@article{lakshminarasimhan_zou_boyuka_pendse_jenkins_vishwanath_papka_klasky_samatova_2014, title={DIRAQ: scalable in situ data- and resource-aware indexing for optimized query performance}, volume={17}, ISSN={["1573-7543"]}, DOI={10.1007/s10586-014-0358-z}, number={4}, journal={CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS}, author={Lakshminarasimhan, Sriram and Zou, Xiaocheng and Boyuka, David A., II and Pendse, Saurabh V. and Jenkins, John and Vishwanath, Venkatram and Papka, Michael E. and Klasky, Scott and Samatova, Nagiza F.}, year={2014}, month={Dec}, pages={1101–1119} }
 @article{jenkins_dinan_balaji_peterka_samatova_thakur_2014, title={Processing MPI Derived Datatypes on Noncontiguous GPU-Resident Data}, volume={25}, ISSN={["1558-2183"]}, DOI={10.1109/tpds.2013.234}, abstractNote={Driven by the goals of efficient and generic communication of noncontiguous data layouts in GPU memory, for which solutions do not currently exist, we present a parallel, noncontiguous data-processing methodology through the MPI datatypes specification. Our processing algorithm utilizes a kernel on the GPU to pack arbitrary noncontiguous GPU data by enriching the datatypes encoding to expose a fine-grained, data-point level of parallelism. Additionally, the typically tree-based datatype encoding is preprocessed to enable efficient, cached access across GPU threads. Using CUDA, we show that the computational method outperforms DMA-based alternatives for several common data layouts as well as more complex data layouts for which reasonable DMA-based processing does not exist. Our method incurs low overhead for data layouts that closely match best-case DMA usage or that can be processed by layout-specific implementations. We additionally investigate usage scenarios for data packing that incur resource contention, identifying potential pitfalls for various packing strategies. We also demonstrate the efficacy of kernel-based packing in various communication scenarios, showing multifold improvement in point-to-point communication and evaluating packing within the context of the SHOC stencil benchmark and HACC mesh analysis.}, number={10}, journal={IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS}, author={Jenkins, John and Dinan, James and Balaji, Pavan and Peterka, Tom and Samatova, Nagiza F. and Thakur, Rajeev}, year={2014}, month={Oct}, pages={2627–2637} }
 @article{boyuka_lakshminarasimhan_zou_gong_jenkins_schendel_podhorszki_liu_klasky_samatova_2014, title={Transparent In Situ Data Transformations in ADIOS}, ISSN={["2376-4414"]}, DOI={10.1109/ccgrid.2014.73}, abstractNote={Though an abundance of novel "data transformation" technologies have been developed (such as compression, level-of-detail, layout optimization, and indexing), there remains a notable gap in the adoption of such services by scientific applications. In response, we develop an in situ data transformation framework in the ADIOS I/O middleware with a "plug in" interface, thus greatly simplifying both the deployment and use of data transform services in scientific applications. Our approach ensures user-transparency, runtime-configurability, compatibility with existing I/O optimizations, and the potential for exploiting read-optimizing transforms (such as level-of-detail) to achieve I/O reduction. We demonstrate use of our framework with the QLG simulation at up to 8,192 cores on the leadership-class Titan supercomputer, showing negligible overhead. We also explore the read performance implications of data transforms with respect to parameters such as chunk size, access pattern, and the "opacity" of different transform methods including compression and level-of-detail.}, journal={2014 14TH IEEE/ACM INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND GRID COMPUTING (CCGRID)}, author={Boyuka, David A., II and Lakshminarasimhan, Sriram and Zou, Xiaocheng and Gong, Zhenhuan and Jenkins, John and Schendel, Eric R. and Podhorszki, Norbert and Liu, Qing and Klasky, Scott and Samatova, Nagiza F.}, year={2014}, pages={256–266} }
 @article{jenkins_kanj_xia_zhang_2012, title={Local construction of spanners in the 3D space}, volume={11}, number={7}, journal={IEEE Transactions on Mobile Computing}, author={Jenkins, J. P. and Kanj, I. A. and Xia, G. and Zhang, F. H.}, year={2012}, pages={1140–1150} }
 @article{gong_lakshminarasimhan_jenkins_kolla_ethier_chen_ross_klasky_samatova_2012, title={Multi-level Layout Optimization for Efficient Spatio-temporal Queries on ISABELA-compressed Data}, ISSN={["1530-2075"]}, DOI={10.1109/ipdps.2012.83}, abstractNote={The size and scope of cutting-edge scientific simulations are growing much faster than the I/O subsystems of their runtime environments, not only making I/O the primary bottleneck, but also consuming space that pushes the storage capacities of many computing facilities. These problems are exacerbated by the need to perform data-intensive analytics applications, such as querying the dataset by variable and spatio-temporal constraints, for what current database technologies commonly build query indices of size greater than that of the raw data. To help solve these problems, we present a parallel query-processing engine that can handle both range queries and queries with spatio-temporal constraints, on B-spline compressed data with user-controlled accuracy. Our method adapts to widening gaps between computation and I/O performance by querying on compressed metadata separated into bins by variable values, utilizing Hilbert space-filling curves to optimize for spatial constraints and aggregating data access to improve locality of per-bin stored data, reducing the false positive rate and latency bound I/O operations (such as seek) substantially. We show our method to be efficient with respect to storage, computation, and I/O compared to existing database technologies optimized for query processing on scientific data.}, journal={2012 IEEE 26TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS)}, author={Gong, Zhenhuan and Lakshminarasimhan, Sriram and Jenkins, John and Kolla, Hemanth and Ethier, Stephane and Chen, Jackie and Ross, Robert and Klasky, Scott and Samatova, Nagiza F.}, year={2012}, pages={873–884} }
 @book{jenkins_zou_tang_kimpe_ross_samatova, title={Parallel data layout optimization of scientific data through access-driven replication}, journal={Technical Report- Not held in TRLN member libraries}, author={Jenkins, J. P. and Zou, X. and Tang, H. and Kimpe, D. and Ross, R. and Samatova, N. F.} }