@article{zhang_tang_zou_harenberg_liu_klasky_samatova_2015, title={Exploring Memory Hierarchy to Improve Scientific Data Read Performance}, ISSN={["1552-5244"]}, DOI={10.1109/cluster.2015.18}, abstractNote={Improving read performance is one of the major challenges with speeding up scientific data analytic applications. Utilizing the memory hierarchy is one major line of researches to address the read performance bottleneck. Related methods usually combine solide-state-drives(SSDs) with dynamic random-access memory(DRAM) and/or parallel file system(PFS) to mitigate the speed and space gap between DRAM and PFS. However, these methods are unable to handle key performance issues plaguing SSDs, namely read contention that may cause up to 50% performance reduction. In this paper, we propose a framework that exploits the memory hierarchy resource to address the read contention issues involved with SSDs. The framework employs a general purpose online read algorithm that able to detect and utilize memory hierarchy resource to relieve the problem. To maintain a near optimal operating environment for SSDs, the framework is able to orchastrate data chunks across different memory layers to facilitate the read algorithm. Compared to existing tools, our framework achieves up to 50% read performance improvement when tested on datasets from real-world scientific simulations.}, journal={2015 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING - CLUSTER 2015}, author={Zhang, Wenzhao and Tang, Houjun and Zou, Xiaocheng and Harenberg, Steven and Liu, Qing and Klasky, Scott and Samatova, Nagiza F.}, year={2015}, pages={66–69} }
 @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} }