Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “buffer layer”

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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

20%-efficient polycrystalline Cd(Se,Te) thin-film solar cells with compositional gradient near the front junction

Bandgap gradient is a proven approach for improving the open-circuit voltages (V OC s) in Cu(In,Ga)Se 2 and Cu(Zn,Sn)Se 2 thin-film solar cells, but has not been realized in Cd(Se,Te) thin-film solar cells, a leading thin-film solar cell technology in the photovoltaic market. Here, we demonstrate the realization of a bandgap gradient in Cd(Se,Te) thin-film solar cells by introducing a Cd(O,S,Se,Te) region with the same crystal structure of the absorber near the front junction. The formation of such a region is enabled by incorporating oxygenated CdS and CdSe layers. We show that the introduction of the bandgap gradient reduces the hole density in the front junction region and introduces a small spike in the band alignment between this and the absorber regions, effectively suppressing the nonradiative recombination therein and leading to improved VOCs in Cd(Se,Te) solar cells using commercial SnO 2 buffers. A champion device achieves an efficiency of 20.03% with a V OC of 0.863 V.

14 SOLAR ENERGY↗
NASA NTRS1978

Mars - The role of the regolith in determining atmospheric pressure and the atmosphere's response to insolation changes

A quantitative model for atmosphere-regolith exchange of CO2 on Mars is presented. The model, based on new laboratory measurements of CO2 adsorption on ground rock at 158, 175, 196, and 231 K for CO2 pressures from 1.0 to 80 mbar, is consistent with Viking observations, while models involving a massive residual CO2 cap and no long-term atmosphere-regolith CO2 exchange are not consistent. The model indicates: (1) the atmosphere-plus-cap system is buffered on a long-term basis by exchangeable CO2 adsorbed in the regolith; (2) if the atmosphere-plus-cap system suddenly disappeared, the system would eventually be almost completely restored by reequilibration with the regolith; (3) exchange with the adsorbed phase in the regolith has greatly restricted O-18 enrichment of the atmosphere; (4) the layered terrain primarily represents current periodic pressure increases; and (5) pressures of 100-300 nbar might have existed during the early history of the planet.

Fanale, F. P.↗
NASA NTRS2015

Tetrahedral-Mesh Simulation of Turbulent Flows with the Space-Time Conservative Schemes

Direct numerical simulations of turbulent flows are predominantly carried out using structured, hexahedral meshes despite decades of development in unstructured mesh methods. Tetrahedral meshes offer ease of mesh generation around complex geometries and the potential of an orientation free grid that would provide un-biased small-scale dissipation and more accurate intermediate scale solutions. However, due to the lack of consistent multi-dimensional numerical formulations in conventional schemes for triangular and tetrahedral meshes at the cell interfaces, numerical issues exist when flow discontinuities or stagnation regions are present. The space-time conservative conservation element solution element (CESE) method - due to its Riemann-solver-free shock capturing capabilities, non-dissipative baseline schemes, and flux conservation in time as well as space - has the potential to more accurately simulate turbulent flows using unstructured tetrahedral meshes. To pave the way towards accurate simulation of shock/turbulent boundary-layer interaction, a series of wave and shock interaction benchmark problems that increase in complexity, are computed in this paper with triangular/tetrahedral meshes. Preliminary computations for the normal shock/turbulence interactions are carried out with a relatively coarse mesh, by direct numerical simulations standards, in order to assess other effects such as boundary conditions and the necessity of a buffer domain. The results indicate that qualitative agreement with previous studies can be obtained for flows where, strong shocks co-exist along with unsteady waves that display a broad range of scales, with a relatively compact computational domain and less stringent requirements for grid clustering near the shock. With the space-time conservation properties, stable solutions without any spurious wave reflections can be obtained without a need for buffer domains near the outflow/farfield boundaries. Computational results for the isotropic turbulent flow decay, at a relatively high turbulent Mach number, show a nicely behaved spectral decay rate for medium to high wave numbers. The high-order CESE schemes offer very robust solutions even with the presence of strong shocks or widespread shocklets. The explicit formulation in conjunction with a close to unity theoretical upper Courant number bound has the potential to offer an efficient numerical framework for general compressible turbulent flow simulations with unstructured meshes.

Chang, Chau-Lyan↗
DOE OSTI2020

High Efficiency 6-Junction Solar Cells for the Global and Direct Spectra

We show 6-junction inverted metamorphic solar cells with high efficiencies under both the global and direct spectrum, and discuss improvements to device components. High voltage AlGaInP subcells are demonstrated on GaAs substrates miscut 2° towards (111)B by using Sb surfactant to reduce atomic ordering. This miscut enables high voltage and low dislocation density GaInAs subcells by using atomically-ordered GaInP-based graded buffers. One-sun efficiencies of 39.2 ± 1.3% under the global spectrum and 39.4 ± 1.1% direct spectrum have been demonstrated by using these high voltage subcell components. For high efficiency under the concentrated direct spectrum, low resistance is also necessary, which requires a challenging and nonintuitive optimization of tunnel junctions and heterobarriers. Increasing the thickness of a (Al)GaInAs spacer layer between the back surface fields (BSF) and tunnel junctions (TJ) of latticemismatched subcells reduces nonlinear resistance, which implies a detrimental interaction between the BSF and TJ. Concentrator devices with optimized spacer layers show reduced effective resistance and maintain fill factor > 75% at 1100 suns. Device efficiencies under the concentrated direct spectrum peak at 47.1 ± 3.2% at 143 suns.

41 EE - Solar Energy Technologies Office (EE-4S)↗
DOE OSTI2021

Ultrathin epitaxial NbN superconducting films with high upper critical field grown at low temperature

Ultrathin (5–50 nm) epitaxial superconducting niobium nitride (NbN) films were grown on AlN-buffered c-plane Al 2 O 3 by an industrial scale physical vapor deposition technique at 400°C. Both X-ray diffraction and scanning electron microscopy analysis show high crystallinity of the (111)-oriented NbN films, with a narrow full-width-at-half-maximum of the rocking curve down to 0.030°. The lattice constant decreases with decreasing NbN layer thickness, suggesting lattice strain for films with thicknesses below 20 nm. The superconducting transition temperature, the transition width, the upper critical field, the irreversibility line, and the coherence length are closely correlated to the film thickness. This work realized high quality ultrathin epitaxial NbN films by an industry-scale PVD technology at low substrate temperature, which opens up new opportunities for quantum devices.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Perfectly Matched Layers and Characteristic Boundaries in Lattice Boltzmann: Accuracy vs Cost

Artificial boundary conditions (BCs) play a ubiquitous role in numerical simulations of transport phenomena in several diverse fields, such as fluid dynamics, electromagnetism, acoustics, geophysics, and many more. They are essential for accurately capturing the behavior of physical systems whenever the simulation domain is truncated for computational efficiency purposes. Ideally, an artificial BC would allow relevant information to enter or leave the computational domain without introducing artifacts or unphysical effects. Boundary conditions designed to control spurious wave reflections are referred to as nonreflective boundary conditions (NRBCs). Another approach is given by the perfectly matched layers (PMLs), in which the computational domain is extended with multiple dampening layers, where outgoing waves are absorbed exponentially in time. Here, in this work, the definition of PML is revised in the context of the lattice Boltzmann method. The impact of adopting different types of BCs at the edge of the dampening zone is evaluated and compared, in terms of both accuracy and computational costs. It is shown that for sufficiently large buffer zones, PMLs allow stable and accurate simulations even when using a simple zeroth-order extrapolation BC. Moreover, employing PMLs in combination with NRBCs potentially offers significant gains in accuracy at a modest computational overhead, provided the parameters of the BC are properly tuned to match the properties of the underlying fluid flow.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Long-Life, Ultrahigh-Nickel Cathodes with Excellent Air Storage Stability for High-Energy Density Lithium-Based Batteries

With increased energy density and cost advantage, ultrahigh-nickel layered oxides (LiNi x M 1-x O 2 , x = 0.9 - 1.0) are becoming front-runner as cathodes for next-generation lithium-based batteries, yet their commercialization is blocked both by severe capacity fade and exponentially aggravated air degradation. Thus, it is imperative to find effective solutions to address these issues simultaneously. Here, a significant enhancement in both the cycling and air storage stability of the ultrahigh-Ni cathode LiNi 0.94 Co 0.06 O 2 is achieved via a distinctive phosphoric acid treatment strategy. The modified cathode displays remarkably improved capacity retention (from 36 % to 80 % after 1,000 cycles) and rate capability (from 0 to 105 mA h g -1 at 30C rate) in pouch cells. Impressively, the modified cathode, after air storage for 450 days, maintains the morphology and 92% of the initial capacity of the fresh sample with excellent cyclability. Comprehensive interphase and structural analyses reveal that the enhanced electrochemical performance is due to a highly stabilized electrode/electrolyte interphase that suppresses electrode corrosion and lattice reconstruction. The excellent air stability results from an adsorption-buffering effect enabled by phosphoric acid to air attack. Finally, the study demonstrates an engineering pathway to improve the cycling and air stability, facilitating the practical viability of high-capacity, affordable, ultrahigh-Ni cathodes in lithium-based batteries.

25 ENERGY STORAGE↗
DOE OSTI2023

Topography and canopy cover influence soil organic carbon composition and distribution across a forested hillslope in the discontinuous permafrost zone

Abstract Topography and canopy cover influence ground temperature in warming permafrost landscapes, yet soil temperature heterogeneity introduced by mesotopographic slope positions, microtopographic differences in vegetation cover, and the subsequent impact of contrasting temperature conditions on soil organic carbon (SOC) dynamics are understudied. Buffering of permafrost‐affected soils against warming air temperatures in boreal forests can reflect surface soil characteristics (e.g., thickness of organic material) as well as the degree and type of canopy cover (e.g., open cover vs. closed cover). Both landscape and soil properties interact to determine meso‐ and microscale heterogeneity of ground warming. We sampled a hillslope catena transect in a discontinuous permafrost zone near Fairbanks, Alaska, to test the small‐scale (1 to 3 m) impacts of slope position and cover type on soil organic matter composition. Mineral active layer samples were collected from backslope, low backslope, and footslope positions at depths spanning 19 to 60 cm. We examined soil mineralogical composition, soil moisture, total carbon and nitrogen content, and organic mat thickness in conjunction with an assessment of SOC composition using Fourier‐transform ion cyclotron resonance mass spectrometry (FT‐ICR‐MS). Soils in the footslope position had a higher relative contribution of lignin‐like compounds, whereas backslope soils had more aliphatic and condensed aromatic compounds as determined using FT‐ICR‐MS. The effect of open versus closed tree canopy cover varied with the slope position. On the backslope, we found higher oxidation of molecules under open cover than closed cover, indicating an effect of warmer soil temperature on decomposition. Little to no effect of the canopy was observed in soils at the footslope position, which we attributed, in part, to the strong impact of soil moisture content in SOC dynamics in the water‐gathering footslope position. The thin organic mat under open cover on the backslope position may have contributed to differences in soil temperature and thus SOC oxidation under open and closed canopies. Here, the thinner organic mat did not appear to buffer the underlying soil against warm season air temperatures and thus increased SOC decomposition as indicated by the higher oxidation of SOC molecules and a lower contribution of simple molecules under open cover than the closed canopy sites. Our findings suggest that the role of canopy cover in SOC dynamics varies as a function of landscape position and soil properties, namely, organic mat thickness and soil moisture. Condition‐specific heterogeneity of SOC composition under open and closed canopy cover highlights the protective effect of canopy cover for soils on backslope positions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Reduced Dislocation Introduction in III–V/Si Heterostructures with Glide-Enhancing Compressively Strained Superlattices

The novel use of a GaAs y P 1-y /GaP compressively-strained superlattice (CSS) to provide enhanced control over misfit dislocation (MD) evolution and threading dislocation density (TDD) during GaP/Si metamorphic heteroepitaxy is demonstrated. Here, the insertion of the CSS just after critical thickness, and thus prior to substantial dislocation introduction, is found to yield significantly reduced TDD in relaxed, 500 nm thick, n-type GaP/Si versus comparable control samples. The impact of CSS period count on average TDD and the overall dislocation network morphology was examined, supported by quantitative microstructural characterization, revealing a nearly 20× relative TDD reduction (to 2.4 ± 0.4×10 6 cm -2 ) with a 3-period CSS structure. A similarly low TDD (3.0 ± 0.6×10 6 cm -2 ) is maintained when the resultant n-GaP/Si virtual substrate is used for the growth of a subsequent n-type GaAs 0.75 P 0.25 -terminal GaAs y P 1-y step-graded metamorphic buffer. Although the physical mechanism for TDD reduction provided by these structures is not yet entirely understood, this initial work suggests that enhanced glide dynamics of MDs at or within the CSS placed early in the growth leads to a reduction in the total number of dislocations introduced overall, as opposed to annihilation-based reduction that occurs in conventional strained-layer superlattice dislocation filter approaches.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1996

Dissolution kinetics of a lunar glass simulant at 25 degrees C: the effect of pH and organic acids

The dissolution kinetics of a simulated lunar glass were examined at pH 3, 5, and 7. Additionally, the pH 7 experiments were conducted in the presence of citric and oxalic acid at concentrations of 2 and 20 mM. The organic acids were buffered at pH 7 to examine the effect of each molecule in their dissociated form. At pH 3, 5, and 7, the dissolution of the synthetic lunar glass was observed to proceed via a two-stage process. The first stage involved the parabolic release of Ca, Mg, Al, and Fe, and the linear release of Si. Dissolution was incongruent, creating a leached layer rich in Si and Ti which was verified by transmission electron microscopy (TEM). During the second stage the release of Ca, Mg, Al, and Fe was linear. A coupled diffusion/surface dissolution model was proposed for dissolution of the simulated lunar glass at pH 3, 5, and 7. During the first stage the initial release of mobile cations (i.e., Ca, Mg, Al, Fe) was limited by diffusion through the surface leached layer of the glass (parabolic release), while Si release was controlled by the hydrolysis of the Si-O-Al bonds at the glass surface (linear release). As dissolution continued, the mobile cations diffused from greater depths within the glass surface. A steady-state was then reached where the diffusion rate across the increased path lengths equalled the Si release rate from the surface. In the presence of the organic acids, the dissolution of the synthetic lunar glass proceeded by a one stage process. The release of Ca, Mg, Al, and Fe followed a parabolic relationship, while the release of Si was linear. The relative reactivity of the organic acids used in the experiments was citrate > oxalate. A thinner leached layer rich in Si/Ti, as compared to the pH experiments, was observed using TEM. Rate data suggest that the chemisorption of the organic anion to the surface silanol groups was responsible for enhanced dissolution in the presence of the organic acids. It is proposed that the increased rate of Si release is responsible for the one stage parabolic release of mobile cations and the relatively thin leached layer compared to experiments at pH 3 and 5.

NASA Discipline Life Support Systems↗
DOE OSTI2023

Topography and canopy cover influence soil organic carbon composition and distribution across a forested hillslope in the discontinuous permafrost zone

This dataset contains data used for the paper "Topography and canopy cover influence soil organic carbon composition and distribution across a forested hillslope in the discontinuous permafrost zone". The Related References field will be updated with a full citation when available. Topography and canopy cover influence ground temperature in warming permafrost landscapes, yet soil temperature heterogeneity introduced by meso-topographic slope positions, microtopographic differences in vegetation cover, and the subsequent impact of contrasting temperature conditions to soil organic carbon (SOC) dynamics are understudied. Buffering of permafrost-affected soils against warming air temperatures in boreal forests can reflect surface soil characteristics (e.g., thickness of organic material) as well as the degree and type of canopy cover (e.g., open cover vs closed cover). Both landscape and soil properties interact to determine meso- and micro-scale heterogeneity of ground warming. We sampled a hillslope catena transect in a discontinuous permafrost zone near Fairbanks, Alaska to test the small-scale (1 to 3 meter) impacts of slope position and cover type on soil organic matter composition. Mineral active layer samples were collected from backslope, low backslope, and footslope positions at depths spanning 19 to 60 cm. We examined soil mineralogical composition, soil moisture, total carbon and nitrogen content, and organic mat thickness in conjunction with an assessment of SOC composition using Fourier-transform ion Cyclotron Resonance Mass Spectrometry (FT-ICR-MS). Soils in the footslope position had a higher relative contribution of lignin-like compounds while backslope soils had more aliphatic and condensed aromatic compounds as determined by FT-ICR-MS. The effect of open versus closed tree canopy cover varied with slope position. On the backslope, we found higher oxidation of molecules under open cover compared with closed cover, indicating an effect of warmer soil temperature on decomposition. Little to no effect of canopy was observed for soils at the footslope position, which we attributed, in part, to the strong impact of soil moisture content in SOC dynamics in the water-gathering footslope position. The thin organic mat under open cover on the backslope position may have contributed to differences in soil temperature and thus SOC oxidation under open and closed canopy. Here, the thinner organic mat did not appear to buffer the underlying soil against warm season air temperatures and thus increased SOC decomposition as indicated by higher oxidation of SOC molecules and a lower contribution of simple molecules under open cover compared with the closed canopy sites. Our findings suggest that the role of canopy cover in SOC dynamics varies as a function of landscape position and soil properties, namely organic mat thickness and soil moisture. Condition-specific heterogeneity of SOC composition under open and closed canopy cover highlights the protective effect of canopy cover for soils on backslope positions. This dataset contains a compressed (.zip) archive of the data and R scripts used for this manuscript. The dataset includes files in .csv format, which can be accessed and processed using MS Excel or R. This archive can also be accessed on GitHub at https://github.com/Erin-Rooney/Y1_fairbanks (DOI: 10.5281/zenodo.8071247).

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2001

Development of a fully integrated analysis system for ions based on ion-selective optodes and centrifugal microfluidics

A fully integrated, miniaturized analysis system for ions based on a centrifugal microfluidics platform and ion-selective optode membranes is described. The microfluidic architecture is composed of channels, five solution reservoirs, a measuring chamber, and a waste reservoir manufactured onto a disk-shaped substrate of poly(methyl methacrylate). Ion-selective optode membranes, composed of plasticized poly(vinyl chloride) impregnated with an ionophore, a proton chromoionophore, and a lipophilic anionic additive, were cast, with a spin-on device, onto a support layer and then immobilized on the disk. Fluid propulsion is achieved by the centrifugal force that results from spinning the disk, while a system of valves is built onto the disk to control flow. These valves operate based on fluid properties and fluid/substrate interactions and are controlled by the angular frequency of rotation. With this system, we have been able to deliver calibrant solutions, washing buffers, or "test" solutions to the measuring chamber where the optode membrane is located. An analysis system based on a potassium-selective optode has been characterized. Results indicate that optodes immobilized on the platform demonstrate theoretical responses in an absorbance mode of measurement. Samples of unknown concentration can be quantified to within 3% error by fitting the response function for a given optode membrane using an acid (for measuring the signal for a fully protonated chromoionophore), a base (for fully deprotonated chromoionophore), and two standard solutions. Further, the ability to measure ion concentrations by employing one standard solution in conjunction with acid and base and with two standards alone were studied to delineate whether the current architecture could be simplified. Finally, the efficacy of incorporating washing steps into the calibration protocol was investigated.

NASA Discipline Life Sciences Technologies↗
NASA NTRS1997

Fiber-Optic Temperature Sensor Using a Thin-Film Fabry-Perot Interferometer

A fiber-optic temperature sensor was developed that is rugged, compact, stable, and can be inexpensively fabricated. This thin-film interferometric temperature sensor was shown to be capable of providing a +/- 2 C accuracy over the range of -55 to 275 C, throughout a 5000 hr operating life. A temperature-sensitive thin-film Fabry-Perot interferometer can be deposited directly onto the end of a multimode optical fiber. This batch-fabricatable sensor can be manufactured at a much lower cost than can a presently available sensor, which requires the mechanical attachment of a Fabry-Perot interferometer to a fiber. The principal disadvantage of the thin-film sensor is its inherent instability, due to the low processing temperatures that must be used to prevent degradation of the optical fiber's buffer coating. The design of the stable thin-film temperature sensor considered the potential sources of both short and long term drifts. The temperature- sensitive Fabry-Perot interferometer was a silicon film with a thickness of approx. 2 microns. A laser-annealing process was developed which crystallized the silicon film without damaging the optical fiber. The silicon film was encapsulated with a thin layer of Si3N4 over coated with aluminum. Crystallization of the silicon and its encapsulation with a highly stable, impermeable thin-film structure were essential steps in producing a sensor with the required long-term stability.

Beheim, Glenn↗
DOE OSTI2021

A control oriented comprehensive degradation model for battery energy storage system life prediction

In order to ensure that stationary battery energy storage systems (BESSs) provide reliable energy buffering, both for power quality and economic purposes, the degradation must be considered. Cell degradation involves various side reactions and is highly dependent on its operating conditions. To accurately track cell degradation and predict its impact on battery behavior, a comprehensive physics-based degradation model based on an electrolyte phase-enhanced single particle (SP) model is developed. Key degradation physics, namely solid electrolyte interphase (SEI) layer formation and growth, Li plating on the graphite anode, and Mn dissolution on cathode of nickel-cobalt-manganese oxide (NMC622) are considered. The model is validated against experimental capacity data. The results reveal that the deposition rate of both SEI layer and Li metal increase as the charge voltage increases. At the cathode side, the solvent oxidation rate determines the Mn dissolution rate. As a result, the volume fraction of NMC622 in the cathode continually decreases at a gradually increasing rate.

25 ENERGY STORAGE↗
NASA NTRS1993

Multigrid direct numerical simulation of the whole process of flow transition in 3-D boundary layers

A new technology was developed in this study which provides a successful numerical simulation of the whole process of flow transition in 3-D boundary layers, including linear growth, secondary instability, breakdown, and transition at relatively low CPU cost. Most other spatial numerical simulations require high CPU cost and blow up at the stage of flow breakdown. A fourth-order finite difference scheme on stretched and staggered grids, a fully implicit time marching technique, a semi-coarsening multigrid based on the so-called approximate line-box relaxation, and a buffer domain for the outflow boundary conditions were all used for high-order accuracy, good stability, and fast convergence. A new fine-coarse-fine grid mapping technique was developed to keep the code running after the laminar flow breaks down. The computational results are in good agreement with linear stability theory, secondary instability theory, and some experiments. The cost for a typical case with 162 x 34 x 34 grid is around 2 CRAY-YMP CPU hours for 10 T-S periods.

Liu, Chaoqun↗
NASA NTRS1995

Large-eddy simulations with wall models

The near-wall viscous and buffer regions of wall-bounded flows generally require a large expenditure of computational resources to be resolved adequately, even in large-eddy simulation (LES). Often as much as 50% of the grid points in a computational domain are devoted to these regions. The dense grids that this implies also generally require small time steps for numerical stability and/or accuracy. It is commonly assumed that the inner wall layers are near equilibrium, so that the standard logarithmic law can be applied as the boundary condition for the wall stress well away from the wall, for example, in the logarithmic region, obviating the need to expend large amounts of grid points and computational time in this region. This approach is commonly employed in LES of planetary boundary layers, and it has also been used for some simple engineering flows. In order to calculate accurately a wall-bounded flow with coarse wall resolution, one requires the wall stress as a boundary condition. The goal of this work is to determine the extent to which equilibrium and boundary layer assumptions are valid in the near-wall regions, to develop models for the inner layer based on such assumptions, and to test these modeling ideas in some relatively simple flows with different pressure gradients, such as channel flow and flow over a backward-facing step. Ultimately, models that perform adequately in these situations will be applied to more complex flow configurations, such as an airfoil.

Cabot, W.↗
DOE OSTI2024

Accelerating Application Bulk Synchronous Writes in HPC Environments

High-bandwidth storage tiers are becoming more common for their capability to absorb high-rate, bursty I/Os. Notably, the designs of these fast storage tiers differ from system to system. The variation of these layers and non-uniform methods of access can pose chal- lenges for applications seeking to run at multiple HPC facilities. Therefore, in this work, we present Spectral, a rapid-output ab- straction library to accelerate application, bulk-synchronous writes on HPC systems. We design Spectral to enable applications to use high-bandwidth storage, such as node-local storage and dis- tributed, write-caches (e.g., burst buffers) transparently without requiring modifications to the application or file system source code. The key idea is to allow applications to spend most of the time performing productive work and to not require any source code changes for maximum portability on different HPC archi- tectures. Spectral internally re-routes write-only files through available, high-performance I/O resources before ultimately mi- grating them to the shared global parallel file system. For instance, on Summit, Spectral transparently places application outputs on node-local storage and then utilizes asynchronous migration to the center-wide GPFS file system. We evaluate Spectral on the Summit HPC system (1024 nodes) using the IOR benchmark and real scientific applications. Spectral shows linear performance scaling, improving application write performance by over an order of magnitude when compared to GPFS.

Khan, Awais↗
DOE OSTI2025

DoCeph: DPU-Offloaded Messaging in Ceph for Reduced Host CPU Utilization

Ceph is a widely used distributed object store, but its messenger layer imposes substantial CPU overhead on the host. To address this limitation, we propose DoCeph, a DPU-offloaded storage architecture for Ceph that disaggregates the system by offloading the communication-intensive messaging component to the DPU while retaining the storage backend on the host. The DPU efficiently manages communication, using lightweight RPC for metadata operations and DMA for data transfer. Moreover, DoCeph introduces a pipelining technique that overlaps data transmission with buffer preparation, mitigating hardware-imposed transfer size limitations. We implemented DoCeph on a Ceph cluster with NVIDIA BlueField-3 DPUs. Evaluation results indicate that DoCeph cuts host CPU usage by up to 92% while sustaining stable throughput and providing larger performance benefits for object writes over 1 MB.

Park, Kuri [Sogang University]↗