Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “high performance graph algorithms”

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 127 records · Page 7

CHALLENGES IN PARALLEL GRAPH PROCESSING

Graph algorithms are becoming increasingly important for solving many problems in scientific computing, data mining and other domains. As these problems grow in scale, parallel computing resources are required to meet their computational and memory requirements. Unfortunately, the algorithms, software, and hardware that have worked well for developing mainstream parallel scientific applications are not necessarily effective for large-scale graph problems. In this paper we present the inter-relationships between graph problems, software, and parallel hardware in the current state of the art and discuss how those issues present inherent challenges in solving large-scale graph problems. The range of these challenges suggests a research agenda for the development of scalable high-performance software for graph problems.

LUMSDAINE, ANDREW↗

Advanced bandwidth scheduling algorithms in dedicated networks

An increasing number of high performance research network testbeds and production networks have the capability of provisioning dedicated channels for high speed data transfer in support of large scale scientific applications. Each dedicated channel in these networks typically consists of one or more physical links that are shared by multiple applications in both time and bandwidth through in advance reservation. The design of efficient bandwidth scheduling algorithms is critical to maximizing the utilization of dedicated network resources and meeting diverse end-to-end transport performance requirements. The topology of a dedicated network is represented by a graph, where each link maintains a list of residual bandwidths specified as segmented constant functions of time. Given a graph with an aggregated time-bandwidth table combining the reservation information on all links, designated source, and destination vertices, and a specified data size, we formulate and investigate five bandwidth scheduling problems to minimize the data transfer end time under different path and bandwidth constraints. (1) variable path with variable bandwidth (VPVB), which computes the widest (highest bandwidth) path in each time slot; (2) fixed path with variable bandwidth (FPVB), which computes a fixed path with varying bandwidths across different time slots; (3) variable path with fixed bandwidth (VPFB), which computes one path in each time slot with the same bandwidth; (4) fixed path with fixed bandwidth (FPFB), which computes a fixed path with a constant bandwidth; and (5) multiple fixed paths with fixed bandwidths (MFPFB), which computes multiple concurrent fixed paths with constant bandwidths. Among these problems, VPVB represents the most flexible scenario where the network resources are fully utilized and the minimal transfer end time is achieved, while FPFB imposes the most stringent transport conditions by fixing both path and bandwidth. We design an optimal algorithm for each of these scheduling problems. VPVB is solved using an extension of the classical Dijkstra's algorithm, and FPVB is solved using Maximum Permutation Algorithm, which tries all possible permutations of throughputs at different time slots to obtain the minimal transfer end time. The algorithm for VPFB, FPFB, and MFPFB are based on Adjacent Time Slots Search, which finds the minimum transfer end time by examining the possibility of data transfer in any number of contiguous time slots. All these algorithms are of polynomial or pseudo polynomial time complexity with respect to the network size and the total number of time slots in a bandwidth reservation table.

99 GENERAL AND MISCELLANEOUS↗

Impact of Domain Knowledge on the Property Prediction of Specialized Machine Learning Models

Developing transferable machine learning models is trending in data-driven materials research. However, how to apply such models to a specific research domain remains unclear. Here, in this work, we choose high-entropy materials as a platform with a specialized data set containing 145,323 DFT-relaxed materials. This data set is used to explore the role of domain-specific knowledge in training effective models. Our tests with three representative graph neural network architectures indicate the model complexity has much smaller influence on performance than the data itself. Specifically, the consideration of low-energy atomic ordering, structures with diverse elemental coverage, and high-order interactions significantly influences the model performance. We also find that domain knowledge-driven sampling can greatly enhance unsupervised learning techniques. This research highlights that developing specialized data sets is more beneficial than further complicating deep learning architectures. Additionally, physics-inspired sampling algorithms are crucially needed for better machine learning models for a specific materials research domain.

36 MATERIALS SCIENCE↗

Sampling frequency thresholds for the quantum advantage of the quantum approximate optimization algorithm

We compare the performance of the Quantum Approximate Optimization Algorithm (QAOA) with state-of-the-art classical solvers Gurobi and MQLib to solve the MaxCut problem on 3-regular graphs. We identify the minimum noiseless sampling frequency and depth p required for a quantum device to outperform classical algorithms. There is potential for quantum advantage on hundreds of qubits and moderate depth with a sampling frequency of 10 kHz. We observe, however, that classical heuristic solvers are capable of producing high-quality approximate solutions in linear time complexity. In order to match this quality for large graph sizes N, a quantum device must support depth p > 11. Additionally, multi-shot QAOA is not efficient on large graphs, indicating that QAOA p ≤ 11 does not scale with N. These results limit achieving quantum advantage for QAOA MaxCut on 3-regular graphs. Other problems, such as different graphs, weighted MaxCut, and 3-SAT, may be better suited for achieving quantum advantage on near-term quantum devices.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Redeye: A Digital Library for Forensic Document Triage

Forensic document analysis has become an important aspect of investigation of many different kinds of crimes from money laundering to fraud and from cybercrime to smuggling. The current workflow for analysts includes powerful tools, such as Palantir and Analyst s Notebook, for moving from evidence to actionable intelligence and tools for finding documents among the millions of files on a hard disk, such as FTK. However, the analysts often leave the process of sorting through collections of seized documents to filter out the noise from the actual evidence to a highly labor-intensive manual effort. This paper presents the Redeye Analysis Workbench, a tool to help analysts move from manual sorting of a collection of documents to performing intelligent document triage over a digital library. We will discuss the tools and techniques we build upon in addition to an in-depth discussion of our tool and how it addresses two major use cases we observed analysts performing. Finally, we also include a new layout algorithm for radial graphs that is used to visualize clusters of documents in our system.

Bogen, Paul Logasa↗

Optimizing FPGA-based Accelerator Design for Large-Scale Molecular Similarity Search (Special Session Paper)

Molecular similarity search has been widely used in drug discovery to rapidly identify structurally similar compounds from large molecular databases. With the increasing size of chemical libraries, there is growing interest in the efficient ac- celeration of large-scale similarity search. Existing works mainly focus on CPU and GPU to accelerate the computation of Tatimoto coefficient in measuring the pairwise similarity between different molecular fingerprints. In this paper, we propose and optimize an FPGA-based accelerator design on exhaustive and approximate search algorithms. On exhaustive search using BitBound & fold- ing, we analyze the similarity cutoff and folding level relationship with search speedup and accuracy, and propose a scalable on- the-fly query engine on FPGAs to reduce the resource utilization and pipeline interval. We achieve a 450 million compounds-per- second processing throughput for a single query engine. On approximate search using hierarchical navigable small world (HNSW), a popular algorithm with high recall and query speed, we propose an FPGA-based graph traversal engine to utilize high throughput register array based priority queue and fine- grained distance calculation engine to increase the processing capability. Experimental results show that the proposed FPGA- based HNSW implementation achieves a 35× speedup than existing works on CPU. To the best of our knowledge, our FPGA- based implementation is the first attempt to accelerate molecular similarity search on FPGA and has the highest performance among existing approaches.

Peng, Hongwu↗

Neuromorphic Graph Algorithms

Graph algorithms enable myriad large-scale applications including cybersecurity, social network analysis, resource allocation, and routing. The scalability of current graph algorithm implementations on conventional computing architectures are hampered by the demise of Moore’s law. We present a theoretical framework for designing and assessing the performance of graph algorithms executing in networks of spiking artificial neurons. Although spiking neural networks (SNNs) are capable of general-purpose computation, few algorithmic results with rigorous asymptotic performance analysis are known. SNNs are exceptionally well-motivated practically, as neuromorphic computing systems with 100 million spiking neurons are available, and systems with a billion neurons are anticipated in the next few years. Beyond massive parallelism and scalability, neuromorphic computing systems offer energy consumption orders of magnitude lower than conventional high-performance computing systems. We employ our framework to design and analyze new spiking algorithms for shortest path and dynamic programming problems. Our neuromorphic algorithms are message-passing algorithms relying critically on data movement for computation. For fair and rigorous comparison with conventional algorithms and architectures, which is challenging but paramount, we develop new models of data-movement in conventional computing architectures. This allows us to prove polynomial-factor advantages, even when we assume a SNN consisting of a simple grid-like network of neurons. To the best of our knowledge, this is one of the first examples of a rigorous asymptotic computational advantage for neuromorphic computing.

97 MATHEMATICS AND COMPUTING↗

Portable Parallel Algorithms and Frameworks for Exascale Graph Analytics

Graphs (or networks) are a tool used to model the interactions among various entities. Efficiently processing large graphs has recently attracted significant attention due to the applications of graphs in various domains, such as biology, chemistry, and cyber-security. Analyzing the structure and properties of these graphs is an important component of many scientific computing pipelines. With the explosion in the volume of data, graphs have become very large and can contain hundreds of billions of vertices and trillions of edges. Therefore, it is crucial to develop high-performance methods to enable graph analysis to be done quickly and energy-efficiently. Furthermore, these solutions should be highly parallel in order to take advantage of modern parallel machines. However, designing efficient solutions is not enough. With the wide variety of computing environments available, each with different programmability and performance characteristics, it is necessary to develop solutions that are portable in terms of both performance (i.e., provide theoretical guarantees) and programmability (i.e., provide high level abstractions).

97 MATHEMATICS AND COMPUTING↗

A Computational Framework for the Discovery of Novel Biotransformations (Final Technical Report for DE-FG02-02ER63457)

Development of biotechnologies, such as recombinant DNA and protein engineering, allows us to genetically engineer biological systems for the production of high-value chemicals. Mathematical and computational methods and frameworks are becoming indispensable, powerful tools for gaining a deeper understanding of the function of complex biological systems and for the rational design of genetic and metabolic engineering applications. Under DOE support, a computational framework, the Biochemical Network Integrated Computational Explorer (BNICE), was developed for the construction of metabolic pathways given input substrates and knowledge of enzyme-catalyzed reactions. Graph theory and its associated algorithms are exploited to represent molecules and perform enzyme-catalyzed reactions. Through repetitive application of the set of operators representing the enzymatic reactions of interest to the reactants and their progeny, reaction pathways are generated automatically. The concept of generalized enzyme function is introduced and defined as the third-level enzyme function (EC i.j.k) based on the four-digit transformations of the enzyme classification system (EC i.j.k.l). It maps enzyme-catalyzed reactions to transformations of functional groups and enables the generation of novel species and pathways. The following papers resulted from this grant. The papers that have been published are attached to the end of this report.

59 BASIC BIOLOGICAL SCIENCES↗

Design and simulation of a SiPM-on-tile ZDC for the future EIC, and its performance with graph neural networks

We present a design for a high-granularity zero-degree calorimeter (ZDC) for the upcoming Electron-Ion Collider (EIC). The design uses SiPM-on-tile technology and features a novel staggered-layer arrangement that improves spatial resolution. To fully leverage the design’s high granularity and non-trivial geometry, we employ graph neural networks (GNNs) for energy and angle regression as well as signal classification. The GNN-boosted performance metrics meet, and in some cases, significantly surpass the requirements set in the report on science requirements and detector requirements for the EIC (Yellow Report), laying the groundwork for enhanced measurements that will facilitate a wide physics program. Our studies show that GNNs can significantly enhance the performance of high-granularity CALICE-style calorimeters by automating and optimizing the software compensation algorithms required for these systems. This improvement holds true even in the case of complicated geometries that pose challenges for image-based AI/ML methods.

Calorimeter↗

Pattern ANalytics To Support High-performance Exploitation and Reasoning (PANTHER)

Sandia researchers are developing analytic techniques that efficiently detect patterns in high-volume, noisy, remote sensing and other geospatial data, improving an analysts’ ability to detect possibly off-normal events in complex homeland security, nuclear weapons, and emerging threat environments. High-consequence, national security decisions rely on timely, comprehensive answers to complex questions, yet critical gaps in our approach to these questions remain. PANTHER addresses these gaps through fundamental research on: geospatial-temporal feature extraction via image segmentation and classification; geospatial-temporal graph algorithms and computational geometry; and domain-relevant models of human perception and cognition informing the design of analytic systems. PANTHER’s cross-disciplinary R&D approach uses fundamental science and mathematics to understand how to maximize decision systems through rethinking key aspects of geospatial data analysis. New methods in motion and trajectory analysis support both rapid search for known trajectories as well as rapid clustering and anomaly detection. Thus, the perceptual and visual load on users is reduced by providing pattern analytics with elegant visual cues to spatial and temporal characteristics.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Crunching Large Graphs with Commodity Processors

Crunching large graphs is the basis of many emerging appli- cations, such as social network analysis and bioinformatics. Graph analytics algorithms exhibit little locality and therefore present significant performance challenges. Hardware multi- threading systems (e.g, Cray XMT) show that with enough concurrency, we can tolerate long latencies. Unfortunately, this solution is not available with commodity parts. Our goal is to develop a latency-tolerant system built out of commodity parts and mostly in software. The proposed system includes a runtime that supports a large number of lightweight contexts, full-bit synchronization and a memory manager that provides a high-latency but high-bandwidth global shared memory. This paper lays out the vision for our system, and justifies its feasibility with a performance analysis of the run- time for latency tolerance.

99 GENERAL AND MISCELLANEOUS↗

Using graph neural networks to reconstruct charged pion showers in the CMS High Granularity Calorimeter

A novel method to reconstruct the energy of hadronic showersin the CMS High Granularity Calorimeter (HGCAL) is presented. TheHGCAL is a sampling calorimeter with very fine transverse andlongitudinal granularity. The active media are silicon sensors andscintillator tiles readout by SiPMs and the absorbers are acombination of lead and Cu/CuW in the electromagnetic section, andsteel in the hadronic section. The shower reconstruction method isbased on graph neural networks and it makes use of a dynamicreduction network architecture. It is shown that the algorithm isable to capture and mitigate the main effects that normally hinderthe reconstruction of hadronic showers using classicalreconstruction methods, by compensating for fluctuations in themultiplicity, energy, and spatial distributions of the shower'sconstituents. The performance of the algorithm is evaluated usingtest beam data collected in 2018 prototype of the CMS HGCALaccompanied by a section of the CALICE AHCAL prototype. Thecapability of the method to mitigate the impact of energy leakagefrom the calorimeter is also demonstrated.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

miniVite: A Graph Analytics Benchmarking Tool for Massively Parallel Systems

Benchmarking of high performance computing sys-tems can help provide critical insights for ef?cient design of computing systems and software applications. Although a large number of tools for benchmarking exist, there is a lack of rep-resentative benchmarks for the class of irregular computations as exempli?ed by graph analytics. In this paper, we propose miniVite as a representative graph analytics benchmark tool to test a variety of distributed-memory systems. Graph clustering, popularly known as community detection, is a prototypical graph operation used in numerous scienti?c computing and analytics applications. The goal of clustering is to partition a graph into clusters (or communities) such that each cluster consists of vertices that are densely connected within the cluster and sparsely connected to the rest of the graph. Modu-larity optimization is a popular technique for identifying clusters in a graph. Ef?cient parallelization of modularity optimization-based algorithms is challenging. One successful approach was conceived in Vite, a distributed-memory implementation of the Louvain algorithm that incorporates several heuristics. We introduce miniVite as a representative but simpli?ed variant of Vite, to serve as a prototypical graph analytics benchmarking tool. Unlike other graph-based methods such as breadth-?rst search and betweenness centrality, miniVite represents highly complex computational patterns stressing a variety of system features, which can provide crucial insight for co-design of future computing systems.

community detection, parallel, MPI↗

ADEPT: a domain independent sequence alignment strategy for gpu architectures

Bioinformatic workflows frequently make use of automated genome assembly and protein clustering tools. At the core of most of these tools, a significant portion of execution time is spent in determining optimal local alignment between two sequences. This task is performed with the Smith-Waterman algorithm, which is a dynamic programming based method. With the advent of modern sequencing technologies and increasing size of both genome and protein databases, a need for faster Smith-Waterman implementations has emerged. Multiple SIMD strategies for the Smith-Waterman algorithm are available for CPUs. However, with the move of HPC facilities towards accelerator based architectures, a need for an efficient GPU accelerated strategy has emerged. Existing GPU based strategies have either been optimized for a specific type of characters (Nucleotides or Amino Acids) or for only a handful of application use-cases. In this paper, we present ADEPT, a new sequence alignment strategy for GPU architectures that is domain independent, supporting alignment of sequences from both genomes and proteins. Our proposed strategy uses GPU specific optimizations that do not rely on the nature of sequence. We demonstrate the feasibility of this strategy by implementing the Smith-Waterman algorithm and comparing it to similar CPU strategies as well as the fastest known GPU methods for each domain. ADEPT’s driver enables it to scale across multiple GPUs and allows easy integration into software pipelines which utilize large scale computational systems. We have shown that the ADEPT based Smith-Waterman algorithm demonstrates a peak performance of 360 GCUPS and 497 GCUPs for protein based and DNA based datasets respectively on a single GPU node (8 GPUs) of the Cori Supercomputer. Overall ADEPT shows 10x faster performance in a node-to-node comparison against a corresponding SIMD CPU implementation. ADEPT demonstrates a performance that is either comparable or better than existing GPU strategies. We demonstrated the efficacy of ADEPT in supporting existing bionformatics software pipelines by integrating ADEPT in MetaHipMer a high-performance denovo metagenome assembler and PASTIS a high-performance protein similarity graph construction pipeline. Our results show 10% and 30% boost of performance in MetaHipMer and PASTIS respectively.

59 BASIC BIOLOGICAL SCIENCES↗

Evaluating the Limits of QAOA Parameter Transfer at High-Rounds on Sparse Ising Models With Geometrically Local Cubic Terms

The emergent practical applicability of the Quantum Approximate Optimization Algorithm (QAOA) for approximate combinatorial optimization is a subject of considerable interest. One of the primary limitations of QAOA is the task of finding a set of good parameters, which is usually done using a variational optimization loop. Parameter transfer, or parameter concentration, is a phenomenon where QAOA angles trained on problem instances that are self-similar tend to perform well for other problem instances from that similar class. This suggests a potentially highly efficient and scalable non-variational learning method for QAOA angle finding. In this work, we systematically study QAOA parameter transferability from small problem sizes (16 and 27 decision variables) onto large problem instances (up to 156 qubits) for heavy-hex graph Ising models with geometrically local higher order terms using the Julia based QAOA simulation tool \texttt{JuliQAOA} to perform classical angle finding for up to $49$ QAOA layers ($p$). Parameter transfer of the fixed angles is validated using a combination of full statevector, Projected Entangled Pair States (PEPS), Matrix Product State (MPS), and LOWESA numerical simulations. We find that the QAOA parameter transfer from single instances applied to other (unseen) problem instances does not in general provide monotonically improving performance as a function of $p$ - there are many cases where the performance temporarily decreases as a function of $p$ - but despite this the transferred angles have a general trend of improved expectation value as the QAOA depth increases, in many cases converging close to the true ground-state energy of the $100+$ qubit instances. We also sample the hardware-compatible Ising models using the ensemble of transfer-learned QAOA parameters on several superconducting qubit IBM Quantum processors with 127, 133, and 156 qubits. We find continuous solution quality improvement of the hardware-compatible QAOA circuits run on the IBM NISQ processors up to $p=5$ on \texttt{ibm\_fez}, up to $p=9$ on \texttt{ibm\_torino}, and up to $p=10$ on \texttt{ibm\_pittsburgh}.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Robust implementation of generative modeling with parametrized quantum circuits

Although the performance of hybrid quantum-classical algorithms is highly dependent on the selection of the classical optimizer and the circuit ansätze, a robust and thorough assessment on-hardware of such features has been missing to date. From the optimizer perspective, the primary challenge lies in the solver’s stochastic nature, and their significant variance over the random initialization. Therefore, a robust comparison requires one to perform several training curves for each solver before one can reach conclusions about their typical performance. Since each of the training curves requires the execution of thousands of quantum circuits in the quantum computer, such a robust study remained a steep challenge for most hybrid platforms available today. In this work, we leverage on Rigetti’s Quantum Cloud Services (QCS™) to overcome this implementation barrier, and we study the on-hardware performance of the data-driven quantum circuit learning (DDQCL) for three different state-of-the-art classical solvers, and on two-different circuit ansätze associated to different entangling connectivity graphs for the same task. Additionally, we assess the gains in performance from varying circuit depths. To evaluate the typical performance associated with each of these settings in this benchmark study, we use at least five independent runs of DDQCL towards the generation of quantum generative models capable of capturing the patterns of the canonical Bars and Stripes dataset. In this experimental benchmarking, the gradient-free optimization algorithms show an outstanding performance compared to the gradient-based solver. In particular, one of them had better performance when handling the unavoidable noisy objective function to be minimized under experimental conditions.

97 MATHEMATICS AND COMPUTING↗

Multiview Incomplete Knowledge Graph Integration with application to cross-institutional EHR data harmonization

Objective: The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems. Methods: The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems. Results: With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks. Conclusions: The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.

Zhou, Doudou↗