Search NASA⌕ Search

SEARCH · Search NASA

Results for “Algorithmic portability”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS2021

Online Photometric Calibration of Automatic Gain Thermal Infrared Cameras

Thermal infrared cameras are increasingly being used in various applications such as robot vision, industrial inspection and medical imaging, thanks to their improved resolution and portability. However, the performance of traditional computer vision techniques developed for electro-optical imagery does not directly translate to the thermal domain due to two major reasons: these algorithms require photometric assumptions to hold, and methods for photometric calibration of RGB cameras cannot be applied to thermal-infrared cameras due to difference in data acquisition and sensor phenomenology. In this paper, we take a step in this direction, and introduce a novel algorithm for online photometric calibration of thermalinfrared cameras. Our proposed method does not require any specific driver/hardware support and hence can be applied to any commercial off-the-shelf thermal IR camera. We present this in the context of visual odometry and SLAM algorithms, and demonstrate the efficacy of our proposed system through extensive experiments for both standard benchmark datasets, and real-world field tests with a thermal-infrared camera in natural outdoor environments.

Daftry, Shreyansh↗
DOE OSTI2024

Performance Results on CPU/GPU Exascale Architectures for OMEGA: The Ocean Model for E3SM Global Applications

The US Department of Energy (DOE) conducts climate simulations on some of the world’s largest supercomputers. These exascale machines use heterogeneous architectures with both CPUs and GPUs, and scientific codes must adapt to make full use of this computing power. Los Alamos National Lab is developing Omega: The Ocean Model for E3SM Global Applications, which is specifically designed for modern exascale computers. It uses external libraries that have been optimized for a variety of architectures to run on different supercomputers. Omega is an unstructured-mesh ocean model based on TRiSK numerical methods. It will be the new ocean component of the DOE’s Energy Exascale Earth System Model (E3SM). The algorithms in Omega follow those of the current ocean component, MPAS-Ocean, but it will be written in C++ rather than Fortran to take advantage of the Kokkos performance portability library. Omega spatial operators are written as Kokkos kernels to run efficiently on both CPUs and GPUs. Work on Omega began in 2023 with a new C++ framework for unstructured mesh partitioning, halo exchanges, parallel IO, and Kokkos interfaces. The current version, Omega-0, is being developed to solve the shallow water equations and at present includes all of the tendency terms but not time stepping. Here we share the results of Omega-0 verification and performance testing. Verification includes unit tests implemented with CTest as well as convergence tests in Polaris, an in-house python package with a large suite of test problems. Performance tests compare simulations conducted on CPUs versus GPUs and across different architectures: tests are run on Frontier, which has AMD “Optimized 3rd Gen EPYC” CPUs and AMD MI250X GPUs, as well as Perlmutter, which is composed of AMD EPYC 7763 CPUs and NVIDIA A100 GPUs.

58 GEOSCIENCES↗
NASA NTRS2006

PixelLearn

PixelLearn is an integrated user-interface computer program for classifying pixels in scientific images. Heretofore, training a machine-learning algorithm to classify pixels in images has been tedious and difficult. PixelLearn provides a graphical user interface that makes it faster and more intuitive, leading to more interactive exploration of image data sets. PixelLearn also provides image-enhancement controls to make it easier to see subtle details in images. PixelLearn opens images or sets of images in a variety of common scientific file formats and enables the user to interact with several supervised or unsupervised machine-learning pixel-classifying algorithms while the user continues to browse through the images. The machinelearning algorithms in PixelLearn use advanced clustering and classification methods that enable accuracy much higher than is achievable by most other software previously available for this purpose. PixelLearn is written in portable C++ and runs natively on computers running Linux, Windows, or Mac OS X.

Mazzoni, Dominic↗
NASA NTRS1998

PLUM: Parallel Load Balancing for Unstructured Adaptive Meshes

Dynamic mesh adaption on unstructured grids is a powerful tool for computing large-scale problems that require grid modifications to efficiently resolve solution features. Unfortunately, an efficient parallel implementation is difficult to achieve, primarily due to the load imbalance created by the dynamically-changing nonuniform grid. To address this problem, we have developed PLUM, an automatic portable framework for performing adaptive large-scale numerical computations in a message-passing environment. First, we present an efficient parallel implementation of a tetrahedral mesh adaption scheme. Extremely promising parallel performance is achieved for various refinement and coarsening strategies on a realistic-sized domain. Next we describe PLUM, a novel method for dynamically balancing the processor workloads in adaptive grid computations. This research includes interfacing the parallel mesh adaption procedure based on actual flow solutions to a data remapping module, and incorporating an efficient parallel mesh repartitioner. A significant runtime improvement is achieved by observing that data movement for a refinement step should be performed after the edge-marking phase but before the actual subdivision. We also present optimal and heuristic remapping cost metrics that can accurately predict the total overhead for data redistribution. Several experiments are performed to verify the effectiveness of PLUM on sequences of dynamically adapted unstructured grids. Portability is demonstrated by presenting results on the two vastly different architectures of the SP2 and the Origin2OOO. Additionally, we evaluate the performance of five state-of-the-art partitioning algorithms that can be used within PLUM. It is shown that for certain classes of unsteady adaption, globally repartitioning the computational mesh produces higher quality results than diffusive repartitioning schemes. We also demonstrate that a coarse starting mesh produces high quality load balancing, at a fraction of the cost required a fine initial mesh. Results indicate that our parallel load balancing strategy will remain viable on large numbers of processors.

Oliker, Leonid↗
NASA NTRS1999

Portability and Cross-Platform Performance of an MPI-Based Parallel Polygon Renderer

Visualizing the results of computations performed on large-scale parallel computers is a challenging problem, due to the size of the datasets involved. One approach is to perform the visualization and graphics operations in place, exploiting the available parallelism to obtain the necessary rendering performance. Over the past several years, we have been developing algorithms and software to support visualization applications on NASA's parallel supercomputers. Our results have been incorporated into a parallel polygon rendering system called PGL. PGL was initially developed on tightly-coupled distributed-memory message-passing systems, including Intel's iPSC/860 and Paragon, and IBM's SP2. Over the past year, we have ported it to a variety of additional platforms, including the HP Exemplar, SGI Origin2OOO, Cray T3E, and clusters of Sun workstations. In implementing PGL, we have had two primary goals: cross-platform portability and high performance. Portability is important because (1) our manpower resources are limited, making it difficult to develop and maintain multiple versions of the code, and (2) NASA's complement of parallel computing platforms is diverse and subject to frequent change. Performance is important in delivering adequate rendering rates for complex scenes and ensuring that parallel computing resources are used effectively. Unfortunately, these two goals are often at odds. In this paper we report on our experiences with portability and performance of the PGL polygon renderer across a range of parallel computing platforms.

Crockett, Thomas W.↗
NASA NTRS2004

Enhanced Software for Scheduling Space-Shuttle Processing

The Ground Processing Scheduling System (GPSS) computer program is used to develop streamlined schedules for the inspection, repair, and refurbishment of space shuttles at Kennedy Space Center. A scheduling computer program is needed because space-shuttle processing is complex and it is frequently necessary to modify schedules to accommodate unanticipated events, unavailability of specialized personnel, unexpected delays, and the need to repair newly discovered defects. GPSS implements constraint-based scheduling algorithms and provides an interactive scheduling software environment. In response to inputs, GPSS can respond with schedules that are optimized in the sense that they contain minimal violations of constraints while supporting the most effective and efficient utilization of space-shuttle ground processing resources. The present version of GPSS is a product of re-engineering of a prototype version. While the prototype version proved to be valuable and versatile as a scheduling software tool during the first five years, it was characterized by design and algorithmic deficiencies that affected schedule revisions, query capability, task movement, report capability, and overall interface complexity. In addition, the lack of documentation gave rise to difficulties in maintenance and limited both enhanceability and portability. The goal of the GPSS re-engineering project was to upgrade the prototype into a flexible system that supports multiple- flow, multiple-site scheduling and that retains the strengths of the prototype while incorporating improvements in maintainability, enhanceability, and portability.

Barretta, Joseph A.↗
DOE OSTI2024

Portable Acceleration of CMS Computing Workflows with Coprocessors as a Service

Computing demands for large scientific experiments, such as the CMS experiment at the CERN LHC, will increase dramatically in the next decades. To complement the future performance increases of software running on central processing units (CPUs), explorations of coprocessor usage in data processing hold great potential and interest. Coprocessors are a class of computer processors that supplement CPUs, often improving the execution of certain functions due to architectural design choices. We explore the approach of Services for Optimized Network Inference on Coprocessors (SONIC) and study the deployment of this as-a-service approach in large-scale data processing. In the studies, we take a data processing workflow of the CMS experiment and run the main workflow on CPUs, while offloading several machine learning (ML) inference tasks onto either remote or local coprocessors, specifically graphics processing units (GPUs). With experiments performed at Google Cloud, the Purdue Tier-2 computing center, and combinations of the two, we demonstrate the acceleration of these ML algorithms individually on coprocessors and the corresponding throughput improvement for the entire workflow. This approach can be easily generalized to different types of coprocessors and deployed on local CPUs without decreasing the throughput performance. We emphasize that the SONIC approach enables high coprocessor usage and enables the portability to run workflows on different types of coprocessors.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Fragme∩t: An Open‐Source Framework for Multiscale Quantum Chemistry Based on Fragmentation

Fragment-based quantum chemistry offers a means to circumvent the nonlinear computational scaling of conventional electronic structure calculations, by partitioning a large calculation into smaller subsystems then considering the many-body interactions between them. Variants of this approach have been used to parameterize classical force fields and machine learning potentials, applications that benefit from interoperability between quantum chemistry codes. However, there is a dearth of software that provides interoperability yet is purpose-built to handle the combinatorial complexity of fragment-based calculations. To fill this void we introduce “Fragme∩t”, an open-source software application that provides a tool for community validation of fragment-based methods, a platform for developing new approximations, and a framework for analyzing many-body interactions. Fragme∩t includes algorithms for automatic fragment generation and structure modification, and for distance- and energy-based screening of the requisite subsystems. Checkpointing, database management, and parallelization are handled internally and results are archived in a portable database. Interfaces to various quantum chemistry engines are easy to write and exist already for Q-Chem, PySCF, xTB, Orca, CP2K, MRCC, Psi4, NWChem, GAMESS, and MOPAC. Applications reported here demonstrate parallel efficiencies around 96% on more than 1000 processors but also showcase that the code can handle large-scale protein fragmentation using only workstation hardware, all with a codebase that is designed to be usable by non-experts. Fragme∩t conforms to modern software engineering best practices and is built upon well established technologies including Python, SQLite, and Ray. The source code is available under the Apache 2.0 license.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Static Subspace Approximation for Random Phase Approximation Correlation Energies: Implementation and Performance

Developing theoretical understanding of complex reactions and processes at interfaces requires using methods that go beyond semilocal density functional theory to accurately describe the interactions between solvent, reactants and substrates. Methods based on many-body perturbation theory, such as the random phase approximation (RPA), have previously been limited due to their computational complexity. However, this is now a surmountable barrier due to the advances in computational power available, in particular through modern GPU-based supercomputers. In this work, we describe the implementation of RPA calculations within BerkeleyGW and show its favorable computational performance on large complex systems relevant for catalysis and electrochemistry applications. Our implementation builds off of the static subspace approximation which, by employing a compressed representation of the frequency dependent polarizability, enables the evaluation of the RPA correlation energy with significant acceleration and systematically controllable accuracy. We find that the computational cost of calculating the RPA correlation energy scales only linearly with system size for systems containing up to 50 thousand bands, and is expected to scale quadratically thereafter. We also show excellent strong scaling results across several supercomputers, demonstrating the performance and portability of this implementation.

algorithmic development↗
DOE OSTI2026

Efficient Probabilistic Visualization of Local Divergence of 2D Vector Fields with Independent Gaussian Uncertainty

This work focuses on visualizing uncertainty of local divergence of two-dimensional vector fields. Divergence is one of the fundamental attributes of fluid flows, as it can help domain scientists analyze potential positions of sources (positive divergence) and sinks (negative divergence) in the flow. However, uncertainty inherent in vector field data can lead to erroneous divergence computations, adversely impacting downstream analysis. While Monte Carlo (MC) sampling is a classical approach for estimating divergence uncertainty, it suffers from slow convergence and poor scalability with increasing data size and sample counts. Thus, we present a two-fold contribution that tackles the challenges of slow convergence and limited scalability of the MC approach. (1) We derive a closed-form approach for highly efficient and accurate uncertainty visualization of local divergence, assuming independently Gaussian-distributed vector uncertainties. (2) We further integrate our approach into Viskores, a platform-portable parallel library, to accelerate uncertainty visualization. In our results, we demonstrate significantly enhanced efficiency and accuracy of our serial analytical (speed-up up to 1946×) and parallel Viskores (speed-up up to 19698×) algorithms over the classical serial MC approach. We also demonstrate qualitative improvements of our probabilistic divergence visualizations over traditional mean-field visualization, which disregards uncertainty. We validate the accuracy and efficiency of our methods on wind forecast and ocean simulation datasets.

Ouermi, Timbwaoga [University of Utah]↗
NASA NTRS2004

Innovative Technology Transfer Partnerships

The National Aeronautics and Space Administration (NASA) seeks to license its Advanced Tire and Strut Pressure Monitor (TSPM) technology. The TSPM is a handheld system to accurately measure tire and strut pressure and temperature over a wide temperature range (20 to 120 OF), as well as improve personnel safety. Sensor accuracy, electronics design, and a simple user interface allow operators quick, easy access to required measurements. The handheld electronics, powered by 12-VAC or by 9-VDC batteries, provide the user with an easy-to-read visual display of pressure/temperature or the streaming of pressure/temperature data via an RS-232 interface. When connected to a laptop computer, this new measurement system can provide users with automated data recording and trending, eliminating the chance for data hand-recording errors. In addition, calibration software allows for calibration data to be automatically utilized for the generation of new data conversion equations, simplifying the calibration processes that are so critical to reliable measurements. The design places a high-accuracy pressure sensor (also used as a temperature sensor) as close to the tire or strut measurement location as possible, allowing the user to make accurate measurements rapidly, minimizing the amount of high-pressure volumes, and allowing reasonable distance between the tire or strut and the operator. The pressure sensor attaches directly to the pressure supply/relief valve on the tire and/or strut, with necessary electronics contained in the handheld enclosure. A software algorithm ensures high accuracy of the device over the wide temperature range. Using the pressure sensor as a temperature sensor permits measurement of the actual temperature of the pressurized gas. This device can be adapted to create a portable calibration standard that does not require thermal conditioning. This allows accurate pressure measurements without disturbing the gas temperature. In-place calibration can save considerable time and money and is suitable in many process applications throughout industry.

Kohler, Jeff↗
DOE OSTI2025

Enabling Efficient Sparse Computations using Linear Algebra Aware Compilers

This project developed the LAPIS compiler framework, built on the Multilevel Intermediate Representation (MLIR), to optimize sparse linear algebra operations and support performance portability across diverse architectures. The main innovation of LAPIS is the Kokkos dialect, which allows for lowering codes from a high productivity language to different architectures in an elegant way. The dialect also allows the conversion of lower-level MLIR code to C++ Kokkos code, facilitating the integration of scientific machine learning (SciML) models into applications. To extend LAPIS for distributed memory architectures, a new partition dialect was created to manage the distribution of sparse tensors and express communication patterns for sparse linear algebra operations. This dialect also supports the distributed execution of operators and includes algorithmic optimizations to minimize communication to improve performance. The project also demonstrates that MLIR can enable effective linear algebra-level optimizations, improving performance on different GPUs for both sparse and dense linear algebra kernels. Key applications of LAPIS include sparse linear algebra and graph kernels, TenSQL, a relational database management solution built on GraphBLAS, and the development of subgraph isomorphism and monomorphism kernels, showcasing performance portability. In summary, the LAPIS framework supports productivity, performance, portability, and distributed memory execution, while also enabling linear algebra-level optimizations that are challenging in traditional programming languages, with successful applications ranging from simple sparse linear algebra to complex graph kernels.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2010

NASA Tech Briefs, November 2010

Topics covered include: Portable Handheld Optical Window Inspection Device; Salience Assignment for Multiple-Instance Data and Its Application to Crop Yield Prediction; Speech Acquisition and Automatic Speech Recognition for Integrated Spacesuit Audio Systems ; Predicting Long-Range Traversability from Short-Range Stereo-Derived Geometry; Browser-Based Application for Telemetry Monitoring of Robotic Assets; Miniature Low-Noise G-Band I-Q Receiver; Methods of Using a Magnetic Field Response Sensor Within Closed, Electrically Conductive Containers; Differential Resonant Ring YIG Tuned Oscillator; Microfabricated Segmented-Involute-Foil Regenerator for Stirling Engines; Reducing Seal Adhesion in Low Impact Docking Systems; Optimal Flow Control Design; Corrosion-Resistant Container for Molten-Material Processing; Reusable Hot-Wire Cable Cutter; Deployment of a Curved Truss; High-Volume Airborne Fluids Handling Technologies to Fight Wildfires; Modeling of Alkane Oxidation Using Constituents and Species; Fabrication of Lanthanum Telluride 14-1-11 Zintl High-Temperature Thermoelectric Couple; A Computer Model for Analyzing Volatile Removal Assembly; Analysis of Nozzle Jet Plume Effects on Sonic Boom Signature; Optical Sidebands Multiplier; Single Spatial-Mode Room-Temperature-Operated 3.0 to 3.4 micrometer Diode Lasers; Self-Nulling Beam Combiner Using No External Phase Inverter; Portable Dew Point Mass Spectrometry System for Real-Time Gas and Moisture Analysis; Maximum Likelihood Time-of-Arrival Estimation of Optical Pulses via Photon-Counting Photodetectors; Handheld White Light Interferometer for Measuring Defect Depth in Windows; Decomposition Algorithm for Global Reachability on a Time-Varying Graph; Autonomous GN and C for Spacecraft Exploration of Comets and Asteroids; Efficient Web Services Policy Combination; Using CTX Image Features to Predict HiRISE-Equivalent Rock Density; Isolation of the Paenibacillus phoenicis, a Spore-Forming Bacterium; Monolithically Integrated, Mechanically Resilient Carbon-Based Probes for Scanning Probe Microscopy; Cell Radiation Experiment System; Process to Produce Iron Nanoparticle Lunar Dust Simulant Composite; Inversion Method for Early Detection of ARES-1 Case Breach Failure; Use of ILTV Control Laws for LaNCETS Flight Research;and Evaluating Descent and Ascent Trajectories Near Non-Spherical Bodies.

Source record↗
DOE OSTI2026

Novel thermal energy storage component: Development, performance, and phase transition diagnosis

Thermal energy storage (TES) using phase change materials (PCMs) is a promising technology for capturing and storing excess thermal energy for later use. However, challenges such as poor heat transfer efficiency and a lack of modular, scalable designs have limited widespread adoption of TES in real-world applications. This study developed and evaluated modular brick-type and blade-type TES prototypes featuring an aluminum housing, an embedded serpentine coil for active or passive thermal exchange, and a cost-effective metal mesh to enhance PCM thermal conductivity. The blade-type TES achieved notable geometric efficiency, with a thickness-to-length ratio of 0.03 and a thickness-to-width ratio of 0.08, enabling highly compact and modular thermal storage suitable for space-constrained applications. The paper presents a detailed evaluation of the TES prototypes’ performance. The comparative analysis indicated that the TES prototypes provide a highly cost-effective, thermally optimized alternative for compact energy storage and load shifting. A novel diagnostic technique was also introduced: using a portable endoscope to capture real-time visualizations of PCM phase transitions inside the TES. This method provides critical insights into internal heat transfer mechanisms, identifies potential issues, and offers valuable support for optimizing the TES design and developing the control algorithm. Overall, the modular brick-type and blade-type TES designs demonstrated in this work provide a scalable, efficient, and economically viable solution for advancing TES across residential, commercial, and industrial sectors. The designs’ compact structure, enhanced thermal performance, and integrated diagnostic capabilities make them strong candidates for future deployment in energy-efficient systems.

Gao, Zhiming [ORNL] (ORCID:0000000271397995)↗
DOE OSTI2026

Rasterization with Data-Parallel Primitives

Parallel rasterization can suffer from race conditions during fragment generation, which is traditionally addressed by using specialized hardware accessible via vendor graphics APIs. Unfortunately, graphics APIs are increasingly problematic on high-performance computers, either because they are not provided or because of concerns about dependencies with in situ visualization. In response, we present a hardware-agnostic rasterization algorithm that handles race conditions using only data-parallel primitives (DPPs), enabling efficient rendering on HPC systems without graphics API dependencies and aligning with recent efforts to deliver visualization software with DPPs. Our evaluation consists of three phases: (1) evaluating portability across different CPU and GPU architectures, (2) evaluating competitiveness with a community standard, and (3) evaluating performance across varying workloads and available parallelism. The supporting experiments run on both AMD and NVIDIA GPUs, considering data sets as large as 460 million triangles and 160 million pixels. While performance generally falls short of graphics API baselines, it achieves interactive frame rates on most workloads. As a result, we conclude our approach is a viable solution for rasterization on high-performance computers since our approach is portably performant across different architectures without the need for specialized vendor support.

Buckley, Makani [University of Oregon] (ORCID:0009↗
NASA NTRS1990

TROJID: A portable software package for upper-stage trajectory optimization

Performance optimization for upper-stage exoatmospheric vehicles often is performed within the framework of a full capability trajectory simulation package requiring either a large mainframe computer or powerful work-station. Since these software packages tend to include capabilities providing for high-fidelity boost and reentry simulations, the programs usually are quite large and not very portable. The program TROJID is an attempt to provide an environment for the optimization of upper-stage trajectories within a small package capable of being run on a standard desktop microcomputer. Utilizing a state-of-the-art nonlinear programming algorithm and a trajectory simulator implementing impulsive burns and an analytic coast phase propagator, TROJID is capable of producing trajectories for optimal multi-burn upper-stage orbit transfers. The package has been designed to allow full generality in definition of both the trajectory simulator and the parameter optimization problem.

Hammes, Steven M.↗
NASA NTRS2022

Airborne Visible/Infrared Imaging Spectrometer 3 (AVIRIS-3)

The Airborne Visible/Infrared Imaging Spectrometer 3 (AVIRIS-3) is the third of the NASA AVIRIS spectrometer series and is being developed in parallel with the Compact Wide-swath Imaging Spectrometer II (CWIS-II) for the University of Zurich, Switzerland. The core spectrometer of AVIRIS-3 is a copy of the optically fast, F/1.8 Dyson imaging spectrometer used by the Earth Surface Mineral Dust Source Investigation (EMIT) that is in development and scheduled for launch to the International Space Station (ISS) in 2022. AVIRIS-3 is intended to provide state-of-the-art imaging spectroscopy measurements for NASA science and application through the next decade and beyond. AVIRIS-3 uses the EMIT spectrometer design interfaced with a scaled two mirror telescope enclosed in a portable vacuum vessel to enable measurements from airborne platforms ranging from a Twin Otter to a business jet or a NASA ER-2. AVIRIS-3 is a cryogenic instrument with advanced system control and real-time onboard spectroscopic data processing algorithms evolved from AVIRIS-NG. The spectral range of AVIRIS-3 is 380 to 2500 nm with 7.4 nm sampling. The radiometric range is from 0 to max terrestrial Lambertian radiance with higher signal-to-noise ratio performance than AVIRIS-Classic or AVIRIS-Next Generation. The spatial field-of-view is 39.5 degrees with 0.56 milliradian sampling. This paper describes the design and development of AVIRIS-3 and presents its characteristics in comparison to the previous generation imaging spectrometers.

Helmlinger, Mark↗
DOE OSTI2024

PANDORA: A Parallel Dendrogram Construction Algorithm for Single Linkage Clustering on GPU

This paper introduces Pandora, a parallel algorithm for computing dendrograms, the hierarchical cluster trees for single linkage clustering (SLC). Current parallel approaches construct dendrograms by partitioning a minimum spanning tree and removing edges. However, they struggle with skewed, hard-to-parallelize real-world dendrograms. Consequently, computing dendrograms is the sequential bottleneck in HDBSCAN*[21], a popular SLC variant. Pandora uses recursive tree contraction to address this limitation. Pandora contracts nodes to construct progressively smaller trees. It computes the smallest contracted dendrogram and expands it by inserting contracted edges. This recursive strategy is highly parallel, skew-independent, work-optimal, and well-suited for GPUs and multicores. We develop a performance portable implementation of Pandora in Kokkos[31] and evaluate its performance on multicore CPUs and multi-vendor GPUs (e.g., Nvidia, AMD) for dendrogram construction in HDBSCAN*. Multithreaded Pandora is 2.2x faster than the current best-multithreaded implementation. Our GPU version achieves 6-20x speedup on AMD GPUs and 10-37x on NVIDIA GPUs over multithreaded Pandora. Pandora removes HDBSCAN*’s sequential bottleneck, greatly boosting efficiency, particularly with GPUs.

Sao, Piyush↗