SEARCH · Search NASA

Results for “parallel application”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 541 records · Page 30

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Predicting Selective Laser Printing Print Quality of Polymer Powders through Melt Flow Index

Selective Laser Sintering (SLS) uses a precisely controlled laser to fuse polymer powder to build complex 3D shapes. While SLS covers a wide application space, the processing knowledge of polymer powder is limited, restricting the number of commercial powders available. This study serves to expand the processing knowledge of polypropylene and polyethylene in parallel with a “mature” SLS feedstock, nylon, through melt flow index (MFI) characterization. Differential Scanning Calorimetry (DSC) was used to explore the sintering window of the polymers. Polyethylene and polypropylene exhibited a relatively narrow sintering window between 4 – 5 °C, whereas the sintering window of nylon was much wider, between 23 – 24 °C. This suggests that the print quality between polyethylene and polypropylene would be similar; however, X-ray computed tomography revealed a higher volume of print defects, voids, and de lamination in polyethylene than in polypropylene. MFI analysis provided additional insight into the difference in print quality, as the MFI of polyethylene was 7.16 g/10 min, 9.95 g/10 min for polypropylene, and 17.23 g/10 min for nylon. MFI is inversely correlated to melt viscosity, and a low melt viscosity is desired for proper coalescing between the layers and particles. These results suggest that MFI is a promising tool, in conjunction with traditional thermal analysis, for screening candidate powder feedstocks for SLS and optimization of print parameters for novel powders.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Development of Integrated Education, Training and Research Program with Interdisciplinary Applications

Plasma models have been formulated including realistic spatial profiles of both flow and radio frequency induced ponderomotive force. With these inclusions the picture of stability of various plasma and fluid instabilities, as expected, changed drastically with ground-breaking consequences. The inhomogeneous parallel flow and the radio frequency waves can actually shown to stabilize turbulence. This is different from the prevalent notion that both parallel flow shear and radio frequency waves are responsible for the excitation (destabilization) of plasma turbulence. This has several ground-breaking consequences:- (1) the stabilization by parallel flow clearly goes against the conventional notion of the origin of ionospheric oscillation which invokes parallel flow destabilization as the origin, (2) the stabilization by parallel flow opens us a new avenue for improved mode formation in fusion devices - which mostly rely on the perpendicular flow shear stabilization for improved mode formation but the perpendicular flow is damped in a tokamak - so the improved mode formed by the parallel flow can sustain longer and has more prospect for ignition, (3) the complete stabilization of the ITG mode (and consequent suppression of transport) not only explain many unknown phenomena in the space physics but it also raises a prospect for transport barrier formation by the RF waves but not by the RF induced flow (as most works suggest) which is never observed in a tokamak of that magnitude to create a barrier. These are indeed ground-breaking consequences.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2021

Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures

Today's high-performance computing (HPC) applications are producing vast volumes of data, which are challenging to store and transfer efficiently during the execution, such that data compression is becoming a critical technique to mitigate the storage burden and data movement cost. Huffman coding is arguably the most efficient Entropy coding algorithm in information theory, such that it could be found as a fundamental step in many modern compression algorithms such as DEFLATE. On the other hand, today's HPC applications are more and more relying on the accelerators such as GPU on supercomputers, while Huffman encoding suffers from low throughput on GPUs, resulting in a significant bottleneck in the entire data processing. In this paper, we propose and implement an efficient Huffman encoding approach based on modern GPU architectures, which addresses two key challenges: (1) how to parallelize the entire Huffman encoding algorithm, including codebook construction, and (2) how to fully utilize the high memory-bandwidth feature of modern GPU architectures. The detailed contribution is fourfold. (1) We develop an efficient parallel codebook construction on GPUs that scales effectively with the number of input symbols. (2) We propose a novel reduction based encoding scheme that can efficiently merge the codewords on GPUs. (3) We optimize the overall GPU performance by leveraging the state-of-the-art CUDA APIs such as Cooperative Groups. (4) We evaluate our Huffman encoder thoroughly using six real-world application datasets on two advanced GPUs and compare with our implemented multi-threaded Huffman encoder. Experiments show that our solution can improve the encoding throughput by up to 5.0x and 6.8x on NVIDIA RTX 5000 and V100, respectively, over the state-of-the-art GPU Huffman encoder, and by up to 3.3x over the multi-thread encoder on two 28-core Xeon Platinum 8280 CPUs.

Tian, Jiannan↗

DOE OSTI2021

Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures

Today's high-performance computing (HPC) applications are producing vast volumes of data, which are challenging to store and transfer efficiently during the execution, such that data compression is becoming a critical technique to mitigate the storage burden and data movement cost. Huffman coding is arguably the most efficient Entropy coding algorithm in information theory, such that it could be found as a fundamental step in many modern compression algorithms such as DEFLATE. On the other hand, today's HPC applications are more and more relying on the accelerators such as GPU on supercomputers, while Huffman encoding suffers from low throughput on GPUs, resulting in a significant bottleneck in the entire data processing. In this paper, we propose and implement an efficient Huffman encoding approach based on modern GPU architectures, which addresses two key challenges: (1) how to parallelize the entire Huffman encoding algorithm, including codebook construction, and (2) how to fully utilize the high memory-bandwidth feature of modern GPU architectures. The detailed contribution is fourfold. (1) We develop an efficient parallel codebook construction on GPUs that scales effectively with the number of input symbols. (2) We propose a novel reduction based encoding scheme that can efficiently merge the codewords on GPUs. (3) We optimize the overall GPU performance by leveraging the state-of-the-art CUDA APIs such as Cooperative Groups. (4) We evaluate our Huffman encoder thoroughly using six real-world application datasets on two advanced GPUs and compare with our implemented multithreaded Huffman encoder. Experiments show that our solution can improve the encoding throughput by up to 5.0× and 6.8× on NVIDIA RTX 5000 and V100, respectively, over the state-of-the-art GPU Huffman encoder, and by up to 3.3× over the multithread encoder on two 28-core Xeon Platinum 8280 CPUs.

Tian, Jiannan↗

DOE OSTI2024

Development of Integrated Education, Training and Research Program with Interdisciplinary Applications II

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2021

Linear and Nonlinear Solvers for Simulating Multiphase Flow within Large-Scale Engineered Subsurface Systems

Simulation of multiphase flow in the subsurface is well-known to be computationally challenging. While there have been many studies that have explored approaches to overcoming these challenges, they often utilize relatively simple case studies. In this paper, we focus on the unique numerical challenges posed by modeling large-scale engineered subsurface systems, characterized by discrete features embedded in a heterogeneous natural subsurface setting. The man-made features such as shafts, tunnels, and barriers often cause multiple challenges in modeling the domain for multiphase porous media flow. This flow scenario can have a wide range of applications such as nuclear waste repositories, enhanced recovery of a petroleum reservoir, geothermal engineering, and carbon sequestration. An example of these severe numerical challenges is the case of performance assessment (PA) for Waste Isolation Pilot Plant (WIPP), the only operating deep geological repository in the US, which simulates extreme material properties of bedded salt rock formation and extreme contrast due to open excavation next to the formation. The models have extremes not only of permeability and porosity but also of the constitutive models needed for multiphase flow; additionally, they have process models like salt creep closure reducing porosity over time, fracturing in clay and anhydrite interbeds of the bedded salt, gas generation from the waste materials, and unintentional human borehole intrusions in some scenarios. Numerical simulations require the solution of coupled systems of nonlinear PDEs; in our work, we use the open-source simulator PFLOTRAN which is based on Finite Volume discretization. The solution of the nonlinear equations requires use of the Newton-Raphson iteration at each time step, which entails the solution of the linearized Jacobian system at each iteration. The effects of all the processes (i.e., large number of unknowns, highly nonlinear constitutive relations, large contrasts in material properties in short distances) lead to an ill-conditioned Jacobian matrix that severely challenges traditional linear solver, i.e., stabilized biconjugate gradient with block Jacobi incomplete LU preconditioner (BCGS-ILU) leading to non-convergence for traditional Newton-Raphson nonlinear solver causing unacceptably long computation time for each model. This paper presents linear solvers such as constrained pressure residual (CPR) two-stage preconditioner with alternate-block-factorization (ABF) and quasi- implicit pressure and explicit saturation (QIMPES) decouplers and flexible generalized residual solver (FGMRES). The new general-purpose nonlinear solver, Newton trust-region dogleg Cauchy (NTRDC), is also introduced to resolve extreme nonlinearities in the models. We demonstrate the effectiveness of each method relative to the default BCGS-Newton solver. The two best cases had nearly 50 times speed-up and achieved completion of a simulation in 14 hours that never completed due to non-convergence with the default solver. We also investigate the strong scalability of each method and discuss some of the deficiencies found for Block Jacobi preconditioner using parallel domain decomposition, and node packing effects of modern processor architecture.

Preconditioner, Nonlinear, Porous media, Multiphas↗

DOE OSTI2022

Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics

We present a novel application of the machine learning / artificial intelligence method called boosted decision trees to estimate physical quantities on field programmable gate arrays (FPGA). The software package fwXmachina features a new architecture called parallel decision paths that allows for deep decision trees with arbitrary number of input variables. It also features a new optimization scheme to use different numbers of bits for each input variable, which produces optimal physics results and ultraefficient FPGA resource utilization. Problems in high energy physics of proton collisions at the Large Hadron Collider (LHC) are considered. Estimation of missing transverse momentum (E T miss ) at the first level trigger system at the High Luminosity LHC (HL-LHC) experiments, with a simplified detector modeled by Delphes, is used to benchmark and characterize the firmware performance. The firmware implementation with a maximum depth of up to 10 using eight input variables of 16-bit precision gives a latency value of $\mathcal{O}$(10) ns, independent of the clock speed, and $\mathcal{O}$(0.1)% of the available FPGA resources without using digital signal processors.

Instruments & Instrumentation↗

DOE OSTI2024

VAN-DAMME: GPU-accelerated and symmetry-assisted quantum optimal control of multi-qubit systems

We present an open-source software package, VAN-DAMME (Versatile Approaches to Numerically Design, Accelerate, and Manipulate Magnetic Excitations), for massively-parallelized quantum optimal control (QOC) calculations of multi-qubit systems. To enable large QOC calculations, the VAN-DAMME software package utilizes symmetry-based techniques with custom GPU-enhanced algorithms. This combined approach allows for the simultaneous computation of hundreds of matrix exponential propagators that efficiently leverage the intra-GPU parallelism found in high-performance GPUs. In addition, to maximize the computational efficiency of the VAN-DAMME code, we carried out several extensive tests on data layout, computational complexity, memory requirements, and performance. These extensive analyses allowed us to develop computationally efficient approaches for evaluating complex-valued matrix exponential propagators based on Padé approximants. To assess the computational performance of our GPU-accelerated VAN-DAMME code, we carried out QOC calculations of systems containing 10 - 15 qubits, which showed that our GPU implementation is 18.4× faster than the corresponding CPU implementation. Our GPU-accelerated enhancements allow efficient calculations of multi-qubit systems, which can be used for the efficient implementation of QOC applications across multiple domains.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

GLUE Code: A framework handling communication and interfaces between scales

Many scientific applications are inherently multiscale in nature. Such complex physical phenomena often require simultaneous execution and coordination of simulations spanning multiple time and length scales. This is possible by combining expensive small-scale simulations (such as molecular dynamics simulations) with larger scale simulations (such continuum limit/hydro solvers) to allow for considerably larger systems using task and data parallelism. However, the granularity of the tasks can be very large and often leads to load imbalance. Traditionally, we use approximations to streamline the computation of the more costly interactions and this introduces trade-offs between simulation cost and accuracy. In recent years, the available computational power and the advances in machine learning have made computing these scale-bridging interactions and multiscale simulations more feasible. One driving application has been plasma modeling in inertial confinement fusion (ICF), which is fundamentally multiscale in nature. This requires deep understanding of how to extrapolate microscopic information into macroscopically relevant scales. For example, in ICF one needs an accurate understanding of the connection between experimental observables and the underlying microphysics. The properties of the larger scales are often affected by the microscale behavior incorporated usually into the equations of state and ionic and electronic transport coefficients (Liboff, 1959; Rinderknecht et al., 2014; Rosenberg et al., 2015; Ross et al., 2017). Instead of incorporating this information using reliable molecular dynamics (MD) simulations, one often needs to use theoretical models, due to the inability of MD to reach engineering scales (Glosli et al., 2007; Marinak et al., 1998). One approach to resolve this issue is by coupling two MD simulations of different scales via force interpolation, e.g., the AdResS method (Krekeler et al., 2018; Nagarajan et al., 2013). Another approach, which we will pursue in the scope of this work, is by enabling scale bridging between MD simulations and meso/macro-scale models through the development and support of application programming interfaces that these different applications can interact through.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

DeepFreeze: Towards Scalable Asynchronous Checkpointing of Deep Learning Models

In the age of big data, deep learning has emerged as a powerful tool to extract insight and exploit its value, both in industry and scientific applications. One common pattern emerging in such applications is frequent checkpointing of the state of the learning model during training, needed in a variety of scenarios: analysis of intermediate states to explain features and correlations with training data, exploration strategies involving alternative models that share a common ancestor, knowledge transfer, resilience, etc. However, with increasing size of the learning models and popularity of distributed data-parallel training approaches, simple checkpointing techniques used so far face several limitations: low serialization performance, blocking I/O, stragglers due to the fact that only a single process is involved in checkpointing. This paper proposes a checkpointing technique specifically designed to address the aforementioned limitations, introducing efficient asynchronous techniques to hide the overhead of serialization and I/O, and distribute the load over all participating processes. Experiments with two deep learning applications (CANDLE and ResNet) on a pre-Exascale HPC platform (Theta) shows significant improvement over state-of-art, both in terms of checkpointing duration and runtime overhead.

checkpointing↗

DOE OSTI2025

Wide-Bandgap Semiconductor Amplifiers for Fusion Plasma Heating and Control

This paper discusses power electronics developed under the ARPA-E GAMOW program to support nuclear fusion power production. The goal of this project was to develop and assess the potential for wide-bandgap (WBG) semiconductor devices in power electronics to enable high-efficiency and high-voltage solid-state systems for fusion plasma generation, heating, and control. The power electronics use an architecture in which multiple high-power boards can be combined to produce megawatt-level power, where using multiple boards provides high reliability. Two main areas of power electronics boards are developed in this project for fusion plasma heating and control applications: (1) pulse generation and control and (2) radiofrequency generation. The first area is for boards capable of driving high-voltage millisecond pulses at high duty cycles. The envisioned application of these pulses is in plasma control of magnetohydrodynamic instabilities, plasma position, and edge-localized modes. Pulse-width modulation allows for the implementation of a wide variety of linear and nonlinear control systems. The boards developed for this project could actuate control coils based on digital input signals and can be parallelized to provide megawatts of output power. The design of the pulse generator is a low-side load switch. A load switch was designed and constructed that utilized 2-kV-rated field-effect transistor (FET)-based cascodes developed by Qorvo under this project to perform initial testing of these cascodes. The second area is being implemented using class E amplifiers with WBG devices and a reactance steering network to handle inductive or capacitive plasma loads. Applications include ion cyclotron resonance heating (ICRH) and high-harmonic fast-wave (HHFW) heating. A class E reactance steering network is demonstrated in modeling and experiment with a resistive-inductive load that models an inductively-coupled plasma. Power combining of boards with class E reactance steering networks is also simulated and demonstrated experimentally, to enable scaling up to high power. Modeling of high-power-density cooling and remaining useful life is conducted to enable reliable, effectively cooled high-power electronics for fusion applications.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2023

Formation and Shape Changing of Conductive Helical Ribbons via Deposition of Highly Stressed Films on Mechanically Responsive Substrates

Abstract This work demonstrates that the electrodeposition of highly stressed films on compliant ribbons is a robust process to obtain helical structures with excellent mechanical stability and potentially high thermal and electrical conductance. Electrodeposition on end‐tethered ribbons alters their axial and bending stiffness while imparting mechanical stress to drive the formation of a helix with a microscale diameter and pitch in a controlled and scalable manner. The process generates helices with diameters and pitches between 80 and 200 µm and lengths as large as several millimeters. The approach is amenable to parallel processing a large number of 3D structures on any substrate, including large‐area semiconductor wafers. This phenomenon is explained in terms of the change of stress gradients as material is added. Applications of the fabricated helices include antennas, metamaterials, and slow‐wave structures in frequency ranges not previously attainable.

Chemistry↗

DOE OSTI2026

Deep Gaussian process-based cost-aware batch Bayesian optimization for complex materials design campaigns

The accelerating pace and expanding scope of materials discovery demand optimization frameworks that efficiently navigate vast design spaces with complex response surfaces while judiciously allocating limited evaluation resources. We present a cost-aware, batch Bayesian optimization scheme powered by deep Gaussian process (DGP) surrogates and a heterotopic querying strategy. Our DGP surrogate, formed by stacking GP layers, models complex hierarchical relationships among high-dimensional compositional features and captures correlations across multiple target properties, propagating uncertainty through successive layers. We integrate evaluation cost into an upper-confidence-bound acquisition extension, which, together with heterotopic querying, proposes small batches of candidates in parallel, balancing exploration of under-characterized regions with exploitation of high-mean, low-variance predictions across correlated properties. Applied to refractory high-entropy alloys for high-temperature applications, our framework converges to optimal formulations in fewer iterations with cost-aware queries than conventional GP-based BO, highlighting the value of deep, uncertainty-aware, cost-sensitive strategies in materials campaigns.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Multifunctional nanopore electrode array method for characterizing and manipulating single entities in attoliter-volume enclosures

Structurally regular nanopore arrays fabricated to contain independently controllable annular electrodes represent a new kind of architecture capable of electrochemically addressing small collections of matter—down to the single entity (molecule, particle, and biological cell) level. Furthermore, these nanopore electrode arrays (NEAs) can also be interrogated optically to achieve single entity spectroelectrochemistry. Larger entities such as nanoparticles and single bacterial cells are investigated by dark-field scattering and potential-controlled single-cell luminescence experiments, respectively, while NEA-confined molecules are probed by single molecule luminescence. By carrying out these experiments in arrays of identically constructed nanopores, massively parallel collections of single entities can be investigated simultaneously. The multilayer metal–insulator design of the NEAs enables highly efficient redox cycling experiments with large increases in analytical sensitivity for chemical sensing applications. NEAs may also be augmented with an additional orthogonally designed nanopore layer, such as a structured block copolymer, to achieve hierarchically organized multilayer structures with multiple stimulus-responsive transport control mechanisms. Finally, NEAs constructed with a transparent bottom layer permit optical access to the interior of the nanopore, which can result in the cutoff of far-field mode propagation, effectively trapping radiation in an ultrasmall volume inside the nanopore. Furthermore, the bottom metal layer may be used as both a working electrode and an optical cladding layer, thus, producing bifunctional electrochemical zero-mode waveguide architectures capable of carrying out spectroelectrochemical investigations down to the single molecule level.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Sequence length scaling in vision transformers for scientific images on frontier

Vision Transformers (ViTs) are pivotal for foundational models in scientific imagery, including Earth science applications, due to their capability to process large sequence lengths. While transformers for text have inspired scaling sequence lengths in ViTs, adapting these for ViTs introduces unique challenges. We develop distributed sequence parallelism for ViTs, enabling them to handle up to 1M tokens. Our approach, leveraging DeepSpeed-Ulysses and Long-Sequence-Segmentation with model sharding, is the first to apply sequence parallelism in ViT training, achieving a 94% batch scaling efficiency on 2,048 AMD-MI250X GPUs. Evaluating sequence parallelism in ViTs, particularly in models up to 10B parameters, highlighted substantial bottlenecks. We countered these with hybrid sequence, pipeline, and flash attention strategies, to scale beyond single GPU memory limits. Our method significantly enhances climate modeling accuracy by 20% in temperature predictions, marking the first training of a vision transformer model to convergence with a sequence length of 188K tokens, using full self-attention.

Tsaris, Aristeidis (aris) [ORNL] (ORCID:0000000277↗

DOE OSTI2025

Cardinal: Seismic and Geoacoustic Array Processing

Data collected via seismic and infrasound array deployments are leveraged in the geosciences to detect and characterize a myriad of natural and anthropogenic sources. These deployments consist of numerous sensors placed in a predetermined configuration to amplify signal strength and improve the efficacy of array processing techniques used to measure signal directionality and waveform coherence. High‐fidelity feature extraction is often predicated on interstation distance as well as the frequency content and wavelength of an incident signal. Numerous array processing softwares analyze data in sequential frequency bands to obtain a more detailed characterization of a signal. However, current algorithms are limited in their ability to determine optimal array configuration for each band. We introduce an open‐source Python code, called Cardinal, to process seismic and infrasound array data in discretized time–frequency space with the option of applying an adaptive array design to determine optimal subarray configuration for each frequency band. To reduce computational time, the array processing step can be run in parallel using multithreading. Furthermore, the software has the capability to aggregate array processing results from different time–frequency pixels to produce separate sets of detections, or families, with added utility via the application of an adaptive semblance threshold, which aids in isolating signals‐of‐interest from coherent background noise. Upon appropriate configuration, Cardinal exhibits the potential to combine distinct seismic and infrasound phases into separate families.

Adaptive Array↗

DOE OSTI2024

Novel Full-Ceramic Multi-Tubular Membrane Systems for Pre-Combustion CO2 Capture with Simultaneous H2 Production: Fabrication, Performance Testing, and 3D CFD Modeling

Inorganic membranes show promise for application in pre-combustion CO2 capture with simultaneous H2 production. State-of-the-art systems for use under high temperature and pressure conditions consist of multiple membrane tube bundles prepared in a "candle-filter" configuration, in which the membrane tubes are open at one end and sealed at the other. This configuration is used for practical reasons, specifically the need to minimize potential problems due to thermal expansion mismatch, at high temperatures, between the ceramic tube bundle and the steel housing. The primary technical problem with the candle-filter configuration for use in commercial-scale installations is the inability to purge the permeate side (typically the tube side), a feature that is crucial for high H2 recovery. In this study, we fabricated dual-end open, commercial-size ceramic multiple-tube bundles made of zeolite, palladium (Pd), and carbon molecular sieve (CMS) membranes that enable permeate-side (tube-side) purge for gas separation applications. Experimental gas separation data with these membrane bundles under harsh operating conditions (temperatures up to 350 and pressures up to 800 psig), to be presented at the meeting, manifest excellent performance. Parallel to the membrane bundle construction and testing efforts, we have also developed a detailed 3D CFD modeling package using COMSOL Multiphysics software to gain more insight into the effect on the H2 purity and recovery of the detailed geometry of the multi-tubular membrane system, including the number of tubes used, their dimensions, and placement in the bundle, as well as the number, type, and positioning of internal baffles and other flow-enhancement accessories. The CFD package is validated with experimental data from different systems (1-tube, 3-tube, and 19-tube bundles), and shows high accuracy in predicting the experimental results (<5 % error in all cases). The results of our study show that the detailed internal geometry of these multi-tubular membrane systems has a considerable impact on the performance of the system as the flow maldistribution within the shell-side can substantially decrease (>40%) the H2 recovery.

20 FOSSIL-FUELED POWER PLANTS↗

DOE OSTI2020

TriC: Distributed-memory Triangle Counting by Exploiting the Graph Structure

Graph analytics has emerged as an important tool in the analysis of large scale data from diverse application domains such as social networks, cyber security and bioinformatics. Counting the number of triangles in a graph is a fundamental kernel with several applications such as detecting the community structure of a graph or in identifying important vertices in a graph. The ubiquity of massive datasets is driving the need to scale graph analytics on parallel systems. However, numerous challenges exist in efficiently parallelizing graph algorithms, especially on distributed-memory systems. Irregular memory accesses and communication patterns, low computation to communication ratios, and the need for frequent synchronization are some of the leading challenges. In this paper, we present TriC, our distributed-memory implementation of triangle counting in graphs using the Message Passing Interface (MPI), as a submission to the 2020 GraphChallenge competition. Using a set of synthetic and real-world inputs from the challenge, we demonstrate a speedup of up to 90x relative to previous work on 32 processor-cores of a NERSC Cori node. We also provide details from distributed runs with up to8192 processes along with strong scaling results. The observations presented in this work provide an understanding of the system-level bottlenecks at scale that specifically impact sparse-irregular workloads and will therefore benefit other efforts to parallelize graph algorithms.

Halappanavar, Mahantesh↗