Changeset 958


Ignore:
Timestamp:
Mar 20, 2011, 6:52:19 PM (8 years ago)
Author:
cameron
Message:

XML performance refs

File:
1 edited

Legend:

Unmodified
Added
Removed
  • docs/PACT2011/reference.bib

    r956 r958  
    213213 keywords = {UTF-16, UTF-8, parallel bit streams, simd text processing, transcoding},
    214214}
     215
     216@incollection {ParaDOM2009,
     217   author = {Shah, Bhavik and Rao, Praveen and Moon, Bongki and Rajagopalan, Mohan},
     218   affiliation = {University of Missouri-Kansas City},
     219   title = {A Data Parallel Algorithm for XML DOM Parsing},
     220   booktitle = {Database and XML Technologies},
     221   series = {Lecture Notes in Computer Science},
     222   editor = {BellahsÚne, Zohra and Hunt, Ela and Rys, Michael and Unland, Rainer},
     223   publisher = {Springer Berlin / Heidelberg},
     224   isbn = {},
     225   pages = {75-90},
     226   volume = {5679},
     227   url = {http://dx.doi.org/10.1007/978-3-642-03555-5_7},
     228   note = {10.1007/978-3-642-03555-5_7},
     229   year = {2009}
     230}
     231
     232@inproceedings{ApparaoBhat04,
     233author = {Apparao, P. and Bhat, M.},
     234title = "{A Detailed Look at the Characteristics of {XML} Parsing}",
     235booktitle = {Proceedings of the 1st Workshop on Building Block Engine Architectures
     236for Computers and Networks (BEACON '04)},
     237address = {Boston, MA},
     238month=oct, year=2004}
     239
     240
     241
     242@misc{TR:XML,
     243author = {Bray, Tim and Paoli, Jean and Sperberg-McQueen, C. M. and
     244    Maler, Eve and Yergeau, François},
     245title = {Extensible Markup Language ({XML}) 1.0 (Fifth Edition)},
     246howpublished={W3C  Recommendation},
     247mon=nov, year=2008}
     248
     249
     250
     251
     252@inproceedings{XMLScreamer,
     253author = "{Kostoulas, M. G., Matsa, M., Mendelsohn, N., Perkins, E., Heifets, A., and Mercaldi, M.}",
     254title = "{{XML} Screamer: An Integrated Approach to High Performance {XML} Parsing, Validation and Deserialization}",
     255booktitle = {Proceedings of the 15th International Conference on World Wide Web (WWW '06)},
     256pages = {93--102}, year=2006
     257}
     258
     259@inproceedings{NicolaJohn03,
     260author = "{Nicola, Matthias, and John, Jasmi}",
     261title = "{XML Parsing: A Threat to Database Performance}",
     262booktitle = {Proceedings of the Twelfth International Conference on Information and
     263Knowledge Management},
     264address = {New Orleans, Louisiana}, year=2003}
     265
     266@inproceedings{Perkins05,
     267author = "{Perkins, E., Kostoulas, M., Heifets, A., Matsa, M., and Mendelsohn, N.}",
     268title = "{Performance Analysis of {XML} APIs}",
     269booktitle = {XML 2005}, address = {Atlanta, Georgia}, month=nov, year=2005}
     270
     271@inproceedings{Psaila06,
     272author = "{Psaila, Giuseppe}",
     273title = "{On the Problem of Coupling Java Algorithms and {XML} Parsers}",
     274booktitle = {17th International Conference on Database and Expert Systems Applications (DEXA'06)},
     275mon=sep, year=2006, pages = {487--491}
     276}
     277
     278
     279@inproceedings{ZhaoBhuyan06,
     280author = "{Zhao, Li \and Laxmi Bhuyan}",
     281title = "{Performance Evaluation and Acceleration for {XML} Data Parsing}",
     282booktitle = "{9th Workshop on Computer Architecture Evaluation using Commercial Workloads (CAECW)}",
     283mon=feb, year=2006, address="{Austin, Texas}"
     284}
     285
     286@inproceedings{PPoPP08,
     287author = {Cameron, Robert D.},
     288title = "{A Case Study in SIMD Text Processing with Parallel Bit Streams}",
     289booktitle = "{ACM Symposium on Principles and Practice of Parallel Programming (PPoPP)}",
     290mon=feb, year=2008, address="{Salt Lake City, Utah}"
     291}
     292
     293@inproceedings{DuCharme04,
     294author = {DuCharme, Bob},
     295title = "Documents vs. Data, Schemas vs. Schemas",
     296booktitle = "{XML 2004}",
     297mon=nov, year=2004, address="{Washington D.C.}"
     298}
     299
     300@inbook{GML04,
     301  author = {Lake, Ron and Burggraf, David and Trninic, Milan and Rae, Laurie},
     302  title = {Geography Mark-Up Language: Foundation for the Geo-Web},
     303  publisher = "John Wiley \& Sons, Inc.",
     304  year = 2004,
     305  pages = "3--4"
     306}
     307
     308@misc{expat,
     309  author = {Clark, James},
     310  title  = "{The Expat {XML} Parser}",
     311  howpublished = "{http://expat.sourceforge.net/}"
     312}
     313
     314@misc{xerces,
     315  title = "{Xerces C++ Parser}",
     316  howpublished = "{http://xerces.apache.org/xerces-c/}"
     317}
     318
     319@misc{papi,
     320  title = "{Performance Application Programming Interface}",
     321  howpublished = "{http://icl.cs.utk.edu/papi/}"
     322}
     323
     324@misc{perfctr,
     325  author = "{Pettersson, Michael}",     
     326  title = "{Linux x86 Performance-Monitoring Counters Driver}",
     327  howpublished = "{http://user.it.uu.se/~mikpe/linux/perfctr}"
     328}
     329
     330@manual{IntelArchOptRefMan,
     331  title = "{IA-32 Intel Architecture Optimization Reference Manual}",
     332  organization = "{Intel Corporation}",
     333  year = 2005,
     334}
     335
     336@inproceedings{Ross07,
     337author = {Ross, Kenneth A.},
     338title = "{Efficient Hash Probes on Modern Processors}",
     339booktitle = "{Proceedings of the 23rd International Conference on Data Engineering (ICDE 2007)}",
     340address="{Istanbul, Turkey}",
     341mon=apr,
     342year=2007}
     343
     344@misc{XMLSSE42,
     345author={Lei, Zhai},
     346title = {{XML} Parsing Accelerator with Intel® Streaming {SIMD} Extensions 4 (Intel® {SSE4})},
     347  organization = "{Intel Corporation}",
     348howpublished = "{http://software.intel.com/en-us/articles/xml-parsing-accelerator-with-intel-streaming-simd-extensions-4-intel-sse4/}",
     349year=2008}
     350
     351@inproceedings{DaiNiZhu2010,
     352 author = {Dai, Zefu and Ni, Nick and Zhu, Jianwen},
     353 title = {A 1 Cycle-per-Byte {XML} Parsing Accelerator},
     354 booktitle = {FPGA '10: Proceedings of the 18th Annual ACM/SIGDA International Symposium on Field Programmable Gate Arrays},
     355 year = {2010},
     356 isbn = {978-1-60558-911-4},
     357 pages = {199--208},
     358 location = {Monterey, California, USA},
     359 doi = {http://doi.acm.org.proxy.lib.sfu.ca/10.1145/1723112.1723148},
     360 publisher = {ACM},
     361 address = {New York, NY, USA},
     362 }
     363
     364@inproceedings{Cameron2009,
     365author ={Cameron, Rob and Herdy, Ken and Amiri, Ehsan},
     366 title = {Parallel Bit Stream Technology as a Foundation for {XML} Parsing Performance},
     367booktitle = {International Symposium on Processing {XML} Efficiently: Overcoming Limits on Space, Time, or Bandwidth},
     368 location = {Montréal, Canada},
     369 month=aug, year=2009,
     370doi={10.4242/BalisageVol4.Cameron01}}
     371 
     372@inproceedings{Leventhal2009,
     373author ={Leventhal, Michael and Lemoine, Eric},
     374title = {The {XML} Chip at 6 Years},
     375booktitle = {International Symposium on Processing {XML} Efficiently: Overcoming Limits on Space, Time, or Bandwidth},
     376 location = {Montréal, Canada},
     377 month=aug, year=2009,
     378doi={10.4242/BalisageVol4.Leventhal01}}
     379
     380@inproceedings{WuZhangYuLi2008,
     381author = {Wu, Yu and Zhang, Qi and Yu, Zhiqiang and Li, Jianhui},
     382title = {A Hybrid Parallel Processing for {XML} Parsing and Schema Validation},
     383booktitle = {Balisage: The Markup Conference 2008},
     384 location = {Montréal, Canada},
     385 month = aug, year = 2008,
     386 doi={10.4242/BalisageVol1.Wu01}}
     387
     388@inproceedings{HilewitzLee2006,
     389 author = {Hilewitz, Yedidya and Lee, Ruby B.},
     390 title = {Fast Bit Compression and Expansion with Parallel Extract and Parallel Deposit Instructions},
     391 booktitle = {{ASAP} '06: Proceedings of the IEEE 17th International Conference on Application-specific Systems, Architectures and Processors},
     392 year = {2006},
     393 isbn = {0-7695-2682-9},
     394 pages = {65--72},
     395 doi = {http://dx.doi.org/10.1109/ASAP.2006.33},
     396 publisher = {IEEE Computer Society},
     397 address = {Washington, DC, USA},
     398 }
     399
     400@inproceedings{CameronLin2009,
     401 author = {Cameron, Robert D. and Lin, Dan},
     402 title = {Architectural support for SWAR text processing with parallel bit streams: the inductive doubling principle},
     403 booktitle = {{ASPLOS} '09: Proceeding of the 14th international conference on Architectural support for programming languages and operating systems},
     404 year = {2009},
     405 isbn = {978-1-60558-406-5},
     406 pages = {337--348},
     407 location = {Washington, DC, USA},
     408 doi = {http://doi.acm.org/10.1145/1508244.1508283},
     409 publisher = {ACM},
     410 address = {New York, NY, USA},
     411 }
     412
     413@inproceedings{CameronHerdyLin2008,
     414 author = {Cameron, Robert D. and Herdy, Kenneth S. and Lin, Dan},
     415 title = {High performance {XML} parsing using parallel bit stream technology},
     416 booktitle = {{CASCON} '08: Proceedings of the 2008 conference of the center for advanced studies on collaborative research},
     417 year = {2008},
     418 pages = {222--235},
     419 location = {Ontario, Canada},
     420 doi = {http://doi.acm.org/10.1145/1463788.1463811},
     421 publisher = {ACM},
     422 address = {New York, NY, USA},
     423 }
     424
     425@techreport{Asanovic:EECS-2006-183,
     426    Author = {Asanovic, Krste and Bodik, Ras and Catanzaro, Bryan Christopher and Gebis, Joseph James and Husbands, Parry and Keutzer, Kurt and Patterson, David A. and Plishker, William Lester and Shalf, John and Williams, Samuel Webb and Yelick, Katherine A.},
     427    Title = {The Landscape of Parallel Computing Research: A View from Berkeley},
     428    Institution = {EECS Department, University of California, Berkeley},
     429    Year = {2006},
     430    Month = {Dec},
     431    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-183.html},
     432    Number = {UCB/EECS-2006-183},
     433    Abstract = {The recent switch to parallel microprocessors is a milestone in the history of computing. Industry has laid out a roadmap for multicore designs that preserves the programming paradigm of the past via binary compatibility and cache coherence. Conventional wisdom is now to double the number of cores on a chip with each silicon generation.
     434
     435A multidisciplinary group of Berkeley researchers met nearly two years to discuss this change. Our view is that this evolutionary approach to parallel hardware and software may work from 2 or 8 processor systems, but is likely to face diminishing returns as 16 and 32 processor systems are realized, just as returns fell with greater instruction-level parallelism.
     436
     437We believe that much can be learned by examining the success of parallelism at the extremes of the computing spectrum, namely embedded computing and high performance computing. This led us to frame the parallel landscape with seven questions, and to recommend the following:
     438<ul>
     439<li>The overarching goal should be to make it easy to write programs that execute efficiently on highly parallel computing systems
     440<li>The target should be 1000s of cores per chip, as these chips are built from processing elements that are the most efficient in MIPS (Million Instructions per Second) per watt, MIPS per area of silicon, and MIPS per development dollar.
     441<li>Instead of traditional benchmarks, use 13 "Dwarfs" to design and evaluate parallel programming models and architectures. (A dwarf is an algorithmic method that captures a pattern of computation and communication.)
     442<li>"Autotuners" should play a larger role than conventional compilers in translating parallel programs.
     443<li>To maximize programmer productivity, future programming models must be more human-centric than the conventional focus on hardware or applications.
     444<li>To be successful, programming models should be independent of the number of processors.
     445<li>To maximize application efficiency, programming models should support a wide range of data types and successful models of parallelism: task-level parallelism, word-level parallelism, and bit-level parallelism.
     446<li>Architects should not include features that significantly affect performance or energy if programmers cannot accurately measure their impact via performance counters and energy counters.
     447<li>Traditional operating systems will be deconstructed and operating system functionality will be orchestrated using libraries and virtual machines.
     448<li>To explore the design space rapidly, use system emulators based on Field Programmable Gate Arrays (FPGAs) that are highly scalable and low cost.
     449</ul>
     450
     451Since real world applications are naturally parallel and hardware is naturally parallel, what we need is a programming model, system software, and a supporting architecture that are naturally parallel. Researchers have the rare opportunity to re-invent these cornerstones of computing, provided they simplify the efficient programming of highly parallel systems.}
     452}
     453
     454@INPROCEEDINGS{ZhangPanChiu09,
     455author={Ying Zhang and Yinfei Pan and Chiu, Kenneth},
     456booktitle={High Performance Computing (HiPC), 2009 International Conference on}, title={Speculative p-DFAs for parallel XML parsing},
     457year={2009},
     458month=dec,
     459volume={},
     460number={},
     461pages={388--397},
     462keywords={Intel Xeon L5320 CPU;Linux machine;Solaris;Sun E6500 machine;parallel XML parsing;preparsing stage;product machines;scientific computing environment;skeleton;speculative p-DFA;statistics;unmodified libxml2;wide-scale grid environment;XML;document handling;open systems;parallel processing;statistical analysis;},
     463doi={10.1109/HIPC.2009.5433187},
     464ISSN={},}
     465
     466@inproceedings{Scarpazza:2009,
     467 author = {Scarpazza, Daniele Paolo and Russell, Gregory F.},
     468 title = {High-performance regular expression scanning on the Cell/B.E. processor},
     469 booktitle = {Proceedings of the 23rd international conference on Supercomputing},
     470 series = {ICS '09},
     471 year = {2009},
     472 isbn = {978-1-60558-498-0},
     473 location = {Yorktown Heights, NY, USA},
     474 pages = {14--25},
     475 numpages = {12},
     476 url = {http://doi.acm.org/10.1145/1542275.1542284},
     477 doi = {http://doi.acm.org/10.1145/1542275.1542284},
     478 acmid = {1542284},
     479 publisher = {ACM},
     480 address = {New York, NY, USA},
     481 keywords = {cell processor, multi-core, regular expressions},
     482}
     483@inproceedings{Herdy2008,
     484title={High Performance {GML} to {SVG} Transformation for the Visual Presentation of Geographic Data in Web-Based Mapping Systems},
     485author = {Herdy, Kenneth S. and Burggraf, David S. and Cameron, Robert D.},
     486booktitle = {Proceedings of {SVG} Open 2008},
     487year = {2008},
     488location={Nuremburg, Germany},
     489month=aug}
     490
     491
Note: See TracChangeset for help on using the changeset viewer.