Engineering Papers⌕ Search

Engineering topics

Wang, Teng

Publications and source records attributed to Wang, Teng.

At least 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Direct-FUSE

The Direct-FUSE framework supports multiple FUSE file systems as well as other, custom user-level file systems in user space without the need to cross the user/kernel boundary into the FUSE kernel module. All layers of Direct-FUSE are in user space, and applications can directly use pre-defined unified file system calls to interact with different user-defined file systems. Our performance results show that Direct- FUSE can outperform some native FUSE file systems by 11.9% on average and does not add significant overhead over backend file systems.

SATO,, KENTO↗
DOE OSTI2019

Reconfigurable Terahertz Metasurface Pure Phase Holograms

Terahertz (THz) radiation has many potential applications. However, comparing with the rapid development of THz sources and detectors, functional devices for THz modulation, especially the spatial modulation devices, are still insufficient. Here, we present a novel approach for generating arbitrary wavefronts of a THz beam is presented. By dynamically creating metasurface structures through illuminating a thin silicon wafer with femtosecond laser, which is spatially modulated, an array of reconfigurable subwavelength resonators is generated. The wavefront of the THz beam is then determined by forming spatial profiles of the Pancharatnam–Berry scattering phase by dynamically controlling the resonator orientation. Proof-of-concept experiments demonstrate that streaming holographic images and lenses of variable focal length can be realized in real time. The reconfigurable scheme demonstrated here is convenient and fast, and may lead to advances in a host of THz applications.

36 MATERIALS SCIENCE↗
DOE OSTI2019

High-Performance Hydroxide Exchange Membrane Fuel Cells through Optimization of Relative Humidity, Backpressure and Catalyst Selection

Hydroxide exchange membrane fuel cells (HEMFC) are an enticing power source for automobiles due to their low cost. Here we focus on improving the beginning-of-life performance of HEMFCs to a higher level with poly(aryl piperidinium) (PAP) membranes and ionomers. We reveal that lower RH and backpressure in anode than cathode can eliminate anode flooding and cathode dryout so that a balanced water management can be achieved. We also find that PtRu/C is a better anode catalyst than Pt/Ketjen Black due to the presence of Ru and Pt/Vulcan XC-72 is a better cathode catalyst than Pt/Ketjen Black due to its better mass transport properties. Once the preferred operating conditions and materials incorporated into the same cell, our HEMFCs achieved a peak power density of 1.89 W cm –2 in H 2 /O 2 and 1.31 W cm –2 in H 2 /air.

25 ENERGY STORAGE↗
DOE OSTI2019

A Zoom-in Analysis of I/O Logs to Detect Root Causes of I/O Performance Bottlenecks

Scientific applications frequently spend a large fraction of their execution time in reading and writing data on parallel file systems. Identifying these I/O performance bottlenecks and attributing root causes are critical steps toward devising optimization strategies. Several existing studies analyze I/O logs of a set of benchmarks or applications that were run with controlled behaviors. However, there is still a lack of general approach that systematically identifies I/O performance bottlenecks for applications running "in the wild" on production systems. In this study, we have developed an analysis approach of "zooming in" from platform-wide to application-wide to job-level I/O logs for identifying I/O bottlenecks in arbitrary scientific applications. We analyze the logs collected on a Cray XC40 system in production over a two-month period. This study results in several insights for application developers to use in optimizing I/O behavior.

Wang, Teng↗
DOE OSTI2018

ARCHIE: Data Analysis Acceleration with Array Caching in Hierarchical Storage

© 2018 IEEE. Scientific data analysis typically involves reading massive amounts of data that was generated by simulations, experiments, and observations. Performance of reading such large volumes of data from disk-based file systems is often poor because of the slow and mechanical components in the disks. Recent supercomputing systems are adding non-volatile storage layers in a hierarchy to handle the performance gap between fast main memory and slow disk-based storage. Software libraries for managing this hierarchy not only need efficient reading of data but also reduce user-involvement for cross-layer data movement. Furthermore, these libraries need to support array data access patterns into hierarchical storage management as scientific data is often organized in array-based data structures. Existing software typically manage individual storage layers requiring significant manual process in moving data among them. In this paper, we introduce a new array caching in hierarchical storage (ARCHIE) to accelerate array data analysis in a seamless fashion. ARCHIE evaluates array access patterns and prefetches data with array semantics between storage layers. Our evaluation shows that ARCHIE outperforms state-of-the-art file systems, i.e., Lustre and DataWarp, on a production supercomputing system by up to 5.8× in accessing data by scientific analysis applications.

Dong, Bin↗
DOE OSTI2018

The rise, collapse, and compaction of Mt. Mantap from the 3 September 2017 North Korean nuclear test

Surveillance of clandestine nuclear tests relies on a global seismic network, but the potential of spaceborne monitoring has been underexploited. Here we used satellite radar imagery to determine the complete surface displacement field of up to 3.5 meters of divergent horizontal motion with 0.5 meters of subsidence associated with North Korea’s largest underground nuclear test. Combining insight from geodetic and seismological remote sensing, we found that the aftermath of the initial explosive deformation involved subsidence associated with subsurface collapse and aseismic compaction of the damaged rocks of the test site. The explosive yield from the nuclear detonation with best-fitting source parameters for 450-meter depth was 191 kilotonnes of TNT equivalent. Finally, our results demonstrate the capability of spaceborne remote sensing to help characterize large underground nuclear tests.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2017

UnifyFS: A Distributed Burst Buffer File System - 0.1.0

UnifyFS is a user-level burst buffer file system under active development. UnifyFS supports scalable and efficient aggregation of I/O bandwidth from burst buffers while having the same life cycle as a batch-submitted job. While UnifyFS is designed for N-N write/read, UnifyFS compliments its functionality with the support for N-1 write/read. It efficiently accelerates scientific I/O based on scalable metadata indexing, co-located I/O delegation, and server-side read clustering and pipelining.

ECP↗
DOE OSTI2017

An Ephemeral Burst-Buffer File System for Scientific Applications

BurstFS is a distributed file system for node-local burst buffers on high performance computing systems. BurstFS presents a shared file system space across the burst buffers so that applications that use shared files can access the highly-scalable burst buffers without changing their applications.

Wang, Teng↗
DOE OSTI2017

Toward full exploitation of coherent and incoherent information in Sentinel-1 TOPS data for retrieving surface displacement: Application to the 2016 Kumamoto (Japan) earthquake

Sentinel-1's continuous observation program over all major plate boundary regions makes it well suited for earthquake studies. However, decorrelation due to large displacement gradients and limited azimuth resolution of the Terrain Observation by Progressive Scan (TOPS) data challenge acquiring measurements in the near field of many earthquake ruptures and prevent measurements of displacements in the along-track direction. Here we propose to fully exploit the coherent and incoherent information of TOPS data by using standard interferometric synthetic aperture radar (InSAR), split-bandwidth interferometry in range and azimuth, swath/burst-overlap interferometry, and amplitude cross correlation to map displacements in both the line-of-sight and the along-track directions. Application to the 2016 Kumamoto earthquake sequence reveals the coseismic displacements from the far field to the near field. By adding near-field constraints, the derived slip model reveals more shallow slip than obtained when only using far-field data from InSAR, highlighting the importance of exploiting all coherent and incoherent information in TOPS data.

58 GEOSCIENCES↗
DOE OSTI2016

Silencing Drp1 inhibits glioma cells proliferation and invasion by RHOA/ ROCK1 pathway

Backgrounds: Dynamin-related protein 1 (Drp1) is a newly discovered therapeutic target for tumor initiation, migration, proliferation, and chemosensitivity. In the present study, we aimed to examine the level of expression and distribution of DRP1 in glioma tissues and explore the concrete mechanism of DRP1 played in glioma. Methods: Expression of DRP1 in glioma tissues was determined by immunohistochemistry staining. The DRP1 gene was knocked down using small interfering RNA, and was overexpressed using plasmids in glioma cells. To assess changes in cell function, in vitro assays for invasion and growth were applied. Protein expression was tested by using Western-blot method. Variation of F-actin in cells was analyzed using immunofluorescence staining. Interactions between proteins were determined by co-immunoprecipitation. Results: The protein expression levels of DRP1 were significantly increased in glioma tissues compared to the normal brain tissues. Down-regulation of DRP1 decreased cell proliferation and invasion, and inhibited the formation of pseudopodias and microvillis. Moreover, a possible link between DRP1 and RHOA was confirmed when interactions between these two proteins were observed in the cells. Conclusions: Our results demonstrated that silencing DRP1 regulated the cytoskeleton remodeling through inhibiting RHOA/ROCK1 pathway, and thus decreased the proliferation and invasion of glioma cells. - Highlights: • DPR1 is significantly increased in glioma tissues. • Down-regulation of DRP1 in glioma cells inhibits cell proliferation. • Down-regulation of DRP1 in glioma cells inhibits cell invasion and induces F-actin remodeling. • Down-regulation of DRP1 inhibits RHOA/ROCK1 pathway in glioma cells.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

TRIO: Burst Buffer Based I/O Orchestration, In: 2015 IEEE International Conference on Cluster Computing

The growing computing power on leadership HPC systems is often accompanied by ever-escalating failure rates. Checkpointing is a common defensive mechanism used by scientific applications for failure recovery. However, directly writing the large and bursty checkpointing dataset to parallel file systems can incur significant I/O contention on storage servers. Such contention in turn degrades bandwidth utilization of storage servers and prolongs the average job I/O time of concurrent applications. Recently burst buffers have been proposed as an intermediate layer to absorb the bursty I/O traffic from compute nodes to storage backend. But an I/O orchestration mechanism is still desirable to efficiently move checkpointing data from burst buffers to storage backend. In this paper, we propose a burst buffer based I/O orchestration framework, named TRIO, to intercept and reshape the bursty writes for better sequential write traffic to storage servers. Meanwhile, TRIO coordinates the flushing orders among concurrent burst buffers to alleviate the contention on storage server. Our experimental results demonstrated that TRIO could efficiently utilize storage bandwidth and reduce the average job I/O time by 37% on average for data-intensive applications in typical checkpointing scenarios.

Computer Science↗
DOE OSTI2015

TRIO: Burst Buffer Based I/O Orchestration

The growing computing power on leadership HPC systems is often accompanied by ever-escalating failure rates. Checkpointing is a common defensive mechanism used by scientific applications for failure recovery. However, directly writing the large and bursty checkpointing dataset to parallel filesystem can incur significant I/O contention on storage servers. Such contention in turn degrades the raw bandwidth utilization of storage servers and prolongs the average job I/O time of concurrent applications. Recently burst buffer has been proposed as an intermediate layer to absorb the bursty I/O traffic from compute nodes to storage backend. But an I/O orchestration mechanism is still desired to efficiently move checkpointing data from bursty buffers to storage backend. In this paper, we propose a burst buffer based I/O orchestration framework, named TRIO, to intercept and reshape the bursty writes for better sequential write traffic to storage severs. Meanwhile, TRIO coordinates the flushing orders among concurrent burst buffers to alleviate the contention on storage server bandwidth. Our experimental results reveal that TRIO can deliver 30.5% higher bandwidth and reduce the average job I/O time by 37% on average for data-intensive applications in various checkpointing scenarios.

Wang, Teng↗
DOE OSTI2014

BurstMem: A high-performance burst buffer system for scientific applications

The growth of computing power on large-scale systems requires commensurate high-bandwidth I/O systems. Many parallel file systems are designed to provide fast sustainable I/O in response to applications' soaring requirements. To meet this need, a novel system is imperative to temporarily buffer the bursty I/O and gradually flush datasets to long-term parallel file systems. In this paper, we introduce the design of BurstMem, a high-performance burst buffer system. BurstMem provides a storage framework with efficient storage and communication management strategies. Our experiments demonstrate that BurstMem is able to speed up the I/O performance of scientific applications by up to 8.5× on leadership computer systems.

Wang, Teng↗
NASA NTRS2013

Profiling and Improving I/O Performance of a Large-Scale Climate Scientific Application

Exascale computing systems are soon to emerge, which will pose great challenges on the huge gap between computing and I/O performance. Many large-scale scientific applications play an important role in our daily life. The huge amounts of data generated by such applications require highly parallel and efficient I/O management policies. In this paper, we adopt a mission-critical scientific application, GEOS-5, as a case to profile and analyze the communication and I/O issues that are preventing applications from fully utilizing the underlying parallel storage systems. Through in-detail architectural and experimental characterization, we observe that current legacy I/O schemes incur significant network communication overheads and are unable to fully parallelize the data access, thus degrading applications' I/O performance and scalability. To address these inefficiencies, we redesign its I/O framework along with a set of parallel I/O techniques to achieve high scalability and performance. Evaluation results on the NASA discover cluster show that our optimization of GEOS-5 with ADIOS has led to significant performance improvements compared to the original GEOS-5 implementation.

Exascale↗