Indexing techniques based on bitmap representations are known to improve query response time in a data warehouse environment. Specifically, bitmap indexing is a good method for improving complex and ad hoc queries without adding additional hardware. This method improves query processing using large numbers of fast Boolean operations and multiple index scans. By performing simple predicate conditions on the index level before going to the primary data source, the average query response time is improved. In this paper, we introduce Dual Bitmap Index that uses less space than existing bitmap indices while maintaining the same improvements in query processing speed. The Dual Bitmap Index represents each attribute value using only two bitmap vectors, with each bitmap vector representing many attribute values. This paper shows a comparative study of five bitmap indexing techniques, and shows that the Dual Bitmap Index is more efficient than the existing techniques for equality and membership queries from a space-time trade-off perspective.
The importance of properly optimizing code for execution on super-scalar processors was investigated. Access to the domain specialist was not available during the optimization investigation. For this study of an existing serial FORTRAN application, the use of compiler switches, manual coding techniques, a commercial preprocessor utility (KAP), and a commercial parallelization utility (FORGE) showed the potential to affect execution performance by more than an order of magnitude. The application for the case study was a three-dimensional boundary element code that modeled spherical particle transport phenomena in a particle suspension. Separate experiments were conducted using two different processor platforms: a four node IBM SP (160Mhz POWER2 CPU) and a single node DEC Alpha (667Mhz 21164 CPU).Execution times for the non-optimized, serial base case were 72 hours on a single IBM SP node and 66 hours on the DEC Alpha. Using a combination of compiler switches and manual optimizations, such as in-lining of inefficient subroutines, execution times were reduced to 7.5 hours on a single IBM SP node and 5.4 hours on the DEC Alpha. The use of the KAP pre-processor reduced execution time to 2.3 hours on the single IBM SP node. Using the parallelization software FORGE and four nodes on the IBM SP resulted in an execution time of 25.8 hours without compiler optimization and 3.0 hours using compiler switches for optimization.
This manuscript h a s been reproduced from the microfilm m aster. UMI films the text directly from the original or copy submitted. Thus, som e thesis and dissertation copies a re in typewriter face, while others may be from any type of computer printer.The quality o f th is reproduction is d ependent upon the q u aiity o f th e copy su b m itted . Broken or indistinct print, colored or poor quality illustrations and photographs, print bleedthrough, substandard margins, and improper alignment can adversely affect reproduction.In the unlikely event that the author did not send UMI a complete manuscript and tfiere are m issing pages, these will be noted. Also, if unauthorized copyright material had to be removed, a note will indicate the deletion.Oversize materials (e.g., maps, drawings, charts) are reproduced by sectioning the original, beginning at the upper left-hand comer and continuing from left to right in equal sections with small overlaps.Photographs included in the original manuscript have been reproduced xerographically in this copy.Higher quality 6" x 9" black and white photographic prints are available for any photographs or illustrations appearing in this copy for a n additional charge. Contact UMI directly to order.ProQ uest Information and Leaming 300 North Z eeb Road, Ann Arbor, Ml 48106-1346 USA 800-521-0600 I w ould like to express m y deepest thanks and e^preciation to my advisor. Prof. Sudarshan K. D hall, and m y co-advisor. Prof. S. L akshm ivarahan, for th eir confidence in m y w ork and me. T hey bo th have guided m e through the dissertation and p ro v id ed sup port and encouragem ent. W ithout them, I would n ev er have finished m y w ork o n th is p ro je c t They are the w ind beneath my wings. I have learned a lot form them b oth p ersonally and professionally. UMI TH E UNIVERSITY O F OKLAHOMA GRADUATE CO LLEG E POW ER-SPEED TRADE-O FF IN PARALLEL P R E F IX CIRCUITS A D issertation SU BM ITTED TO THE G R A D U A TE FACULTY POW ER-SPEED TRA D E-O FF IN PARALLEL PR E FIX CIRCUITSI am greatly indebted to Prof. John K. Antonio for his financial support, his kindness, and h is guidance during th e w ork as w ell as for his com m ents, suggestions, and support o n m y dissertation. I am very grateful to have had the o p p o rtu n i^ to work on his p ro je c t I ex ten d m y gratitude, appreciation and sincere thanks to D r. Le G ruenw ald fo r h er valuable guidance, and support through my study, and fo r serving on m y com m ittee. I also w ould like to thank Dr. A lbert Schw arzkopf fo r h is tim e and support w hile serv in g o n m y com m ittee.I w ould like to thank the T hai governm ent fo r b ringing m e to the U SA , an d fo r supporting m e financially and m otivating me. I w ould n o t dare to be in the States a ll by m yself.I w ould like to thank th e O klahom a Clim atological S urvey fo r giving m e an op p ortunity to w ork w ith them .A ll m y life, I have m et m any people and have m any good fiiends. I w ould like to th an k a ll o f them fo r touching m e and giving me t...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.