Search NASA⌕ Search

SEARCH · Search NASA

Results for “Node selection”

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 559 records · Page 31

Role of W and Mn for reliable 1X nanometer-node ultra-large-scale integration Cu interconnects proved by atom probe tomography

We used atom probe tomography (APT) to study the use of a Cu(Mn) as a seed layer of Cu, and a Co(W) single-layer as reliable Cu diffusion barriers for future interconnects in ultra-large-scale integration. The use of Co(W) layer enhances adhesion of Cu to prevent electromigration and stress-induced voiding failures. The use of Cu(Mn) as seed layer may enhance the diffusion barrier performance of Co(W) by stuffing the Cu diffusion pass with Mn. APT was used to visualize the distribution of W and Mn in three dimensions with sub-nanometer resolution. W was found to segregate at the grain boundaries of Co, which prevents diffusion of Cu via the grain boundaries. Mn was found to diffuse from the Cu(Mn) layer to Co(W) layer and selectively segregate at the Co(W) grain boundaries with W, reinforcing the barrier properties of Co(W) layer. Hence, a Co(W) barrier coupled with a Cu(Mn) seed layer can form a sufficient diffusion barrier with film that is less than 2.0-nm-thick. The diffusion barrier behavior was preserved following a 1-h annealing at 400 °C. The underlayer of the Cu interconnects requires a large adhesion strength with the Cu, as well as low electrical resistivity. The use of Co(W) has previously been shown to satisfy these requirements, and addition of Mn is not expected to deteriorate these properties.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Community detection in sequence similarity networks based on attribute clustering

Networks are powerful tools for the presentation and analysis of interactions in multi-component systems. A commonly studied mesoscopic feature of networks is their community structure, which arises from grouping together similar nodes into one community and dissimilar nodes into separate communities. Here in this paper, the community structure of protein sequence similarity networks is determined with a new method: Attribute Clustering Dependent Communities (ACDC). Sequence similarity has hitherto typically been quantified by the alignment score or its expectation value. However, pair alignments with the same score or expectation value cannot thus be differentiated. To overcome this deficiency, the method constructs, for pair alignments, an extended alignment metric, the link attribute vector, which includes the score and other alignment characteristics. Rescaling components of the attribute vectors qualitatively identifies a systematic variation of sequence similarity within protein superfamilies. The problem of community detection is then mapped to clustering the link attribute vectors, selection of an optimal subset of links and community structure refinement based on the partition density of the network. ACDC-predicted communities are found to be in good agreement with gold standard sequence databases for which the "ground truth" community structures (or families) are known. ACDC is therefore a community detection method for sequence similarity networks based entirely on pair similarity information. A serial implementation of ACDC is available from https://cmb.ornl.gov/resources/developments

59 BASIC BIOLOGICAL SCIENCES↗

MOF-enabled confinement and related effects for chemical catalyst presentation and utilization

A defining characteristic of nearly all catalytically functional MOFs is uniform, molecular-scale porosity. MOF pores, linkers and nodes that define them, help regulate reactant and product transport, catalyst siting, catalyst accessibility, catalyst stability, catalyst activity, co-catalyst proximity, composition of the chemical environment at and beyond the catalytic active site, chemical intermediate and transition-state conformations, thermodynamic affinity of molecular guests for MOF interior sites, framework charge and density of charge-compensating ions, pore hydrophobicity/hydrophilicity, pore and channel rigidity vs. flexibility, and other features and properties. Collectively and individually, these properties help define overall catalyst functional behaviour. Here, this review focuses on how porous, catalyst-containing MOFs capitalize on molecular-scale confinement, containment, isolation, environment modulation, energy delivery, and mobility to accomplish desired chemical transformations with potentially superior selectivity or other efficacy, especially in comparison to catalysts in homogeneous solution environments.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Examining Metal Identity and Proximity Effects on Acetylene Hydrogenation with Azolate-Based MOFs

Liquid organic hydrogen carriers (LOHCs) are an attractive fuel source due to their compatibility with existing transportation methods and ease of use. However, they suffer from sluggish (de)hydrogenation kinetics. One promising platform for developing next-generation catalysts is metal–organic frameworks (MOFs), which can enable systematic interrogation into the influence of metal identity and spatial arrangement. In this study, the effect of the coordination environment was investigated using Ni- and Co-based azolate MOFs: MFU-4l-OH (M x Zn 5–x (OH) 4 (BTDD) 3 ; x = 4 for M = Co and x = 3 for M = Ni, H 2 BTDD = bis(1H-1,2,3-triazolo[4,5-b][4′,5′-i])dibenzo[1,4]dioxin), composed of single-site nodes, and M(OH) 2 BBTA (M = Ni, Co; H 2 BBTA = 1H,5H-benzo(1,2-d:4,5-d’)bistriazole), composed of extended chain-type nodes. The catalysts were characterized by isotherms, powder X-ray diffraction (PXRD), scanning electron microscopy (SEM), inductively coupled plasma-optical emission spectroscopy (ICP-OES), and X-ray photoelectron spectroscopy (XPS) analysis. Acetylene hydrogenation activity under steady state conditions (150 °C, 1:1 C 2 H 2 :H 2 ) revealed higher turnover frequencies (TOFs) up 1.17 × 10 –2 mol C 2 H 2 mol −1 Ni min −1 and 1.98 × 10 –3 mol C 2 H 2 mol −1 Co min −1 for Ni-MFU-4l-OH and Co-MFU-4l-OH, respectively, compared to their BBTA analogues. However, the Co-based MOFs, particularly Co 2 (OH) 2 -BBTA, exhibited greater selectivity (up to 19%) for the fully hydrogenated ethane product. Isosteric heat of adsorption (Q st ) measurements for ethylene and ethane revealed that the BBTA framework had stronger binding to the products than MFU-4l. Furthermore, these findings demonstrate that metal identity and coordination environment may modulate acetylene hydrogenation performance, leading to design principles for tuning LOHC hydrogenation catalysts.

catalysts↗

Molecular and Serological Survey of Selected Viruses in Free-Ranging Wild Ruminants in Iran

A molecular and serological survey of selected viruses in free-ranging wild ruminants was conducted in 13 different districts in Iran. Samples were collected from 64 small wild ruminants belonging to four different species including 25 Mouflon (Ovis orientalis), 22 wild goat (Capra aegagrus), nine Indian gazelle (Gazella bennettii) and eight Goitered gazelle (Gazella subgutturosa) during the national survey for wildlife diseases in Iran. Serum samples were evaluated using serologic antibody tests for Peste de petits ruminants virus (PPRV), Pestiviruses [Border Disease virus (BVD) and Bovine Viral Diarrhoea virus (BVDV)], Bluetongue virus (BTV), Bovine herpesvirus type 1 (BHV-1), and Parainfluenza type 3 (PI3). Sera were also ELISA tested for Pestivirus antigen. Tissue samples including spleen, liver, lung, tonsils, mesenteric and mediastinal lymph nodes and white blood cells (WBCs) were tested using polymerase chain reaction (PCR) for PPRV, Foot and Mouth Disease virus (FMDV), Pestivirus, BTV, Ovine herpesvirus type 2 (OvHV-2) and BHV-1. Serologic tests were positive for antibodies against PPRV (17%), Pestiviruses (2%) and BTV (2%). No antibodies were detected for BHV-1 or PI3, and no Pestivirus antigen was detected. PCR results were positive for PPRV (7.8%), FMDV (11%), BTV (3%), OvHV-2 (31%) and BHV-1 (1.5%). Finally, none of the samples were positive for Pestiviruses.

59 BASIC BIOLOGICAL SCIENCES↗

Conforming quadrilaterals meshes on the cubed sphere.

The cubed sphere geometry, obtained by inscribing a cube in a sphere and mapping points between the two surfaces using a gnomonic (central) projection, is commonly used in atmospheric models because it is free of polar singularities and is well-suited for parallel computing. Global meshes on the cubed-sphere typically project uniform (square) grids from each face of the cube onto the sphere, and if refinement is desired then it is done with non-conforming meshes - overlaying the area of interest with a finer uniform mesh, which introduces so-called hanging nodes on edges along the boundary of the fine resolution area. An alternate technique is to tile each face of the cube with quadrilaterals without requiring the quads to be rectangular. These meshes allow for refinement in areas of interest with a conforming mesh, providing a smoother transition between high and low resolution portions of the grid than non-conforming refinement. The conforming meshes are demonstrated in HOMME, NCAR's High Order Method Modeling Environment, where two modifications have been made: the dependence on uniform meshes has been removed, and the ability to read arbitrary quadrilateral meshes from a previously-generated file has been added. Numerical results come from a conservative spectral element method modeling a selection of the standard shallow water test cases.

99 GENERAL AND MISCELLANEOUS↗

Stable metal–organic framework-supported niobium catalysts

In this study by developing structurally well-defined, supported oxide catalysts remains a significant challenge. Here, we report the grafting of Nb(V) oxide sites onto the nodes of the Zr-based metal organic framework (MOF) NU-1000 as a stable, well-defined catalyst support. Nb(V) oxide was deposited with loadings up to 1.6 mmol/g via two post-synthetic methods: atomic layer deposition in a MOF (AIM), and solution-phase grafting in a MOF (SIM). Difference envelope density (DED) measurements indicated that the two synthetic methods resulted in different local structures of the Nb(V) ions within NU-1000. Despite their high Nb(V) loadings, which were equivalent to >60% surface coverage, nearly all Nb(V) sites of the MOF-supported catalysts were active sites for alkene epoxidation, as confirmed by phenylphosphonic acid titration. The MOF-supported catalysts were more selective than the control Nb-ZrO 2 catalyst for cyclohexene epoxidation with aqueous H 2 O 2 , and were far more active on a gravimetric basis.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Impacts of the IBM Cell Processor to Support Climate Models

NASA is interested in the performance and cost benefits for adapting its applications to the IBM Cell processor. However, its 256KB local memory per SPE and the new communication mechanism, make it very challenging to port an application. We selected the solar radiation component of the NASA GEOS-5 climate model, which: (1) is representative of column physics (approximately 50% computational time), (2) has a high computational load relative to transferring data from and to main memory, (3) performs independent calculations across multiple columns. We converted the baseline code (single-precision, Fortran) to C and ported it with manually SIMDizing 4 independent columns and found that a Cell with 8 SPEs can process 2274 columns per second. Compared with the baseline results, the Cell is approximately 5.2X, approximately 8.2X, approximately 15.1X faster than a core on Intel Woodcrest, Dempsey, and Itanium2, respectively. We believe this dramatic performance improvement makes a hybrid cluster with Cell and traditional nodes competitive.

97 MATHEMATICS AND COMPUTING↗

Cartesian equivariant representations for learning and understanding molecular orbitals

Qualitative and quantitative orbital properties such as bonding/antibonding character, localization, and orbital energies are critical to how chemists understand reactivity, catalysis, and excited-state behavior. Despite this, representations of orbitals in deep learning models have been very underdeveloped relative to representations of molecular geometries and Hamiltonians. Here, we apply state-of-the-art equivariant deep learning architectures to the task of assigning global labels to orbitals, namely energies characterizations, given the molecular coefficients from Hartree–Fock or density functional theory. The architecture we have developed, the Cartesian Equivariant Orbital Network (CEONET), shows how molecular orbital coefficients are readily featurized as equivariant node features common to all graph-based machine-learned potentials. We find that CEONET performs well at predicting difficult quantitative labels such as the orbital energy and orbital entropy. Furthermore, we find that the CEONET representation provides an intuitive latent space for differentiating orbital character for the qualitative assignment of e.g. bonding or antibonding character. In addition to providing a useful representation for further integrating deep learning with electronic structure theory, we expect CEONET to be useful for automatizing and interpreting the results of advanced electronic structure methods such as complete active space self-consistent field theory. In particular, the ability of CEONET to infer multireference character via the orbital entropy paves the way toward the machine-learned selection of active spaces.

chemical reactions↗

Sinter‐Resistant Platinum Catalyst Supported by Metal–Organic Framework

Abstract Single atoms and few‐atom clusters of platinum are uniformly installed on the zirconia nodes of a metal‐organic framework (MOF) NU‐1000 via targeted vapor‐phase synthesis. The catalytic Pt clusters, site‐isolated by organic linkers, are shown to exhibit high catalytic activity for ethylene hydrogenation while exhibiting resistance to sintering up to 200 °C. In situ IR spectroscopy reveals the presence of both single atoms and few‐atom clusters that depend upon synthesis conditions. Operando X‐ray absorption spectroscopy and X‐ray pair distribution analyses reveal unique changes in chemical bonding environment and cluster size stability while on stream. Density functional theory calculations elucidate a favorable reaction pathway for ethylene hydrogenation with the novel catalyst. These results provide evidence that atomic layer deposition (ALD) in MOFs is a versatile approach to the rational synthesis of size‐selected clusters, including noble metals, on a high surface area support.

Kim, In Soo↗

RECQ1 A159C Polymorphism Is Associated With Overall Survival of Patients With Resected Pancreatic Cancer: A Replication Study in NRG Oncology Radiation Therapy Oncology Group 9704

Purpose: To confirm whether a previously observed association between RECQ1 A159C variant and clinical outcome of resectable pancreatic cancer patients treated with preoperative chemoradiation is reproducible in another patient population prospectively treated with postoperative chemoradiation. Methods and Materials: Patients were selected, according to tissue availability, from eligible patients with resected pancreatic cancer who were enrolled on the NRG Oncology Radiation Therapy Oncology Group 9704 trial of 5-fluorouacil (5-FU)-based chemoradiation preceded and followed by 5-FU or gemcitabine. Deoxyribonucleic acid was extracted from paraffin-embedded tissue sections, and genotype was determined using the Taqman method. The correlation between genotype and overall survival was analyzed using a Kaplan-Meier plot, log-rank test, and multivariate Cox proportional hazards models. Results: In the 154 of the study's 451 eligible patients with evaluable tissue, genotype distribution followed Hardy-Weinberg equilibrium (ie, 37% had genotype AA, 43% AC, and 20% CC). The RECQ1 variant AC/CC genotype carriers were associated with being node positive compared with the AA carrier (P=.03). The median survival times (95% confidence interval [CI]) for AA, AC, and CC carriers were 20.6 (16.3-26.1), 18.8 (14.2-21.6), and 14.2 (10.3-21.0) months, respectively. On multivariate analysis, patients with the AC/CC genotypes were associated with worse survival than patients with the AA genotype (hazard ratio [HR] 1.54, 95% CI 1.07-2.23, P=.022). This result seemed slightly stronger for patients on the 5-FU arm (n=82) (HR 1.64, 95% CI 0.99-2.70, P=.055) than for patients on the gemcitabine arm (n=72, HR 1.46, 95% CI 0.81-2.63, P=.21). Conclusions: Results of this study suggest that the RECQ1 A159C genotype may be a prognostic or predictive factor for resectable pancreatic cancer patients who are treated with adjuvant 5-FU before and after 5-FU-based chemoradiation. Further study is needed in patients treated with gemcitabine to determine whether an association exists.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Krylov subspace recycling for evolving structures

Krylov subspace recycling is a powerful tool when solving a long series of large, sparse linear systems that change only slowly over time. In PDE constrained shape optimization, these series appear naturally, as typically hundreds or thousands of optimization steps are needed with only small changes in the geometry. In this setting, however, applying Krylov subspace recycling can be a difficult task. As the geometry evolves, in general, so does the finite element mesh defined on or representing this geometry, including the numbers of nodes and elements and element connectivity. This is especially the case if re-meshing techniques are used. As a result, the number of algebraic degrees of freedom in the system changes, and in general the linear system matrices resulting from the finite element discretization change size from one optimization step to the next. Changes in the mesh connectivity also lead to structural changes in the matrices. In the case of re-meshing, even if the geometry changes only a little, the corresponding mesh might differ substantially from the previous one. Obviously, this prevents any straightforward mapping of the approximate invariant subspace of the linear system matrix (the focus of recycling in this work) from one optimization step to the next; similar problems arise for other selected subspaces. In this paper, we present an algorithm to map an approximate invariant subspace of the linear system matrix for the previous optimization step to an approximate invariant subspace of the linear system matrix for the current optimization step, for general meshes. This is achieved by exploiting the map from coefficient vectors to finite element functions on the mesh, combined with interpolation or approximation of functions on the finite element mesh. We demonstrate the effectiveness of our approach numerically with several proof of concept studies for a specific meshing technique.

42 ENGINEERING↗

Kinetic energy classification and smoothing for compact B-spline basis sets in quantum Monte Carlo

Quantum Monte Carlo calculations of defect properties of transition metal oxides have become feasible in recent years due to increases in computing power. As the system size has grown, availability of on-node memory has become a limiting factor. Saving memory while minimizing computational cost is now a priority. The main growth in memory demand stems from the B-spline representation of the single particle orbitals, especially for heavier elements such as transition metals where semi-core states are present. Despite the associated memory costs, splines are computationally efficient. In this paper, we explore alternatives to reduce the memory usage of splined orbitals without significantly affecting numerical fidelity or computational efficiency. We make use of the kinetic energy operator to both classify and smooth the occupied set of orbitals prior to splining. By using a partitioning scheme based on the per-orbital kinetic energy distributions, we show that memory savings of about 50% is possible for select transition metal oxide systems. Finally, for production supercells of practical interest, our scheme incurs a performance penalty of less than 5%.

97 MATHEMATICS AND COMPUTING↗

Chemical and structural characterization of EUV photoresists as a function of depth by standing-wave x-ray photoelectron spectroscopy

The success in the miniaturization of the electronic device constituents depends mostly on the photolithographic techniques. Recently, to achieve patterning at the sub-10-nm node, extreme ultraviolet (EUV) lithography has been introduced into high volume production. Continued scaling of EUV via increased numerical aperture to achieve nodes at 3-nm and below requires the development of fundamentally new patterning materials and new characterization methods. Current EUV-resist film thicknesses are in the 20- to 40-nm range, and further thickness reduction is required for the next generation. Therefore, interfaces become exceedingly important, and the properties of the resist film would be dominated by top and bottom interfacial effects. X-ray photoelectron spectroscopy (XPS) combined with standing-wave excitation (SW-XPS), a fairly new method in the EUV lithography field, previously had been largely applied in multilayers and superlattices for characterizing the composition and electronic structure of buried layers and interfaces as a function of depth. We applied the SW-XPS method to organic/inorganic photoresists to provide depth-selective information on their structural and chemical conditions of as a function of temperature, EUV exposure, different underlayers, and other fundamental parameters. As a first attempt, we perform an SW-XPS feasibility study on self-assembled monolayer (SAM) films after exposure to an electron beam. By SW-XPS, we determined that the interface between the Al 2 O 3 underlayer and the SAMs is smooth, with a mean roughness of about 0.2 nm. Moreover, we determined that the SAM chains are, on average, tilted by 1/430 deg off the sample normal. The SW-XPS results also suggest that the SAM is not a perfectly aligned and uniform monolayer, with some areas having thickness higher than a single monolayer. We demonstrated that SW-XPS can provide useful information on ultrathin materials with high potential for being used as a characterization method of organic/inorganic photoresists.

36 MATERIALS SCIENCE↗

Metal–Organic Frameworks as a Tunable Platform to Deconvolute Stereoelectronic Effects on the Catalytic Activity of Thioanisole Oxidation

The local environment of a metal active site plays an important role in affecting catalytic activity and selectivity. In re-cent studies, tailoring the behavior of a molybdenum-based active site via modulation of the first coordination sphere has led to improved thioanisole oxidation performance, but disentangling electronic effects from steric influences that arise from these modifications is nontrivial, especially in heterogeneous systems. To this end, the tunability of metal–organic frameworks (MOFs) makes them promising scaffolds for controlling the coordination sphere of a heterogene-ous, catalytically-active metal site while offering additional, attractive features such as crystallinity and high porosity. Herein, we report a variety of MOF-supported Mo species, which were investigated for catalytic thioanisole oxidation to methyl phenyl sulfoxide and/or methyl phenyl sulfone using tert-butyl hydroperoxide (tBHP) as the oxidant. In particular, MOFs of contrasting node architectures were targeted, presenting a unique opportunity to investigate ste-reoelectronic control of Mo active sites in a systematic manner. A Zr 6 -based MOF, NU-1000, was employed along with its sulfated analog Zr 6 -based NU-1000-SO 4 to anchor a dioxymolybdenum species, which enabled examination of sup-port-mediated active site polarizability on catalytic performance. In addition, a MOF containing a mixed metal node, Mo-MFU-4l, was used to probe the stereoelectronic impact of an N-donor ligand environment on the catalytic activity of the transmetalated Mo center. Furthermore, characterization techniques including single crystal X-ray diffraction, were concomi-tantly used with reaction kinetic profiles to better comprehend the dynamics of different Mo active sites, thus correlat-ing structural change with activity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Sinter-Resistant Platinum Catalyst Supported by Metal-Organic Framework

Installed on the zirconia nodes of a metal-organic framework (MOF) NU-1000 via targeted vapor-phase synthesis. The catalytic Pt clusters, site-isolated by organic linkers, are shown to exhibit high catalytic activity for ethylene hydrogenation while exhibiting resistance to sintering up to 200 degrees C. In situ IR spectroscopy reveals the presence of both single atoms and few-atom clusters that depend upon synthesis conditions. Operando X-ray absorption spectroscopy and Xray pair distribution analyses reveal unique changes in chemical bonding environment and cluster size stability while on stream. Density functional theory calculations elucidate a favorable reaction pathway for ethylene hydrogenation with the novel catalyst. Lastly, these results provide evidence that atomic layer deposition (ALD) in MOFs is a versatile approach to the rational synthesis of size-selected clusters, including noble metals, on a high surface area support.

36 MATERIALS SCIENCE↗

Insights into regulatory T-cell and type-I interferon roles in determining abacavir-induced hypersensitivity or immune tolerance

Introduction Clinical use of several small molecule drugs may lead to severe T-cell-mediated idiosyncratic drug hypersensitivity reactions (iDHR) linked to HLA alleles, including abacavir (ABC) with HLA-B*57:01. Due to study limitations in humans, pathogenic networks in iDHR remain elusive. HLA transgenic murine models have been proposed to bridge knowledge gaps in tolerance and susceptibility to drugs. Methods Mice expressing HLA-B*57:01 and Foxp3-DTR/EGFP were generated to selectively deplete regulatory T-cells (Treg) with diphtheria toxin. ABC was administered for 8 days alone or together with cell- and cytokine-depleting antibodies. Cellular and transcriptomic responses were analyzed by RNA, flow cytometry and fluorescence methods. Results While CD8 + T-cell responses to ABC require HLA presentation, ABC also triggered mitochondrial stress in macrophagesin vitro, independently of HLA.In vivo, Treg were the primary mechanism of drug tolerance controlling HLA presentation and costimulation by antigen presenting cells. Treg ablation uncovered immune adverse events linked to activation and proliferation of both drug-specific and bystander CD8 + T-cells through CD28-mediated pathways with support from CD4 + non-Treg. Type-I interferon (IFN-I) and cellular-stress pathways influenced the fate of lymph node cells responding to ABC, implicating innate immune cells such as macrophages and plasmacytoid dendritic cells in the development of T-cell responses against the drug. IFN-I and IL-2 were necessary for CD8 + T-cell differentiation and ABC-induced adverse reactions. Conclusions This study unveils novel immune mechanisms driven by drug and host-related factors required forin vivoreactions and sheds light on potential biomarker and therapeutic targets for managing and preventing severe and life-threatening iDHR.

Immunology↗

Unraveling Network-induced Memory Contention: Deeper Insights with Machine Learning

Remote Direct Memory Access (RDMA) is expected to be an integral communication mechanism for future exascale systems enabling asynchronous data transfers, so that applications may fully utilize CPU resources while simultaneously sharing data amongst remote nodes. We examine Network-induced Memory Contention (NiMC) on Infiniband networks. We expose the interactions between RDMA, main-memory and cache, when applications and out-of-band services compete for memory resources. We then explore NiMCs resulting impact on application-level performance. For a range of hardware technologies and HPC workloads, we quantify NiMC and show that NiMCs impact grows with scale resulting in up to 3X performance degradation at scales as small as 8K processes even in applications that previously have been shown to be performance resilient in the presence of noise. In addition, this work examines the problem of predicting NiMC's impact on applications by leveraging machine learning and easily accessible performance counters. This approach provides additional insights about the root cause of NiMC and facilitates dynamic selection of potential solutions. Finally, we evaluated three potential techniques to reduce NiMCs impact, namely hardware offloading, core reservation and network throttling.

97 MATHEMATICS AND COMPUTING↗