TY - CONF T1 - Finding comparable temporal categorical records: A similarity measure with an interactive visualization T2 - IEEE Symposium on Visual Analytics Science and Technology, 2009. VAST 2009 Y1 - 2009 A1 - Wongsuphasawat,K. A1 - Shneiderman, Ben KW - data visualisation KW - Educational institutions KW - Feedback KW - Information retrieval KW - interactive search tool KW - interactive systems KW - interactive visualization tool KW - large databases KW - M&M Measure KW - Match & Mismatch measure KW - Medical services KW - numerical time series KW - parameters customization KW - Particle measurements KW - Similan KW - similarity measure KW - Similarity Search KW - temporal categorical databases KW - Temporal Categorical Records KW - temporal databases KW - Testing KW - Time measurement KW - time series KW - transportation KW - usability KW - very large databases KW - visual databases KW - Visualization AB - An increasing number of temporal categorical databases are being collected: Electronic Health Records in healthcare organizations, traffic incident logs in transportation systems, or student records in universities. Finding similar records within these large databases requires effective similarity measures that capture the searcher's intent. Many similarity measures exist for numerical time series, but temporal categorical records are different. We propose a temporal categorical similarity measure, the M&M (Match & Mismatch) measure, which is based on the concept of aligning records by sentinel events, then matching events between the target and the compared records. The M&M measure combines the time differences between pairs of events and the number of mismatches. To accom-modate customization of parameters in the M&M measure and results interpretation, we implemented Similan, an interactive search and visualization tool for temporal categorical records. A usability study with 8 participants demonstrated that Similan was easy to learn and enabled them to find similar records, but users had difficulty understanding the M&M measure. The usability study feedback, led to an improved version with a continuous timeline, which was tested in a pilot study with 5 participants. JA - IEEE Symposium on Visual Analytics Science and Technology, 2009. VAST 2009 PB - IEEE SN - 978-1-4244-5283-5 M3 - 10.1109/VAST.2009.5332595 ER - TY - JOUR T1 - A tool to help tune where computation is performed JF - IEEE Transactions on Software Engineering Y1 - 2001 A1 - Eom, Hyeonsang A1 - Hollingsworth, Jeffrey K KW - Computational modeling KW - Current measurement KW - Distributed computing KW - distributed program KW - distributed programming KW - load balancing factor KW - Load management KW - parallel program KW - parallel programming KW - Performance analysis KW - performance evaluation KW - Performance gain KW - performance metric KW - Programming profession KW - software metrics KW - software performance evaluation KW - Testing KW - Time measurement KW - tuning AB - We introduce a new performance metric, called load balancing factor (LBF), to assist programmers when evaluating different tuning alternatives. The LBF metric differs from traditional performance metrics since it is intended to measure the performance implications of a specific tuning alternative rather than quantifying where time is spent in the current version of the program. A second unique aspect of the metric is that it provides guidance about moving work within a distributed or parallel program rather than reducing it. A variation of the LBF metric can also be used to predict the performance impact of changing the underlying network. The LBF metric is computed incrementally and online during the execution of the program to be tuned. We also present a case study that shows that our metric can accurately predict the actual performance gains for a test suite of six programs VL - 27 SN - 0098-5589 CP - 7 M3 - 10.1109/32.935854 ER - TY - CONF T1 - Predicting the CPU availability of time-shared Unix systems on the computational grid T2 - The Eighth International Symposium on High Performance Distributed Computing, 1999. Proceedings Y1 - 1999 A1 - Wolski,R. A1 - Spring, Neil A1 - Hayes,J. KW - accuracy KW - Application software KW - Autocorrelation KW - Availability KW - Central Processing Unit KW - computational grid KW - correlation methods KW - CPU availability prediction KW - CPU resources predictability KW - CPU sensor KW - Dynamic scheduling KW - grid computing KW - Load forecasting KW - long-range autocorrelation dependence KW - medium-term forecasts KW - network operating systems KW - Network Weather Service KW - NWS KW - performance evaluation KW - self-similarity degree KW - short-term forecasts KW - successive CPU measurements KW - Time measurement KW - Time sharing computer systems KW - time-shared Unix systems KW - time-sharing systems KW - Unix KW - Unix load average KW - vmstat utility KW - Weather forecasting AB - Focuses on the problem of making short- and medium-term forecasts of CPU availability on time-shared Unix systems. We evaluate the accuracy with which availability can be measured using the Unix load average, the Unix utility “vmstat” and the Network Weather Service (NWS) CPU sensor that uses both. We also examine the autocorrelation between successive CPU measurements to determine their degree of self-similarity. While our observations show a long-range autocorrelation dependence, we demonstrate how this dependence manifests itself in the short- and medium-term predictability of the CPU resources in our study JA - The Eighth International Symposium on High Performance Distributed Computing, 1999. Proceedings PB - IEEE SN - 0-7803-5681-0 M3 - 10.1109/HPDC.1999.805288 ER - TY - JOUR T1 - Critical path profiling of message passing and shared-memory programs JF - IEEE Transactions on Parallel and Distributed Systems Y1 - 1998 A1 - Hollingsworth, Jeffrey K KW - Computer Society KW - Concurrent computing KW - critical path computation KW - critical path profile KW - critical path zeroing KW - distributed processing KW - distributed shared memory systems KW - Instruments KW - Message passing KW - Monitoring KW - online algorithm KW - online critical path profiling KW - Parallel algorithms KW - program bottlenecks KW - Runtime KW - runtime nontrace-based algorithm KW - runtime overhead KW - shared-memory programs KW - system monitoring KW - Time measurement KW - Yarn AB - We introduce a runtime, nontrace-based algorithm to compute the critical path profile of the execution of message passing and shared-memory parallel programs. Our algorithm permits starting or stopping the critical path computation during program execution and reporting intermediate values. We also present an online algorithm to compute a variant of critical path, called critical path zeroing, that measures the reduction in application execution time that improving a selected procedure will have. Finally, we present a brief case study to quantify the runtime overhead of our algorithm and to show that online critical path profiling can be used to find program bottlenecks VL - 9 SN - 1045-9219 CP - 10 M3 - 10.1109/71.730530 ER -