Search NASA⌕ Search

Engineering topics

Tang, Li

Publications and source records attributed to Tang, Li.

The ECP SICM project: Managing complex memory hierarchies for exascale applications

The Exascale Computing Project (ECP)’s Simplified Interface to Complex Memories (SICM) effort focuses on developing universal interfaces for discovering, managing, and sharing data across complex memory hierarchies. These facilitate the exploitation of emerging memory technologies and support precise control over their various trade-offs such as high-bandwidth versus low-latency, persistent versus ephemeral, high-capacity versus low-capacity, and near-CPU versus near-GPU. SICM comprises three interrelated components: a low-level interface, a high-level interface, and a persistent-heap interface. The low-level SICM interface is intended for system and run-time developers as well as expert application developers who prefer full control of the memory objects used within their application. The high-level SICM interface builds upon the low-level interface, employing application-level profiling and analysis to optimize data management for complex memory hierarchies. The persistent-heap interface provides applications with a persistent memory allocator that can allocate custom C++ data structures in both block-storage and byte-addressable persistent memories.

97 MATHEMATICS AND COMPUTING↗

Concurrent Inter-Model Spread of Boreal Winter Westerly Jet Meridional Positions Between the Northern and Southern Hemispheres in CMIP6 Models

Here, this study investigates the inter-model spread of climatological extratropical westerly jets in boreal winter, using the historical simulation of 52 Coupled Model Intercomparison Project phase 6 (CMIP6) models from 1851 to 2014. The results show that there is a substantial spread in the latitude of the upper-tropospheric westerly jet across models, characterised by large inter-model standard deviations to both the poleward and equatorward sides of the jet axis, although the multi-model ensemble mean (MME) performs well in simulating meridional position of westerly jets. Furthermore, we detect the consistency of inter-model jet position spread between the Northern and Southern Hemispheres, based on the inter-model empirical orthogonal function (EOF) decomposition and correlation of regional-averaged zonal winds. Specifically, the models that simulate the westerly jets poleward/equatorward relative to the MME position in one hemisphere also tend to simulate the jets poleward/equatorward in the other hemisphere. Accordingly, we define a global jet spread index to depict the concurrence of jet shift in the two hemispheres. The results of inter-model regression analyses based on this index indicate that the models positioning the jets poleward than the MME tend to simulate a wider Hadley Cell, a poleward-shifted Ferrel Cell in the Southern Hemisphere, enhanced precipitation in the subtropics and suppressed precipitation in the tropics, and warmer sea surface temperatures in the subtropics and mid-latitudes. The present results suggest that improving the simulation of jet positions in climate models requires a comprehensive consideration of thermal states in the tropics and subtropics/mid latitudes.

54 ENVIRONMENTAL SCIENCES↗

CLC: A cross-level program characterization method

Characterization of program execution plays a key role in performance improvement. There are numerous transformations applied to each step that a program takes on its lowering from source code to a compiler intermediate representation to machine language to microarchitecture-specific execution. The unpredictable benefit of each transformation step could lead a notionally superior algorithm to exhibit inferior performance once actually run, and it can be hard to discern which step in the transformation path contradicted the code developer’s assumptions. Conventional approaches to program-execution characterization consider the behavior after only a single one of those steps, which limits the information that can be provided to the user. To help address the issue of myopic views of program execution, this paper presents a novel cross-level characterization approach for understanding the behavior of program execution at different levels in the process of writing, compiling, and running a program. We show that this approach provides a richer view of the sources of performance gains and losses and helps identify program execution in a more accurate manner.

97 MATHEMATICS AND COMPUTING↗

System and method for torque split arbitration

A method for torque split arbitration in a vehicle includes identifying at least one route characteristic of a portion of a route being traversed by the vehicle. The method further includes determining a target torque split based on the at least one route characteristics. The method further includes generating a first output torque demand that corresponds to a product of a first portion of a target torque demand to be provided by a first propulsion unit and a ratio of a total propulsion system torque demand and the target torque demand. The method further includes generating a second output torque demand based on the first output torque demand.

Aggoune, Karim↗

Lithium metal recovery and synthesis

A process and system for creating a lithium ion anolyte from lithium alloys. Metal and lithium alloys are processed to remove the metal with lithium from the alloy remaining. A lithium ion anolyte formed may be used in a process to form lithium metal. Alternatively, a process and system for recovering lithium from sources such as lithium alloys and lithium metal oxides and other feedstock such as recycled batteries into a thin lithium metal film via electrodeposition in an organic electrolyte contacting both anode (holder for lithium source) and cathode (substrate for lithium deposition) in a single-compartment electrolysis cell.

Ignacio de Leon, Patricia Anne↗

Pre-existing humoral immunity to human common cold coronaviruses negatively impacts the protective SARS-CoV-2 antibody response

SARS-CoV-2 infection causes diverse outcomes ranging from asymptomatic infection to respiratory distress and death. A major unresolved question is whether prior immunity to endemic, human common cold coronaviruses (hCCCoVs) impacts susceptibility to SARS-CoV-2 infection or immunity following infection and vaccination. Therefore, we analyzed samples from the same individuals before and after SARS-CoV-2 infection or vaccination. We found hCCCoV antibody levels increase after SARS-CoV-2 exposure, demonstrating cross-reactivity. However, a case-control study indicates that baseline hCCCoV antibody levels are not associated with protection against SARS-CoV-2 infection. Rather, higher magnitudes of pre-existing betacoronavirus antibodies correlate with more SARS-CoV-2 antibodies following infection, an indicator of greater disease severity. Additionally, immunization with hCCCoV spike proteins before SARS-CoV-2 immunization impedes the generation of SARS-CoV-2-neutralizing antibodies in mice. Together, these data suggest that pre-existing hCCCoV antibodies hinder SARS-CoV-2 antibody-based immunity following infection and provide insight on how pre-existing coronavirus immunity impacts SARS-CoV-2 infection, which is critical considering emerging variants.

60 APPLIED LIFE SCIENCES↗

Hardware Evaluation Analytical Modeling and Node Simulation: Benefits of Tighter GPU Integration

In this report, we examine several emerging technologies of interest to the Department of Energy and its computational centers. These include: 1) quantifying the benefit of tighter CPU-GPU integration, 2) quantifying the appropriate CPU core:GPU ratio, 3) quantifying the penalty for CPU-GPU disaggregation, 4) quantifying the benefits of tighter GPU-GPU integration, 5) quantifying the benefits of unified memory, and 6) quantifying the benefits of tighter FPGA-GPU integration.

97 MATHEMATICS AND COMPUTING↗

Chimbuko: A Workflow-Level Scalable Performance Trace Analysis Tool

Due to the sheer volume of data it is typically impractical to analyze the detailed performance of an HPC application running at-scale. While conventional small-scale benchmarking and scaling studies are often sufficient for simple applications, many modern workflow-based applications couple multiple elements with competing resource demands and complex inter-communication patterns for which performance cannot easily be studied in isolation and at small scale. This work discusses Chimbuko, a performance analysis framework that provides real-time, in situ anomaly detection. By focusing specifically on performance anomalies and their origin (aka provenance), data volumes are dramatically reduced without losing necessary details. To the best of our knowledge, Chimbuko is the first online, distributed, and scalable workflow-level performance trace analysis framework. We demonstrate the tool's usefulness on Oak Ridge National Laboratory's Summit system.

97 MATHEMATICS AND COMPUTING↗

Chimbuko: A Workflow-Level Scalable Performance Trace Analysis Tool

ABSTRACT Due to the sheer volume of data it is typically impractical to analyze the detailed performance of an HPC application running at-scale. While conventional small-scale benchmarking and scaling studies are often sufficient for simple applications, many modern workflow-based applications couple multiple elements with competing resource demands and complex inter-communication patterns for which performance cannot easily be studied in isolation and at small scale. This work discusses Chimbuko, a performance analysis framework that provides real-time, in situ anomaly detection. By focusing specifically on performance anomalies and their origin (aka provenance), data volumes are dramatically reduced without losing necessary details. To the best of our knowledge, Chimbuko is the first online, distributed, and scalable workflow-level performance trace analysis framework. We demonstrate the tool's usefulness on Oak Ridge National Laboratory's Summit system.

97 MATHEMATICS AND COMPUTING↗

A data mining approach to investigate food groups related to incidence of bladder cancer in the BLadder cancer Epidemiology and Nutritional Determinants International Study

Abstract At present, analysis of diet and bladder cancer (BC) is mostly based on the intake of individual foods. The examination of food combinations provides a scope to deal with the complexity and unpredictability of the diet and aims to overcome the limitations of the study of nutrients and foods in isolation. This article aims to demonstrate the usability of supervised data mining methods to extract the food groups related to BC. In order to derive key food groups associated with BC risk, we applied the data mining technique C5.0 with 10-fold cross-validation in the BLadder cancer Epidemiology and Nutritional Determinants study, including data from eighteen case–control and one nested case–cohort study, compromising 8320 BC cases out of 31 551 participants. Dietary data, on the eleven main food groups of the Eurocode 2 Core classification codebook, and relevant non-diet data (i.e. sex, age and smoking status) were available. Primarily, five key food groups were extracted; in order of importance, beverages (non-milk); grains and grain products; vegetables and vegetable products; fats, oils and their products; meats and meat products were associated with BC risk. Since these food groups are corresponded with previously proposed BC-related dietary factors, data mining seems to be a promising technique in the field of nutritional epidemiology and deserves further examination.

Nutrition & Dietetics↗

Computational Reproducibility of Scientific Workflows at Extreme Scales

We propose an approach for improved reproducibility that includes capturing and relating provenance characteristics and performance metrics, in a hybrid queriable system, the ProvEn server. The system capabilities are illustrated on two use cases: scientific reproducibility of results in the ACME climate simulations and performance reproducibility in molecular dynamics workflows on HPC computing platforms.

provenance, Reproducibility, Climate & Earth Syste↗

MPI jobs within MPI jobs: A practical way of enabling task-level fault-tolerance in HPC workflows

While the use of workflows for HPC is growing, MPI interoperability remains a challenge for workflow management systems. The MPI standard and/or its implementations provide a number of ways to build multiple-programs-multiple-data (MPMD) applications. These methods present limitations related to fault tolerance, and are not easy to use. In this paper, we advocate for a novel MPI_Comm_launch function acting as the parallel counterpart of a system(3) call. MPI_Comm_launch allows a child MPI application to be launched inside the resources originally held by processes of a parent MPI application. Two important aspects of MPI_Comm_launch is that it pauses the calling process, and runs the child processes on the parent’s CPU cores, but in an isolated manner with respect to memory. This function makes it easier to build MPMD applications with well-decoupled subtasks. We show how this feature can provide better flexibility and better fault tolerance in ensemble simulations and HPC workflows. Here, we report results showing 2x throughput improvement for application workflows with faults, and scaling results for challenging workloads up to 256 nodes.

97 MATHEMATICS AND COMPUTING↗

Enhanced Flux and Electrochemical Cleaning of Silicate Scaling on Carbon Nanotube-Coated Membrane Distillation Membranes Treating Geothermal Brines

The desalination of inland brackish groundwater offers the opportunity to provide potable drinking water to residents and industrial cooling water to industries located in arid regions. Geothermal brines are used to generate electricity, but often contain high concentrations of dissolved salt. Here in this paper, we demonstrate how the residual heat left in spent geothermal brines can be used to drive a membrane distillation (MD) process and recover desalinated water. Porous polypropylene membranes were coated with a carbon nanotube (CNT)/poly(vinyl alcohol) layer, resulting in composite membranes having a binary structure that combines the hydrophobic properties critical for MD with the hydrophilic and conductive properties of the CNTs. We demonstrate that the addition of the CNT layer increases membrane flux due to enhanced heat transport from the bulk feed to the membrane surface, a result of CNT's high thermal transport properties. Furthermore, we show how hydroxide ion generation, driven by water electrolysis on the electrically conducting membrane surface, can be used to efficiently dissolve silicate scaling that developed during the process of desalinating the geothermal brine, negating the need for chemical cleaning.

15 GEOTHERMAL ENERGY↗

International pooled study on diet and bladder cancer: the bladder cancer, epidemiology and nutritional determinants (BLEND) study: design and baseline characteristics

Background: In 2012, more than 400,000 urinary bladder cancer cases occurred worldwide, making it the 7th most common type of cancer. Although many previous studies focused on the relationship between diet and bladder cancer, the evidence related to specific food items or nutrients that could be involved in the development of bladder cancer remains inconclusive. Dietary components can either be, or be activated into, potential carcinogens through metabolism, or act to prevent carcinogen damage. Methods/design: The BLadder cancer, Epidemiology and Nutritional Determinants (BLEND) study was set up with the purpose of collecting individual patient data from observational studies on diet and bladder cancer. In total, data from 11,261 bladder cancer cases and 675,532 non-cases from 18 case–control and 6 cohort studies from all over the world were included with the aim to investigate the association between individual food items, nutrients and dietary patterns and risk of developing bladder cancer. Discussion: The substantial number of cases included in this study will enable us to provide evidence with large statistical power, for dietary recommendations on the prevention of bladder cancer.

59 BASIC BIOLOGICAL SCIENCES↗

Monodisperse In{sub 2}O{sub 3} nanoparticles synthesized by a novel solvothermal method with In(OH){sub 3} as precursors

Highlights: • Monodisperse In{sub 2}O{sub 3} nanoparticles were synthesized by a novel solvothermal method. • The particle size of In{sub 2}O{sub 3} nanoparticles is ultrafine, ∼5 nm. • The precursor is readily available. • It is free of any surfactant and template. • The possible growth mechanism, delayed burst nucleation, are elucidated. - Abstract: A novel solvothermal method has been developed for monodisperse In{sub 2}O{sub 3} nanoparticles (NPs) with ∼5 nm particle size, In(OH){sub 3} as precursors and free of any surfactant and template. The NPs were characterized by X-ray diffraction (XRD), transmission electron microscopy (TEM), high-resolution TEM (HRTEM), energy-dispersive X-ray spectrum (EDS) and Fourier transform infrared spectrum (FT-IR). The temperature, the concentration of precursors and washing conditions dramatically affected the structure, morphology and size of NPs. The possible growth mechanism was elucidated as well, which was delayed burst nucleation. A weak quantum confinement effect of In{sub 2}O{sub 3} NPs resulting from the small particle size was observed in UV spectrum and one photoluminescence emission peak occurring in the visible region was detected as well.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Performance and Energy Implications for Heterogeneous Computing Systems: A MiniFE Case Study

Heterogeneous computing systems, which employ a mix of general-purpose (GP) processors and accelerators such as graphics processing units (GPUs) or Field Programmable Gate Arrays (FPGAs), have the potential to offer much higher performance and lower energy usage than homogeneous systems. However, designing heterogeneous computing systems to achieve high performance and low energy usage is a challenging task. Designs that offer higher performance do not necessarily lead to lower energy consumption. Furthermore, mapping of applications to different computing devices can play a key role in performance and energy tradeoff. In this report, we present a detailed performance and energy study of executing a specific mini-application on different heterogeneous systems. The results show that hardware choices, application implementations, and mapping of applications to hardware can all significantly impact system performance and energy consumption and that the impact on performance and energy can be quite different. This study forms a basis for modeling the interdependencies of program structures and hardware execution units, which could be used to guide design space exploration.

97 MATHEMATICS AND COMPUTING↗