@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} }
 @inproceedings{schendel_harenberg_tang_vishwanath_papka_samatova_2013, title={A generic high-performance method for deinterleaving scientific data}, volume={8097}, DOI={10.1007/978-3-642-40047-6_58}, abstractNote={High-performance and energy-efficient data management applications are a necessity for HPC systems due to the extreme scale of data produced by high fidelity scientific simulations that these systems support. Data layout in memory hugely impacts the performance. For better performance, most simulations interleave variables in memory during their calculation phase, but deinterleave the data for subsequent storage and analysis. As a result, efficient data deinterleaving is critical; yet, common deinterleaving methods provide inefficient throughput and energy performance. To address this problem, we propose a deinterleaving method that is high performance, energy efficient, and generic to any data type. To the best of our knowledge, this is the first deinterleaving method that 1) exploits data cache prefetching, 2) reduces memory accesses, and 3) optimizes the use of complete cache line writes. When evaluated against conventional deinterleaving methods on 105 STREAM standard micro-benchmarks, our method always improved throughput and throughput/watt on multi-core systems. In the best case, our deinterleaving method improved throughput up to 26.2x and throughput/watt up to 7.8x.}, booktitle={Euro-par 2013 parallel processing}, author={Schendel, E. R. and Harenberg, S. and Tang, H. J. and Vishwanath, V. and Papka, M. E. and Samatova, N. F.}, year={2013}, pages={571–582} }
 @inproceedings{jenkins_schendel_lakshminarasimhan_boyuka_rogers_ethier_ross_klasky_samatova_2012, title={Byte-precision level of detail processing for variable precision analytics}, DOI={10.1109/sc.2012.26}, abstractNote={I/O bottlenecks in HPC applications are becoming a more pressing problem as compute capabilities continue to outpace I/O capabilities. While double-precision simulation data often must be stored losslessly, the loss of some of the fractional component may introduce acceptably small errors to many types of scientific analyses. Given this observation, we develop a precision level of detail (APLOD) library, which partitions double-precision datasets along user-defined byte boundaries. APLOD parameterizes the analysis accuracy-I/O performance tradeoff, bounds maximum relative error, maintains I/O access patterns compared to full precision, and operates with low overhead. Using ADIOS as an I/O use-case, we show proportional reduction in disk access time to the degree of precision. Finally, we show the effects of partial precision analysis on accuracy for operations such as k-means and Fourier analysis, finding a strong applicability for the use of varying degrees of precision to reduce the cost of analyzing extreme-scale data.}, booktitle={International conference for high performance computing networking}, author={Jenkins, J. and Schendel, E. R. and Lakshminarasimhan, S. and Boyuka, D. A. and Rogers, T. and Ethier, S. and Ross, R. and Klasky, S. and Samatova, N. F.}, year={2012} }
 @article{schendel_jin_shah_chen_chang_ku_ethier_klasky_latham_ross_et al._2012, title={ISOBAR Preconditioner for Effective and High-throughput Lossless Data Compression}, ISSN={["1084-4627"]}, DOI={10.1109/icde.2012.114}, abstractNote={Efficient handling of large volumes of data is a necessity for exascale scientific applications and database systems. To address the growing imbalance between the amount of available storage and the amount of data being produced by high speed (FLOPS) processors on the system, data must be compressed to reduce the total amount of data placed on the file systems. General-purpose loss less compression frameworks, such as zlib and bzlib2, are commonly used on datasets requiring loss less compression. Quite often, however, many scientific data sets compress poorly, referred to as hard-to-compress datasets, due to the negative impact of highly entropic content represented within the data. An important problem in better loss less data compression is to identify the hard-to-compress information and subsequently optimize the compression techniques at the byte-level. To address this challenge, we introduce the In-Situ Orthogonal Byte Aggregate Reduction Compression (ISOBAR-compress) methodology as a preconditioner of loss less compression to identify and optimize the compression efficiency and throughput of hard-to-compress datasets.}, journal={2012 IEEE 28TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE)}, author={Schendel, Eric R. and Jin, Ye and Shah, Neil and Chen, Jackie and Chang, C. S. and Ku, Seung-Hoe and Ethier, Stephane and Klasky, Scott and Latham, Robert and Ross, Robert and et al.}, year={2012}, pages={138–149} }
 @inproceedings{jenkins_arkatkar_lakshminarasimhan_boyuka_schendel_shah_ethier_chang_chen_kolla_et al., title={ALACRITY: Analytics-driven lossless data compression for rapid in-situ indexing, storing, and querying}, volume={8220}, booktitle={Transactions on large-scale data- and knowledge- centered systems x: special issue on database- and expert-systems applications}, author={Jenkins, J. and Arkatkar, I. and Lakshminarasimhan, S. and Boyuka, D. A. and Schendel, E. R. and Shah, N. and Ethier, S. and Chang, C. S. and Chen, J. and Kolla, H. and et al.}, pages={95–114} }