparison between QAOA (Quantum Alternating Operator Ansatz), and QA (Quantum Annealing) on 127 qubit problem instances. QAOA with p = 1, 2 rounds is executed on the 127 qubit heavy-hex graph gate-model quantum computer ibm_washington, using on-device grid-searches for angle finding, and QA is executed on two Pegasus-chip D-Wave quantum annealers. The problems are random Ising models whose connectivity matches heavy-hex graphs and the Pegasus graph connectivity, and optionally include hardware-compatible cubic terms ( Z Z Z terms). The QAOA circuits are heavily optimized and of extremely short depth, with a CNOT depth of 6 per round, which allows whole chip usage of the heavy-hex lattice. QAOA and QA are both compared against simulated annealing and the optimal solutions are computed exactly using CPLEX. The noiseless mean QAOA expectation values for p = 1, 2 are computed using classical light-cone based simulations. We find QA outperforms QAOA on the evaluated devices.

127 qubits↗

Quantum speed limits for quantum-information-processing tasks

We derive algebraic bounds on achievable rates for quantum state transfer and entanglement generation in general quantum systems. We apply these bounds to graph-based models of local quantum spin systems to obtain speed limits on these tasks. A comparison to numerical optimal control results for spin chains suggests that unexplored regions of the dynamical landscape may support enhanced performance of key quantum-information-processing tasks.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

MICCO: An Enhanced Multi-GPU Scheduling Framework for Many-Body Correlation Functions

Calculation of many-body correlation functions is one of the critical kernels utilized in many scientific computing areas, especially in Lattice Quantum Chromodynamics (Lattice QCD). It is formalized as a sum of a large number of contraction terms each of which can be represented by a graph consisting of vertices describing quarks inside a hadron node and edges designating quark propagations at specific time intervals. Due to its computation- and memory-intensive nature, real-world physics systems (e.g., multi-meson or multi-baryon systems) explored by Lattice QCD prefer to leverage multi-GPUs. Different from general graph processing, many-body correlation function calculations show two specific features: a large number of computation-/data-intensive kernels and frequently repeated appearances of original and intermediate data. The former results in expensive memory operations such as tensor movements and evictions. The latter offers data reuse opportunities to mitigate the data-intensive nature of many-body correlation function calculations. However, existing graph-based multi-GPU schedulers cannot capture these data-centric features, thus resulting in a sub-optimal performance for many-body correlation function calculations. To address this issue, this paper presents a multi-GPU scheduling framework, MICCO, to accelerate contractions for correlation functions particularly by taking the data dimension (e.g., data reuse and data eviction) into account. This work first performs a comprehensive study on the interplay of data reuse and load balance, and designs two new concepts: local reuse pattern and reuse bound to study the opportunity of achieving the optimal trade-off between them. Based on this study, MICCO proposes a heuristic scheduling algorithm and a machine-learning-based regression model to generate the optimal setting of reuse bounds. Specifically, MICCO is integrated into a real-world Lattice QCD system, Redstar, for the first time running on multiple GPUs. The evaluation demonstrates MICCO outperforms other state-of-art works, achieving up to 2.25× speedup in synthesized datasets, and 1.49× speedup in real-world correlation functions.

Wang, Qihan↗

Programming Strategies for Irregular Algorithms on the Emu Chick

The Emu Chick prototype implements migratory memory-side processing in a novel hardware system. Rather than transferring large amounts of data across the system interconnect, the Emu Chick moves lightweight thread contexts to near-memory cores before the beginning of each remote memory read. Previous work has characterized the performance of the Chick prototype in terms of memory bandwidth and programming differences from more typical, non-migratory platforms, but there has not yet been an analysis of algorithms on this system. This work evaluates irregular algorithms that could benefit from the lightweight, memory-side processing of the Chick and demonstrates techniques and optimization strategies for achieving performance in sparse matrix-vector multiply operation (SpMV), breadth-first search (BFS), and graph alignment across up to eight distributed nodes encompassing 64 nodelets in the Chick system. We also define and justify relative metrics to compare prototype FPGA-based hardware with established ASIC architectures. The Chick currently supports up to 68x scaling for graph alignment, 80 MTEPS for BFS on balanced graphs, and 50% of measured STREAM bandwidth for SpMV.

Hein, Eric↗