Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallelization Strategy”

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 469 records · Page 26
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

THE QUEST FOR DUSTY STAR-FORMING GALAXIES AT HIGH REDSHIFT z ≳ 4

We exploit the continuity equation approach and “main-sequence” star formation timescales to show that the observed high abundance of galaxies with stellar masses ≳ a few 10{sup 10} M {sub ⊙} at redshift z ≳ 4 implies the existence of a galaxy population featuring large star formation rates (SFRs) ψ ≳ 10{sup 2} M {sub ⊙} yr{sup −1} in heavily dust-obscured conditions. These galaxies constitute the high-redshift counterparts of the dusty star-forming population already surveyed for z ≲ 3 in the far-IR band by the Herschel Space Observatory . We work out specific predictions for the evolution of the corresponding stellar mass and SFR functions out to z ∼ 10, determining that the number density at z ≲ 8 for SFRs ψ ≳ 30 M {sub ⊙} yr{sup −1} cannot be estimated relying on the UV luminosity function alone, even when standard corrections for dust extinction based on the UV slope are applied. We compute the number counts and redshift distributions (including galaxy-scale gravitational lensing) of this galaxy population, and show that current data from the AzTEC - LABOCA , SCUBA-2 , and ALMA - SPT surveys are already addressing it. We demonstrate how an observational strategy based on color preselection in the far-IR or (sub-)millimeter band with Herschel and SCUBA-2 , supplemented by photometric data from on-source observations with ALMA , can allow us to reconstruct the bright end of the SFR functions out to z ≲ 8. In parallel, such a challenging task can be managed by exploiting current UV surveys in combination with (sub-)millimeter observations by ALMA and NIKA2 and/or radio observations by SKA and its precursors.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2015

The GRISM Lens-Amplified Survey from Space (GLASS). I. Survey overview and first data release

We give an overview of the Grism Lens Amplified Survey from Space (GLASS), a large Hubble Space Telescope program aimed at obtaining grism spectroscopy of the fields of 10 massive clusters of galaxies at redshift z = 0.308–0.686, including the Hubble Frontier Fields (HFF). The Wide Field Camera 3 (WFC3) yields near-infrared spectra of the cluster cores covering the wavelength range 0.81–1.69 μm through grisms G102 and G141, while the Advanced Camera for Surveys in parallel mode provides G800L spectra of the infall regions of the clusters. The WFC3 spectra are taken at two almost orthogonal position angles in order to minimize the effects of confusion. After summarizing the scientific drivers of GLASS, we describe the sample selection as well as the observing strategy and data processing pipeline. We then utilize MACS J0717.5+3745, a HFF cluster and the first one observed by GLASS, to illustrate the data quality and the high-level data products. Each spectrum brighter than H{sub AB}=23 is visually inspected by at least two co-authors and a redshift is measured when sufficient information is present in the spectra. Furthermore, we conducted a thorough search for emission lines through all of the GLASS WFC3 spectra with the aim of measuring redshifts for sources with continuum fainter than H{sub AB}=23. We provide a catalog of 139 emission-line-based spectroscopic redshifts for extragalactic sources, including three new redshifts of multiple image systems (one probable, two tentative). In addition to the data itself, we also release software tools that are helpful to navigate the data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2012

Report of the Task Group 186 on model-based dose calculation methods in brachytherapy beyond the TG-43 formalism: Current status and recommendations for clinical implementation

The charge of Task Group 186 (TG-186) is to provide guidance for early adopters of model-based dose calculation algorithms (MBDCAs) for brachytherapy (BT) dose calculations to ensure practice uniformity. Contrary to external beam radiotherapy, heterogeneity correction algorithms have only recently been made available to the BT community. Yet, BT dose calculation accuracy is highly dependent on scatter conditions and photoelectric effect cross-sections relative to water. In specific situations, differences between the current water-based BT dose calculation formalism (TG-43) and MBDCAs can lead to differences in calculated doses exceeding a factor of 10. MBDCAs raise three major issues that are not addressed by current guidance documents: (1) MBDCA calculated doses are sensitive to the dose specification medium, resulting in energy-dependent differences between dose calculated to water in a homogeneous water geometry (TG-43), dose calculated to the local medium in the heterogeneous medium, and the intermediate scenario of dose calculated to a small volume of water in the heterogeneous medium. (2) MBDCA doses are sensitive to voxel-by-voxel interaction cross sections. Neither conventional single-energy CT nor ICRU/ICRP tissue composition compilations provide useful guidance for the task of assigning interaction cross sections to each voxel. (3) Since each patient-source-applicator combination is unique, having reference data for each possible combination to benchmark MBDCAs is an impractical strategy. Hence, a new commissioning process is required. TG-186 addresses in detail the above issues through the literature review and provides explicit recommendations based on the current state of knowledge. TG-43-based dose prescription and dose calculation remain in effect, with MBDCA dose reporting performed in parallel when available. In using MBDCAs, it is recommended that the radiation transport should be performed in the heterogeneous medium and, at minimum, the dose to the local medium be reported along with the TG-43 calculated doses. Assignments of voxel-by-voxel cross sections represent a particular challenge. Electron density information is readily extracted from CT imaging, but cannot be used to distinguish between different materials having the same density. Therefore, a recommendation is made to use a number of standardized materials to maintain uniformity across institutions. Sensitivity analysis shows that this recommendation offers increased accuracy over TG-43. MBDCA commissioning will share commonalities with current TG-43-based systems, but in addition there will be algorithm-specific tasks. Two levels of commissioning are recommended: reproducing TG-43 dose parameters and testing the advanced capabilities of MBDCAs. For validation of heterogeneity and scatter conditions, MBDCAs should mimic the 3D dose distributions from reference virtual geometries. Potential changes in BT dose prescriptions and MBDCA limitations are discussed. When data required for full MBDCA implementation are insufficient, interim recommendations are made and potential areas of research are identified. Application of TG-186 guidance should retain practice uniformity in transitioning from the TG-43 to the MBDCA approach.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2013

Enhancing the MPI Programming Model for PetaScale Systems (Final Report)

This project performed research into enhancing the MPI programming model in two ways: developing improved algorithms and implementation strategies, tested and realized in the MPICH implementation, and exploring extensions to the MPI standard to better support PetaScale and ExaScale systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

XPRESS: eXascale PRogramming Environment and System Software

The XPRESS project is the research and development of a complete software architecture for Exascale computing. The four major R&D thrusts include: 1) an Exascale lightweight kernel operating system (LXK), based on the Kitten operating system (OS), to manage billion way hardware parallelism, management of faults and power, management of global virtual name space, and other features of future system architectures; 2) a runtime system (HPX-5), co-designed with LXK, based on the ParalleX execution model that supports dynamic resource management and task scheduling; 3) system interfaces for interoperability between the runtime system and both the OS and the runtime system (RIOS); 4) compilation strategies and systems to translate MPI and OpenMP legacy codes to a form that can be run with performance at least as good as a native code implementation. The software architecture development has been driven by performance evaluation of mini-applications developed at Department of Energy Co-Design Centers as well as ancillary in-house developed applications and benchmarks. Research on the ParalleX execution model has been driven by the development of formal semantics and model checkers for the execution model. The major components of the software architecture are: ParalleX execution model – guiding principles for co-design of components of the system stack with advances in locality management and task prioritization through introspection; HPX runtime system – support of application dynamic adaptive resource management, task scheduling, and introspective control policies; LXK operating system – lightweight kernel operating system for order-constant scalability and low/no noise to manage resources; RIOS – a realm of Exascale system operation unique in the XPRESS project that includes the relationship between the new generation of lightweight kernel operating systems and runtime system software; XPI advanced programming model – intermediate form and low-level (readable) programming interface reflecting the ParalleX model, providing a target for source-to- source high level parallel language translation, and supporting early direct programming experimentation and measurement; Performance models & metrics – providing parameters and their mutual sensitivities to guide co-design and quantify operational behavior; Legacy migration – ensuring seamless transition of legacy codes and programming methods to the future generation of ParalleX-based Exascale systems; . Experiments and evaluation – critical to determining degree of effectiveness and likelihood of ultimate success as well as guiding corrective design changes to achieve DOE objectives; and Applications – collaborations with Co-Design Centers and other mission critical codes. The exemplar implementation of the ParalleX execution model, HPX-5, has been released along with five fully ported applications (LULESH, HPCG, SSSP, WAMR, and DASHMM) and multiple microbenchmarks. Using these applications, the system architecture demonstrated dynamic load balancing through active migration, legacy code migration, and data-driven approaches to for graph-like applications. Crucially for Exascale and billion way parallelism, the needs and patterns of irregular applications in HPX-5 were addressed using local flow control rather than relying on globally synchronized data structures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

An inertia-free filter line-search algorithm for large-scale nonlinear programming

We present a filter line-search algorithm that does not require inertia information of the linear system. This feature enables the use of a wide range of linear algebra strategies and libraries, which is essential to tackle large-scale problems on modern computing architectures. The proposed approach performs curvature tests along the search step to detect negative curvature and to trigger convexification. We prove that the approach is globally convergent and we implement the approach within a parallel interior-point framework to solve large-scale and highly nonlinear problems. Our numerical tests demonstrate that the inertia-free approach is as efficient as inertia detection via symmetric indefinite factorizations. We also demonstrate that the inertia-free approach can lead to reductions in solution time because it reduces the amount of convexification needed.

Chiang, Nai-Yuan↗
DOE OSTI2025

Enhanced polymorph metastability drives glycine nucleation in aqueous salt solutions

Crystal nucleation from aqueous solutions influences countless geological, biochemical, astrophysical, environmental, and materials science–related phenomena, including ice formation, the manufacturing of active pharmaceutical ingredients, development of diseases such as Alzheimer’s and the origin of life itself. Understanding and controlling nucleation is essential for designing materials with specific properties, developing strategies to inhibit or promote crystallization in various contexts and preventing pathological aggregation in neurodegenerative diseases. Similar to the protein structure prediction problem—where a single amino acid sequence can in theory adopt one most stable conformation but in practice may sample multiple competing conformations—crystal nucleation faces a parallel challenge: the same chemical species can form diverse polymorphs under different environmental conditions (e.g., temperature, pressure, solvent). Each polymorph presents its own set of physical and chemical properties, highlighting the importance of understanding and controlling polymorph selection in fields ranging from pharmaceuticals to materials design. Despite advances in experimental and computational methods for studying phase transitions and polymorph stability, nucleation remains challenging due to its nanoscale nature. Furthermore, in practical settings, salts and impurities can further influence crystal nucleation in diverse contexts, from scaling in pipelines and desalination plants to the durability of concrete and the efficiency of battery materials. This can lead to the formation of polymorphs that may differ from the most stable phase in pure solutions. Or, even though the final structure might appear same irrespective of whether the environment contained impurities or not, the mechanism through which it was formed might be completely different and not intuitive.

Wang, Ruiyu [University of Maryland, College Park,↗
DOE OSTI2024

Quantum simulation of excited states from parallel contracted quantum eigensolvers

Abstract Computing excited-state properties of molecules and solids is considered one of the most important near-term applications of quantum computers. While many of the current excited-state quantum algorithms differ in circuit architecture, specific exploitation of quantum advantage, or result quality, one common feature is their rooting in the Schrödinger equation. However, through contracting (or projecting) the eigenvalue equation, more efficient strategies can be designed for near-term quantum devices. Here we demonstrate that when combined with the Rayleigh–Ritz variational principle for mixed quantum states, the ground-state contracted quantum eigensolver (CQE) can be generalized to compute any number of quantum eigenstates simultaneously. We introduce two excited-state (anti-Hermitian) CQEs that perform the excited-state calculation while inheriting many of the remarkable features of the original ground-state version of the algorithm, such as its scalability. To showcase our approach, we study several model and chemical Hamiltonians and investigate the performance of different implementations.

Physics↗
DOE OSTI2012

Multi-core and Many-core Shared-memory Parallel Raycasting Volume Rendering Optimization and Tuning

Given the computing industry trend of increasing processing capacity by adding more cores to a chip, the focus of this work is tuning the performance of a staple visualization algorithm, raycasting volume rendering, for shared-memory parallelism on multi-core CPUs and many-core GPUs. Our approach is to vary tunable algorithmic settings, along with known algorithmic optimizations and two different memory layouts, and measure performance in terms of absolute runtime and L2 memory cache misses. Our results indicate there is a wide variation in runtime performance on all platforms, as much as 254% for the tunable parameters we test on multi-core CPUs and 265% on many-core GPUs, and the optimal configurations vary across platforms, often in a non-obvious way. For example, our results indicate the optimal configurations on the GPU occur at a crossover point between those that maintain good cache utilization and those that saturate computational throughput. This result is likely to be extremely difficult to predict with an empirical performance model for this particular algorithm because it has an unstructured memory access pattern that varies locally for individual rays and globally for the selected viewpoint. Our results also show that optimal parameters on modern architectures are markedly different from those in previous studies run on older architectures. And, given the dramatic performance variation across platforms for both optimal algorithm settings and performance results, there is a clear benefit for production visualization and analysis codes to adopt a strategy for performance optimization through auto-tuning. These benefits will likely become more pronounced in the future as the number of cores per chip and the cost of moving data through the memory hierarchy both increase.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Chance-Constrained Energy Management System for Power Grids With High Proliferation of Renewables and Electric Vehicles

This paper proposes a two-stage energy management system (EMS) for power grids with massive integration of electric vehicles (EVs) and renewable energy resources. The first stage economic dispatch determines the optimal operating points of charging stations and battery swapping stations (BSS) for EVs under plug-in and battery swapping modes, respectively. The proposed stochastic model predictive control (SMPC) problem in this stage is characterized through a chance-constrained optimization formulation that can effectively capture the system and the forecast uncertainties. A distributed algorithm, the alternating direction method of multipliers (ADMM), is applied to accelerate the optimization computation through parallel computing. The second stage is aimed in coordinating the EV charging mechanisms to continuously follow the first-stage solutions, i.e., the target operating points, and meeting the EV customers' charging demands captured via the Advanced Metering Infrastructure (AMI). In this work, the proposed solution offers a holistic control strategy for large-scale centralized power grids in which the aggregated individual parameters are predictable and the system dynamics do not vary sharply within a short time-interval.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2014

MO-G-17A-03: MR-Based Cortical Bone Segmentation for PET Attenuation Correction with a Non-UTE 3D Fast GRE Sequence

Purpose: To determine the feasibility of identifying cortical bone on MR images with a short-TE 3D fast-GRE sequence for attenuation correction of PET data in PET/MR. Methods: A water-fat-bone phantom was constructed with two pieces of beef shank. MR scans were performed on a 3T MR scanner (GE Discovery™ MR750). A 3D GRE sequence was first employed to measure the level of residual signal in cortical bone (TE{sub 1}/TE{sub 2}/TE{sub 3}=2.2/4.4/6.6ms, TR=20ms, flip angle=25°). For cortical bone segmentation, a 3D fast-GRE sequence (TE/TR=0.7/1.9ms, acquisition voxel size=2.5×2.5×3mm{sup 3}) was implemented along with a 3D Dixon sequence (TE{sub 1}/TE{sub 2}/TR=1.2/2.3/4.0ms, acquisition voxel size=1.25×1.25×3mm{sup 3}) for water/fat imaging. Flip angle (10°), acquisition bandwidth (250kHz), FOV (480×480×144mm{sup 3}) and reconstructed voxel size (0.94×0.94×1.5mm{sup 3}) were kept the same for both sequences. Soft tissue and fat tissue were first segmented on the reconstructed water/fat image. A tissue mask was created by combining the segmented water/fat masks, which was then applied on the fast-GRE image (MRFGRE). A second mask was created to remove the Gibbs artifacts present in regions in close vicinity to the phantom. MRFGRE data was smoothed with a 3D anisotropic diffusion filter for noise reduction, after which cortical bone and air was separated using a threshold determined from the histogram. Results: There is signal in the cortical bone region in the 3D GRE images, indicating the possibility of separating cortical bone and air based on signal intensity from short-TE MR image. The acquisition time for the 3D fast-GRE sequence was 17s, which can be reduced to less than 10s with parallel imaging. The attenuation image created from water-fat-bone segmentation is visually similar compared to reference CT. Conclusion: Cortical bone and air can be separated based on intensity in MR image with a short-TE 3D fast-GRE sequence. Further research is required to optimize the strategy to reduce Gibbs artifacts.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

torch-einshard v1.0

torch-einshard is a Python library for describing local and distributed PyTorch tensor computations with compact, einsum-like notation. Its expressions name logical axes, specify how they are sharded across a PyTorch DeviceMesh, and represent partial reductions. The library automatically performs contractions, permutations, reshaping, splitting, gathering, reduction, reduce-scatter, and repartitioning while preserving autograd. Additional features include sharding-aware FFTs, tensor rolls, halo exchange, sliding windows, 1D–3D convolutions, uneven-shard handling, parameter initialization and gradient management, and cost-based execution planning. It is designed for scientific machine learning and large-model workloads, including tensor-, sequence-, and spatial-parallel MLPs, attention, convolutions, and spectral operations. Compared with manually combining torch.einsum and distributed collectives, torch-einshard expresses both the mathematical operation and data placement in one readable formula. This reduces boilerplate and synchronization errors, keeps forward and backward communication consistent, and allows the library to select optimized collective strategies without changing model code.

Morozov, Dmitriy [Lawrence Berkeley National Labor↗
DOE OSTI2014

Load Balancing Scientific Applications

The largest supercomputers have millions of independent processors, and concurrency levels are rapidly increasing. For ideal efficiency, developers of the simulations that run on these machines must ensure that computational work is evenly balanced among processors. Assigning work evenly is challenging because many large modern parallel codes simulate behavior of physical systems that evolve over time, and their workloads change over time. Furthermore, the cost of imbalanced load increases with scale because most large-scale scientific simulations today use a Single Program Multiple Data (SPMD) parallel programming model, and an increasing number of processors will wait for the slowest one at the synchronization points. To address load imbalance, many large-scale parallel applications use dynamic load balance algorithms to redistribute work evenly. The research objective of this dissertation is to develop methods to decide when and how to load balance the application, and to balance it effectively and affordably. We measure and evaluate the computational load of the application, and develop strategies to decide when and how to correct the imbalance. Depending on the simulation, a fast, local load balance algorithm may be suitable, or a more sophisticated and expensive algorithm may be required. We developed a model for comparison of load balance algorithms for a specific state of the simulation that enables the selection of a balancing algorithm that will minimize overall runtime.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Integrated in silico analyses of regulatory and metabolic networks of Synechococcus sp. PCC 7002 reveal relationships between gene centrality and essentiality

Cyanobacteria dynamically relay environmental inputs to intracellular adaptations through a coordinated adjustment of photosynthetic efficiency and carbon processing rates. The output of such adaptations is reflected through changes in transcriptional patterns and metabolic flux distributions that ultimately define growth strategy. To address interrelationships between metabolism and regulation, we performed integrative analyses of metabolic and gene co-expression networks in a model cyanobacterium, Synechococcus sp. PCC 7002. Centrality analyses using the gene co-expression network identified a set of key genes, which were defined here as ‘topologically important.’ Parallel in silico gene knock-out simulations, using the genome-scale metabolic network, classified what we termed as ‘functionally important’ genes, deletion of which affected growth or metabolism. A strong positive correlation was observed between topologically and functionally important genes. Functionally important genes exhibited variable levels of topological centrality; however, the majority of topologically central genes were found to be functionally essential for growth. Subsequent functional enrichment analysis revealed that both functionally and topologically important genes in Synechococcus sp. PCC 7002 are predominantly associated with translation and energy metabolism, two cellular processes critical for growth. This research demonstrates how synergistic network-level analyses can be used for reconciliation of metabolic and gene expression data to uncover fundamental biological principles.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2017

RElative QUantitation Inferred by Evaluating Mixtures (REQUIEM)

Motivated by the lack of easily implementable and generally applicable strategies to increase and assess data accuracy, we devised a novel label-free approach, termed REQUIEM, to address challenges in relative quantitation. For comparing the relative amounts of analytes in two samples, a mixture is prepared from aliquots of the samples, and the samples and the mixture are analyzed in parallel according to the intended workflow. Processing of the resulting data using the REQUIEM algorithm yields unbiased analyte fold-changes and associated statistics, allowing several types of errors to be diagnosed or eliminated. Extensive simulations and analysis of carefully prepared standard samples demonstrated the rigorous foundations of REQUIEM. We applied REQUIEM to several real-world analytical techniques and workflows, notably to tandem mass spectrometry analysis by using isomeric oligosaccharides as test analytes. Finally, we conclude that REQUIEM can reveal inaccuracies in the data that are difficult to identify by using traditional approaches.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2016

Spectral splitting optimization for high-efficiency solar photovoltaic and thermal power generation

Utilizing the full solar spectrum is desirable to enhance the conversion efficiency of a solar power generator. In practice, this can be achieved through spectral splitting between multiple converters in parallel. However, it is unclear which wavelength bands should be directed to each converter in order to maximize the efficiency. We developed a model of an ideal hybrid solar converter which utilizes both a single-junction photovoltaic cell and a thermal engine. We determined the limiting efficiencies of this hybrid strategy and the corresponding optimum spectral bandwidth directed to the photovoltaic cell. This optimum width is inversely proportional to the thermal engine efficiency and scales with the bandgap of the photovoltaic cell. This bandwidth was also obtained analytically through an entropy minimization scheme and matches well with our model. We show that the maximum efficiency of the system occurs when it minimizes the spectral entropy generation. This concept can be extended to capture generalized non-idealities to increase the usefulness of this technique for a range of full solar spectrum utilization technologies.

14 SOLAR ENERGY↗
DOE OSTI2013

A Medipix quantum area detector allows rotation electron diffraction data collection from submicrometre three-dimensional protein crystals

An ultrasensitive Medipix2 detector allowed the collection of rotation electron-diffraction data from single three-dimensional protein nanocrystals for the first time. The data could be analysed using the standard X-ray crystallography programs MOSFLM and SCALA. When protein crystals are submicrometre-sized, X-ray radiation damage precludes conventional diffraction data collection. For crystals that are of the order of 100 nm in size, at best only single-shot diffraction patterns can be collected and rotation data collection has not been possible, irrespective of the diffraction technique used. Here, it is shown that at a very low electron dose (at most 0.1 e{sup −} Å{sup −2}), a Medipix2 quantum area detector is sufficiently sensitive to allow the collection of a 30-frame rotation series of 200 keV electron-diffraction data from a single ∼100 nm thick protein crystal. A highly parallel 200 keV electron beam (λ = 0.025 Å) allowed observation of the curvature of the Ewald sphere at low resolution, indicating a combined mosaic spread/beam divergence of at most 0.4°. This result shows that volumes of crystal with low mosaicity can be pinpointed in electron diffraction. It is also shown that strategies and data-analysis software (MOSFLM and SCALA) from X-ray protein crystallography can be used in principle for analysing electron-diffraction data from three-dimensional nanocrystals of proteins.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2025

New Results on Communication- and Memory-Aware Load Balancing Model and Algorithms

While load balancing in distributed-memory computing has been well-studied, we present an innovative approach to this problem: a unified, reduced-order model that combines three key components to describe “work” in a distributed system: computation, communication, and memory. Our model enables an optimizer to explore complex tradeoffs in task placement, such as augmented parallelism, at the expense of data replication increasing memory usage. We propose a fully distributed, heuristic-based load balancing optimization algorithm, and demonstrate that it quickly finds close-to-optimal solutions. We formalize the complex optimization problem as a mixed-integer linear program, and compare it to our strategy. Finally, we show that when applied to an electromagnetics code, our approach obtains up to 2.3x speedups for the imbalanced execution.

97 MATHEMATICS AND COMPUTING↗